What is Clustering?

.

Clustering is an unsupervised machine learning technique that divides the population into several groups or clusters such that data points in the same group are similar to each other, and data points in different groups are dissimilar.

Clustering is used to identify some segments or groups in the dataset.

Clustering can be divided into two subgroups:

(1) Hard Clustering.

In hard clustering, each data point is clustered or grouped to any one cluster. For each data point, it may either completely belong to a cluster or not. 

K-Means Clustering is a hard clustering algorithm. It clusters data points into k-clusters. 

(2) Soft Clustering.

In soft clustering, instead of putting each data points into separate clusters, a probability of that point to be in that cluster assigned. In soft clustering or fuzzy clustering, each data point can belong to multiple clusters along with its probability score or likelihood.

One of the widely used soft clustering algorithms is the Fuzzy C-means clustering (FCM) Algorithm.

.

https://towardsdatascience.com/fuzzy-c-means-clustering-is-it-better-than-k-means-clustering-448a0aba1ee7

.

.

Clustering is a unsupervised Machine learning algorithm. In unsupervised learning , you have only input data and no output data. Unsupervised learning is used to find pattern in given data in order learn more about data.

.

https://medium.com/@codingpilot25/clustering-explained-to-beginners-of-data-science-e25d73c77a24

.

Cluster analysis or clustering is the most commonly used technique of unsupervised learning. It is used to find data clusters such that each cluster has the most closely matched data.

.

.

The types of Clustering Algorithms are:

1.Prototype-Based Clustering

2.Graph-Based Clustering (Contiguity-Based Clustering)

3.Density-Based Clustering

4.Well Separated Clustering

.

.

https://github.com/VijayPrakashReddy-k/Machine_Learning#iclustering

.

What is the difference between K Means and Hierarchical Clustering?

.

k-means is method of cluster analysis using a pre-specified no. of clusters. It requires advance knowledge of ‘K’. 

Hierarchical clustering also known as hierarchical cluster analysis (HCA) is also a method of cluster analysis which seeks to build a hierarchy of clusters without having fixed number of cluster. 

Main differences between K means and Hierarchical Clustering are: 

k-means Clustering	Hierarchical Clustering
k-means, using a pre-specified  number of clusters, the method  assigns records to each cluster to  find the mutually exclusive cluster  of spherical shape based on distance.	Hierarchical methods can be either divisive or agglomerative.
K Means clustering needed advance knowledge of K i.e. no. of clusters one want to divide your data.	In hierarchical clustering one can stop at any number of clusters, one find appropriate by interpreting the dendrogram.
One can use median or mean as a cluster centre to represent each cluster.	Agglomerative methods  begin with ‘n’ clusters and sequentially combine similar clusters until only one cluster is obtained.
Methods used are normally less computationally intensive and are suited with very large datasets.	Divisive methods work in the opposite direction, beginning with one cluster that includes all the records and Hierarchical methods are especially useful when the target is to arrange the clusters into a natural hierarchy.
In K Means clustering, since one start with random choice of clusters, the results produced by running the algorithm many times may differ.	In Hierarchical Clustering, results are reproducible in Hierarchical clustering
K- means clustering a simply a division of the set of data objects into non-overlapping subsets (clusters) such that each  data object is in exactly one subset).	A hierarchical clustering is a set of nested clusters that are arranged as a tree.
K Means clustering is found to work well when the structure of the clusters is hyper spherical (like circle in 2D,  sphere in 3D).	Hierarchical clustering don’t work  as well as, k means when the  shape of the clusters is hyper  spherical.
Advantages: 1. Convergence is guaranteed. 2. Specialized to clusters of different sizes and shapes.	Advantages:  1 .Ease of handling of any forms of similarity or distance. 2. Consequently, applicability to any attributes types.
Disadvantages: 1. K-Value is difficult to predict 2. Didn’t work well with global cluster.	Disadvantage: 1. Hierarchical clustering requires the computation and storage of an n×n  distance matrix. For very large datasets, this can be expensive and slow

 

.

https://www.geeksforgeeks.org/difference-between-k-means-and-hierarchical-clustering

.

What is hierarchical clustering analysis?

 .

In data mining and statistics, hierarchical clustering analysis is a method of cluster analysis that seeks to build a hierarchy of clusters i.e. tree-type structure based on the hierarchy. 

Basically, there are two types of hierarchical cluster analysis strategies –

1. Agglomerative Clustering: Also known as bottom-up approach or hierarchical agglomerative clustering (HAC). A structure that is more informative than the unstructured set of clusters returned by flat clustering. This clustering algorithm does not require us to prespecify the number of clusters. Bottom-up algorithms treat each data as a singleton cluster at the outset and then successively agglomerates pairs of clusters until all clusters have been merged into a single cluster that contains all data. 

2. Divisive clustering: Also known as a top-down approach. This algorithm also does not require to prespecify the number of clusters. Top-down clustering requires a method for splitting a cluster that contains the whole data and proceeds by splitting clusters recursively until individual data have been split into singleton clusters.

.

https://www.geeksforgeeks.org/ml-hierarchical-clustering-agglomerative-and-divisive-clustering/

.

Google Scholar Search Tips

.

Google / Google Scholar Search Tips

Getting started

• Decide what you’re looking for.

• Choose as many descriptive words as needed; include as many synonyms as you can think of. 

o Too few words may give poor results.

o The Google search box accepts up to 32 words.

o Select distinctive words; avoid stop words (unnecessary works that can skew your search). • Explore Search Settings to set your Google preferences.

Google search conventions

• Search words are not case-sensitive

o Enter keywords in upper or lower case, or both: Circles, circles, CIRCLES

o Exception: Boolean operator OR

▪ Find apartments in Bethlehem or Allentown:

apartments bethlehem OR allentown (OR must be in caps)

• Boolean operator AND is assumed

o If no operators are entered, results will contain all words entered

▪ Find apartments in Bethlehem and Allentown:

apartments bethlehem allentown

▪ Find information about Si Lewen’s painting series Eva:

si lewen eva

• Word order matters

o Google ranks the first word slightly higher than the first, the second over the third, etc. ▪ offender parole (results are slightly different from parole offender)

• Google ignores most punctuation and symbols. Exceptions:

o Dollar sign when used to indicate price

▪ hp $300 gives different results than hp 300

o Underscore or hyphen when used to connect words

▪ mother-in-law

▪ do_not_resucsitate  

o Symbols when used to convey meaning, as in a programming language (C++), musical  terms (F#), etc.

Search Operators

Operator	Description	Examples
“ “	Exact phrase search o Search for words in order entered o Use double quotes at beginning  and end of phrase	“family group conference” “9 affects” “dreaming of a new reality”

 

 

Operator	Description	Examples
-	Exclude words from results o Type a minus sign before the word  or phrase to eliminate o Same as Boolean NOT	“restorative practices” –dentistry books wachtel -baruch
site:	Restrict search to specific domain or  website o Search top-level   domains: .edu, .org, .com, .gov, net, etc. o Search within a specific country’s  domain. List of country codes	Find volunteer opportunities in  Philadelphia at non-profit   organizations: volunteering Philadelphia site:org Information about graduate   certificates from IIRP “graduate certificate” site:iirp.edu Restorative practices related to  indigenous communities in Canada restorative “indigenous communities”  site:.ca
*	Whole word wildcard o Searches for missing word in a  phrase search	“joseph * biden” retrieves o Joseph Biden o Joseph R. Biden o Joseph Robinette Biden “president * signed the executive  order”
…	Numeric range search o number…number	Find tablet devices that cost $100 to  $300 tablets $100…$300
allintext:	Search for multiple words in the body of  the search result o Restricts results to pages that have  all query words in body of the   document o Use with individual words only; for  phrases, use intext:	Find information on email fraud in  Microsoft Outlook allintext:outlook email fraud
intext:	Search for single word or phrase in body  of the search result o Restricts results to pages that have  the query word or phrase in body  of the document	Learn about grants to criminal justice  programs given by the Macarthur  Foundation allintext:grants criminal   intext:”macarthur foundation”

 

 

Operator	Description	Examples
	o Use double quotes to enclose multi word phrases
allintitle:	Search for multiple words in the title of  the search result o Restricts results to pages that have  all query words in title of the page o Use with individual words only; for  phrases, use intitle: Hint: Searching for words/phrases in titles  can help maximize the relevance of your  search	Find information on discrimination  against LGBTQ youth allintitle:lgbtq youth discrimination
intitle:	Search for single word or phrase in title  of the search result o Restricts results to pages that have  the query word or phrase in title of  the document o Use double quotes to enclose multi word phrases Hint: Searching for words/phrases in titles  can help maximize the relevance of your  search	Find information on using narrative  therapy in working with traumatized  children children trauma intitle:”narrative  therapy”
define:	Search for definitions of terms from  various web sources. o Use operator with or without colon o With colon: Results are restricted to  a list of definitions o Without colon: Results are   broadened to include dictionary   definitions plus other relevant   pages	define:civil society define affect theory
filetype:	Restrict your search to a specific file type o No space between filetype: and  the following extension o List of filetypes returned in  Google searches	Find handbooks in PDF format on  facilitating circles Handbook facilitating circles   filetype:pdf
movie:	Searches for showtimes by location or  specific movie	What’s playing in Center Valley, PA? movie:18034 Find showtimes and reviews for Justice  League near Freehold, NJ movie:07728 movie:justice league

 

 

SOURCE:

IIRP Graduate School Library >External Databases - Free Public Resources

https://www.iirp.edu/library/external-databases-resources

-Google Scholar Overview

--https://scholar.google.com/intl/en/scholar/help.html#overview

-Google Scholar tips

--https://www.iirp.edu/images/pdf/Google_search_tips.pdf

-Choose the right tool for your research needs!

--https://guides.rider.edu/c.php?g=420759&p=2873050

allintitle: (("lexicon construction")("automatic"))

Title	Authors	Abstract	Title URL Link	Full text Link
Noun-phrase co-occurrence statistics for semi-automatic semantic lexicon construction	B Roark, E Charniak - arXiv preprint cs/0008026, 2000 - arxiv.org	Generating semantic lexicons semi-automatically could be a great time saver, relative to creating them by hand. In this paper, we present an algorithm for extracting potential entries for a category from an on-line corpus, based upon a small set of exemplars. Our algorithm …	https://arxiv.org/abs/cs/0008026	https://arxiv.org/pdf/cs/0008026.pdf%20http://portal.acm.org/citation.cfm?doid=980432.980751
Automatic lexicon construction for arabic sentiment analysis	N Abdulla, S Mohammed, M Al-Ayyoub… - … Conference on Future …, 2014 - ieeexplore.ieee.org	Sentiment Analysis (SA) is the process of determining the sentiment of a text written in a natural language to be positive, negative or neutral. It is one of the most interesting subfields of natural language processing (NLP) and Web mining due to its diverse applications and …	https://ieeexplore.ieee.org/abstract/document/6984251/
Automatic construction of target-specific sentiment lexicon	S Wu, F Wu, Y Chang, C Wu, Y Huang - Expert Systems with Applications, 2019 - Elsevier	… Most domain-specific sentiment lexicon construction methods are incapable to solve these two problems. As a result, an automatic approach to build a sentiment lexicon incorporating information of opinion target is beneficial to sentiment analysis …	https://www.sciencedirect.com/science/article/pii/S0957417418306018
Emotion representation mapping for automatic lexicon construction (mostly) performs on human level	S Buechel, U Hahn - arXiv preprint arXiv:1806.08890, 2018 - arxiv.org	Emotion Representation Mapping (ERM) has the goal to convert existing emotion ratings from one representation format into another one, eg, mapping Valence-Arousal-Dominance annotations for words or sentences into Ekman's Basic Emotions and vice versa. ERM can …	https://arxiv.org/abs/1806.08890	https://arxiv.org/pdf/1806.08890
Automatic construction of domain-specific sentiment lexicon based on constrained label propagation	S Huang, Z Niu, C Shi - Knowledge-Based Systems, 2014 - Elsevier	… This paper focuses on the problem of automatic domain-specific sentiment lexicon construction. By definition, a domain-specific sentiment lexicon commonly contains a collection of sentiment bearing terms and phrases, and their sentiment polarities in the specific domain …	https://www.sciencedirect.com/science/article/pii/S0950705113003596
Adapting information bottleneck method for automatic construction of domain-oriented sentiment lexicon	W Du, S Tan, X Cheng, X Yun - … of the third ACM international conference …, 2010 - dl.acm.org	… Automatic sentiment analysis [1][9][13][17][19-26] could play an important role in a wide variety of flexible and dynamic information management tasks … As a result, our approach could be considered as a sentiment-lexicon- construction version of information bottleneck method …	https://dl.acm.org/doi/abs/10.1145/1718487.1718502	http://www.wsdm-conference.org/2010/proceedings/docs/p111.pdf
A random walk algorithm for automatic construction of domain-oriented sentiment lexicon	S Tan, Q Wu - Expert Systems with Applications, 2011 - Elsevier	… Experimental results indicate that the proposed algorithm could dramatically improve the performance of automatic construction of domain-oriented sentiment lexicon. Highlights … So far, some studies have been conducted to deal with the lexicon construction problem …	https://www.sciencedirect.com/science/article/pii/S0957417411003113
Automatic construction of domain sentiment lexicon for semantic disambiguation	Y Wang, F Yin, J Liu, M Tosato - Multimedia Tools and Applications, 2020 - Springer	… In this paper, we propose an automatic method for the construction of the domain-specific sentiment lexicon (SDS-lex) to avoid sentimental ambiguity, which incorporates the senti- ment information not only from … [24] transformed the sentiment lexicon construction problem into …	https://link.springer.com/content/pdf/10.1007/s11042-020-09030-1.pdf
[HTML][HTML] Automatic Construction of a Depression-Domain Lexicon Based on Microblogs: Text Mining Study	G Li, B Li, L Huang, S Hou - JMIR medical informatics, 2020 - qa-medinform.jmir.org	Background: According to a World Health Organization report in 2017, there was almost one patient with depression among every 20 people in China. However, the diagnosis of depression is usually difficult in terms of clinical detection owing to slow observation, high cost, and patient …	https://qa-medinform.jmir.org/2020/6/e17650/	https://qa-medinform.jmir.org/2020/6/e17650/
Automatic construction of a core lexicon for specific domain	L Ji, Q Lu, W Li, Y Chen - Sixth International Conference on …, 2007 - ieeexplore.ieee.org	… phrases. The semantic phrases and their meanings are extracted from the input sentences and their representations. But few works has been done automatic core lexicon construction from existing domain lexicons. Some ontology …	https://ieeexplore.ieee.org/abstract/document/4460637/
Automatic construction of domain-specific sentiment lexicon for unsupervised domain adaptation and sentiment classification	OM Beigi, MH Moattar - Knowledge-Based Systems, 2020 - Elsevier	… introduced. 2.1. Sentiment lexicon construction. Sentiment Lexicon plays a crucial role in sentiment analysis. It … lexicon. Ref. [20] uses the co-occurrence pattern of negations and adverbials to generate an automatic word lexicon. To …	https://www.sciencedirect.com/science/article/pii/S0950705120305529
The development of semi-automatic sentiment lexicon construction tool for thai sentiment analysis	M Suktarachan - Advances in Natural Language Processing, Intelligent …, 2018 - Springer	Sentiment analysis has gained so much interest from many companies and organizations in Thailand. However, there are a few research studies focused on developing Thai sentiment lexicon, which is an important resource for the sentiment analysis. In this work, we …	https://link.springer.com/content/pdf/10.1007/978-3-319-70016-8.pdf#page=108
Research on automatic construction of sentiment lexicon based on Bayesian framework	J Liu, Y Wang, F Yin - 2018 14th International Conference on …, 2018 - ieeexplore.ieee.org	… Literature [21] proposed an automatic domain-specific sentiment lexicon construction strategy based on constrained label propagation, using block- dependent information and existing lexicons to extract candidate sentimental words …	https://ieeexplore.ieee.org/abstract/document/8687185/
A CRF-based method for automatic construction of Chinese symptom lexicon	M Ju, H Duan, H Li - 2015 7th International Conference on …, 2015 - ieeexplore.ieee.org	… The iteration stopped when the certain condition was satisfied. Detailed descriptions are presented in the below. Figure 1. Workflow of the automatic lexicon construction. 2015 7th International Conference on Information Technology in Medicine and Education …	https://ieeexplore.ieee.org/abstract/document/7429085/
[PDF][PDF] Automatic Construction of the Polish Nominal Lexicon for the OpenCyc Ontology	A Pohl - Recent Advances in Intelligent Information Systems, 2009 - researchgate.net	… Its main purpose is to give an answer whether semi-automatic construction of it is feasible in a reasonable amount of time … Section 4 discuss the details of the algorithm used for the lexicon construction. Section 5 contains the results of the algorithm, while section …	https://www.researchgate.net/profile/Aleksander_Smywinski-Pohl/publication/255596010_Automatic_Construction_of_the_Polish_Nominal_Lexicon_for_the_OpenCyc_Ontology/links/0deec5374f326b5cdf000000.pdf	https://www.researchgate.net/profile/Aleksander_Smywinski-Pohl/publication/255596010_Automatic_Construction_of_the_Polish_Nominal_Lexicon_for_the_OpenCyc_Ontology/links/0deec5374f326b5cdf000000.pdf
Automatic Construction of Aramaic-Hebrew Translation Lexicon	C Liebeskind, S Liebeskind - … of LT4HALA 2020-1st Workshop on …, 2020 - aclweb.org	… In this paper, we suggest a methodology for automatic construction of Aramaic-Hebrew translation Lexicon. First, we generate an initial translation lexicon by a state-of-the-art word alignment translation model … Translation lexicon construction requires parallel data for learning …	https://www.aclweb.org/anthology/2020.lt4hala-1.2/	https://www.aclweb.org/anthology/2020.lt4hala-1.2.pdf
[PDF][PDF] Opinion Lexicon Automatic Construction on Arabic language	F Alqasemi, A Abdelwahab, H Abdelkader - 2018 - researchgate.net	… PMI. So, we named it SOPMI. PMI is a very popular method that used in sentiment analysis [8], especially, in automatic lexicon construction process [9]. SOPMI is found by computing PMI relation for each corpus term Page 3 …	https://www.researchgate.net/profile/Penerbit_Akademia_Baru/publication/330881318_Opinion_Lexicon_Automatic_Construction_on_Arabic_language/links/5c598d3d299bf1d14cadb3cb/Opinion-Lexicon-Automatic-Construction-on-Arabic-language.pdf	https://www.researchgate.net/profile/Penerbit_Akademia_Baru/publication/330881318_Opinion_Lexicon_Automatic_Construction_on_Arabic_language/links/5c598d3d299bf1d14cadb3cb/Opinion-Lexicon-Automatic-Construction-on-Arabic-language.pdf
Construction of an accurate automatic lexicon for Arabic sentiment analysis	I Touahri, A Mazroui - Proceedings of the 13th International Conference …, 2020 - dl.acm.org	… 4.2 Automatic construction of Bag-of-Words In this section, we aim to construct an automatic BOW that weighs terms according to their occurrences and helps to reduce the lexicon construction time taken by other approaches that need a manual verification …	https://dl.acm.org/doi/abs/10.1145/3419604.3419627
The development of semi-automatic sentiment lexicon construction tool for Thai sentiment analysis	H Chanlekha, W Damdoung, M Suktarachan - International Symposium on …, 2016 - Springer	Sentiment analysis has gained so much interest from many companies and organizations in Thailand. However, there are a few research studies focused on developing Thai sentiment lexicon, which is an important resource for the sentiment analysis. In this work, we …	https://link.springer.com/chapter/10.1007/978-3-319-70016-8_9
Automatic construction of domain-specific sentiment lexicon based on the semantics graph	G Xiong, Y Fang, Q Liu - 2017 IEEE International Conference …, 2017 - ieeexplore.ieee.org	… III. THE CONSTRUCTION OF DOMAIN-SPECIFIC SENTIMENT LEXICON In this section, we will introduce the method of automatic construction of domain … and evaluation metrics In order to verify the validity of the proposed method, two kinds of lexicon construction methods are …	https://ieeexplore.ieee.org/abstract/document/8242562/
[CITATION][C] Automatic construction of financial semantic orientation lexicon from large-scale Chinese news corpus	H Mao, P Gao, Y Wang, J Bollen - Institut Louis Bachelier, 2014
Automatic Construction of Korean Two-level Lexicon using Lexical and Morphological Information	B Kim, JS Lee - KIPS Transactions on Software and Data …, 2013 - koreascience.or.kr	… Keywords : Korean Two-level Morphology, Two-level Lexicon, Korean Morphotactic, Automatic Construction, Tagged Corpus 어휘 및 형태 정보를 이용한 한국어 Two-level 어휘사전 자동 구축 김 보 겸†․이 재 성†† 요 약 … Fig. 7. Lexicon construction algorithm Fig …	https://www.koreascience.or.kr/article/JAKO201301671902416.page	https://www.koreascience.or.kr/article/JAKO201301671902416.pdf
Automatic bilingual lexicon construction via bilingual parallel corpus and pivot language	HW Seo, HS Kwon, JH Kim - Proceedings of the Korea …, 2013 - koreascience.or.kr	본 논문은 한국어-스페인어와 한국어-불어 간의 양방향 이국어 사전 (Bi-directional bilingual lexicon) 을 자동으로 구축하기 위한 새로운 방법을 제안한다. 일반적으로 한국어와 스페인어/불어 간의 병렬 말뭉치를 직접적으로 구축하기에는 어려움에 따르기 때문에, 영어를 …	https://www.koreascience.or.kr/article/CFKO201335553774813.page	https://www.koreascience.or.kr/article/CFKO201335553774813.pdf
[CITATION][C] Noun Phrase Co-occurrence Statistics for Semi-automatic Semantic Lexicon Construction	E Charniak, B Roark - … Conference on Computational Linguistics (COLING 98 …, 1998
[CITATION][C] Automatic lexicon construction for domain‑specific sentiment analysis: a frame‑based approach	SS Tan - dr.ntu.edu.sg	Tan, S. S. (2020). Automatic lexicon construction for domain‑specific sentiment analysis : a frame‑based approach. Doctoral thesis, Nanyang Technological University, Singapore … This work is licensed under a Creative Commons Attribution‑NonCommercial 4.0 International License …	https://dr.ntu.edu.sg/bitstream/10356/143088/2/Final%20thesis.pdf
[CITATION][C] Semi-Automatic Thai Computational Lexicon Construction: KULEX	DNMSA Kawtrakul

allintitle: (("lexicon construction")("automatic"))

Title,Authors,Abstract,Title URL Link,Full text Link Noun-phrase co-occurrence statistics for semi-automatic semantic lexicon construction,"B Roark, E Charniak - arXiv preprint cs/0008026, 2000 - arxiv.org","Generating semantic lexicons semi-automatically could be a great time saver, relative to creating them by hand. In this paper, we present an algorithm for extracting potential entries for a category from an on-line corpus, based upon a small set of exemplars. Our algorithm …",https://arxiv.org/abs/cs/0008026,https://arxiv.org/pdf/cs/0008026.pdf%20http://portal.acm.org/citation.cfm?doid=980432.980751 Automatic lexicon construction for arabic sentiment analysis,"N Abdulla, S Mohammed, M Al-Ayyoub… - … Conference on Future …, 2014 - ieeexplore.ieee.org","Sentiment Analysis (SA) is the process of determining the sentiment of a text written in a natural language to be positive, negative or neutral. It is one of the most interesting subfields of natural language processing (NLP) and Web mining due to its diverse applications and …",https://ieeexplore.ieee.org/abstract/document/6984251/, Automatic construction of target-specific sentiment lexicon,"S Wu, F Wu, Y Chang, C Wu, Y Huang - Expert Systems with Applications, 2019 - Elsevier","… Most domain-specific sentiment lexicon construction methods are incapable to solve these two problems. As a result, an automatic approach to build a sentiment lexicon incorporating information of opinion target is beneficial to sentiment analysis …",https://www.sciencedirect.com/science/article/pii/S0957417418306018, Emotion representation mapping for automatic lexicon construction (mostly) performs on human level,"S Buechel, U Hahn - arXiv preprint arXiv:1806.08890, 2018 - arxiv.org","Emotion Representation Mapping (ERM) has the goal to convert existing emotion ratings from one representation format into another one, eg, mapping Valence-Arousal-Dominance annotations for words or sentences into Ekman's Basic Emotions and vice versa. ERM can …",https://arxiv.org/abs/1806.08890,https://arxiv.org/pdf/1806.08890 Automatic construction of domain-specific sentiment lexicon based on constrained label propagation,"S Huang, Z Niu, C Shi - Knowledge-Based Systems, 2014 - Elsevier","… This paper focuses on the problem of automatic domain-specific sentiment lexicon construction. By definition, a domain-specific sentiment lexicon commonly contains a collection of sentiment bearing terms and phrases, and their sentiment polarities in the specific domain …",https://www.sciencedirect.com/science/article/pii/S0950705113003596, Adapting information bottleneck method for automatic construction of domain-oriented sentiment lexicon,"W Du, S Tan, X Cheng, X Yun - … of the third ACM international conference …, 2010 - dl.acm.org","… Automatic sentiment analysis [1][9][13][17][19-26] could play an important role in a wide variety of flexible and dynamic information management tasks … As a result, our approach could be considered as a sentiment-lexicon- construction version of information bottleneck method …",https://dl.acm.org/doi/abs/10.1145/1718487.1718502,http://www.wsdm-conference.org/2010/proceedings/docs/p111.pdf A random walk algorithm for automatic construction of domain-oriented sentiment lexicon,"S Tan, Q Wu - Expert Systems with Applications, 2011 - Elsevier","… Experimental results indicate that the proposed algorithm could dramatically improve the performance of automatic construction of domain-oriented sentiment lexicon. Highlights … So far, some studies have been conducted to deal with the lexicon construction problem …",https://www.sciencedirect.com/science/article/pii/S0957417411003113, Automatic construction of domain sentiment lexicon for semantic disambiguation,"Y Wang, F Yin, J Liu, M Tosato - Multimedia Tools and Applications, 2020 - Springer","… In this paper, we propose an automatic method for the construction of the domain-specific sentiment lexicon (SDS-lex) to avoid sentimental ambiguity, which incorporates the senti- ment information not only from … [24] transformed the sentiment lexicon construction problem into …",https://link.springer.com/content/pdf/10.1007/s11042-020-09030-1.pdf, [HTML][HTML] Automatic Construction of a Depression-Domain Lexicon Based on Microblogs: Text Mining Study,"G Li, B Li, L Huang, S Hou - JMIR medical informatics, 2020 - qa-medinform.jmir.org","Background: According to a World Health Organization report in 2017, there was almost one patient with depression among every 20 people in China. However, the diagnosis of depression is usually difficult in terms of clinical detection owing to slow observation, high cost, and patient …",https://qa-medinform.jmir.org/2020/6/e17650/,https://qa-medinform.jmir.org/2020/6/e17650/ Automatic construction of a core lexicon for specific domain,"L Ji, Q Lu, W Li, Y Chen - Sixth International Conference on …, 2007 - ieeexplore.ieee.org","… phrases. The semantic phrases and their meanings are extracted from the input sentences and their representations. But few works has been done automatic core lexicon construction from existing domain lexicons. Some ontology …",https://ieeexplore.ieee.org/abstract/document/4460637/, ,,,, Automatic construction of domain-specific sentiment lexicon for unsupervised domain adaptation and sentiment classification,"OM Beigi, MH Moattar - Knowledge-Based Systems, 2020 - Elsevier","… introduced. 2.1. Sentiment lexicon construction. Sentiment Lexicon plays a crucial role in sentiment analysis. It … lexicon. Ref. [20] uses the co-occurrence pattern of negations and adverbials to generate an automatic word lexicon. To …",https://www.sciencedirect.com/science/article/pii/S0950705120305529, The development of semi-automatic sentiment lexicon construction tool for thai sentiment analysis,"M Suktarachan - Advances in Natural Language Processing, Intelligent …, 2018 - Springer","Sentiment analysis has gained so much interest from many companies and organizations in Thailand. However, there are a few research studies focused on developing Thai sentiment lexicon, which is an important resource for the sentiment analysis. In this work, we …",https://link.springer.com/content/pdf/10.1007/978-3-319-70016-8.pdf#page=108, Research on automatic construction of sentiment lexicon based on Bayesian framework,"J Liu, Y Wang, F Yin - 2018 14th International Conference on …, 2018 - ieeexplore.ieee.org","… Literature [21] proposed an automatic domain-specific sentiment lexicon construction strategy based on constrained label propagation, using block- dependent information and existing lexicons to extract candidate sentimental words …",https://ieeexplore.ieee.org/abstract/document/8687185/, A CRF-based method for automatic construction of Chinese symptom lexicon,"M Ju, H Duan, H Li - 2015 7th International Conference on …, 2015 - ieeexplore.ieee.org","… The iteration stopped when the certain condition was satisfied. Detailed descriptions are presented in the below. Figure 1. Workflow of the automatic lexicon construction. 2015 7th International Conference on Information Technology in Medicine and Education …",https://ieeexplore.ieee.org/abstract/document/7429085/, [PDF][PDF] Automatic Construction of the Polish Nominal Lexicon for the OpenCyc Ontology,"A Pohl - Recent Advances in Intelligent Information Systems, 2009 - researchgate.net","… Its main purpose is to give an answer whether semi-automatic construction of it is feasible in a reasonable amount of time … Section 4 discuss the details of the algorithm used for the lexicon construction. Section 5 contains the results of the algorithm, while section …",https://www.researchgate.net/profile/Aleksander_Smywinski-Pohl/publication/255596010_Automatic_Construction_of_the_Polish_Nominal_Lexicon_for_the_OpenCyc_Ontology/links/0deec5374f326b5cdf000000.pdf,https://www.researchgate.net/profile/Aleksander_Smywinski-Pohl/publication/255596010_Automatic_Construction_of_the_Polish_Nominal_Lexicon_for_the_OpenCyc_Ontology/links/0deec5374f326b5cdf000000.pdf Automatic Construction of Aramaic-Hebrew Translation Lexicon,"C Liebeskind, S Liebeskind - … of LT4HALA 2020-1st Workshop on …, 2020 - aclweb.org","… In this paper, we suggest a methodology for automatic construction of Aramaic-Hebrew translation Lexicon. First, we generate an initial translation lexicon by a state-of-the-art word alignment translation model … Translation lexicon construction requires parallel data for learning …",https://www.aclweb.org/anthology/2020.lt4hala-1.2/,https://www.aclweb.org/anthology/2020.lt4hala-1.2.pdf [PDF][PDF] Opinion Lexicon Automatic Construction on Arabic language,"F Alqasemi, A Abdelwahab, H Abdelkader - 2018 - researchgate.net","… PMI. So, we named it SOPMI. PMI is a very popular method that used in sentiment analysis [8], especially, in automatic lexicon construction process [9]. SOPMI is found by computing PMI relation for each corpus term Page 3 …",https://www.researchgate.net/profile/Penerbit_Akademia_Baru/publication/330881318_Opinion_Lexicon_Automatic_Construction_on_Arabic_language/links/5c598d3d299bf1d14cadb3cb/Opinion-Lexicon-Automatic-Construction-on-Arabic-language.pdf,https://www.researchgate.net/profile/Penerbit_Akademia_Baru/publication/330881318_Opinion_Lexicon_Automatic_Construction_on_Arabic_language/links/5c598d3d299bf1d14cadb3cb/Opinion-Lexicon-Automatic-Construction-on-Arabic-language.pdf Construction of an accurate automatic lexicon for Arabic sentiment analysis,"I Touahri, A Mazroui - Proceedings of the 13th International Conference …, 2020 - dl.acm.org","… 4.2 Automatic construction of Bag-of-Words In this section, we aim to construct an automatic BOW that weighs terms according to their occurrences and helps to reduce the lexicon construction time taken by other approaches that need a manual verification …",https://dl.acm.org/doi/abs/10.1145/3419604.3419627, The development of semi-automatic sentiment lexicon construction tool for Thai sentiment analysis,"H Chanlekha, W Damdoung, M Suktarachan - International Symposium on …, 2016 - Springer","Sentiment analysis has gained so much interest from many companies and organizations in Thailand. However, there are a few research studies focused on developing Thai sentiment lexicon, which is an important resource for the sentiment analysis. In this work, we …",https://link.springer.com/chapter/10.1007/978-3-319-70016-8_9, Automatic construction of domain-specific sentiment lexicon based on the semantics graph,"G Xiong, Y Fang, Q Liu - 2017 IEEE International Conference …, 2017 - ieeexplore.ieee.org","… III. THE CONSTRUCTION OF DOMAIN-SPECIFIC SENTIMENT LEXICON In this section, we will introduce the method of automatic construction of domain … and evaluation metrics In order to verify the validity of the proposed method, two kinds of lexicon construction methods are …",https://ieeexplore.ieee.org/abstract/document/8242562/, ,,,, [CITATION][C] Automatic construction of financial semantic orientation lexicon from large-scale Chinese news corpus,"H Mao, P Gao, Y Wang, J Bollen - Institut Louis Bachelier, 2014",,, Automatic Construction of Korean Two-level Lexicon using Lexical and Morphological Information,"B Kim, JS Lee - KIPS Transactions on Software and Data …, 2013 - koreascience.or.kr","… Keywords : Korean Two-level Morphology, Two-level Lexicon, Korean Morphotactic, Automatic Construction, Tagged Corpus 어휘 및 형태 정보를 이용한 한국어 Two-level 어휘사전 자동 구축 김 보 겸†․이 재 성†† 요 약 … Fig. 7. Lexicon construction algorithm Fig …",https://www.koreascience.or.kr/article/JAKO201301671902416.page,https://www.koreascience.or.kr/article/JAKO201301671902416.pdf Automatic bilingual lexicon construction via bilingual parallel corpus and pivot language,"HW Seo, HS Kwon, JH Kim - Proceedings of the Korea …, 2013 - koreascience.or.kr","본 논문은 한국어-스페인어와 한국어-불어 간의 양방향 이국어 사전 (Bi-directional bilingual lexicon) 을 자동으로 구축하기 위한 새로운 방법을 제안한다. 일반적으로 한국어와 스페인어/불어 간의 병렬 말뭉치를 직접적으로 구축하기에는 어려움에 따르기 때문에, 영어를 …",https://www.koreascience.or.kr/article/CFKO201335553774813.page,https://www.koreascience.or.kr/article/CFKO201335553774813.pdf [CITATION][C] Noun Phrase Co-occurrence Statistics for Semi-automatic Semantic Lexicon Construction,"E Charniak, B Roark - … Conference on Computational Linguistics (COLING 98 …, 1998",,, [CITATION][C] Automatic lexicon construction for domain‑specific sentiment analysis: a frame‑based approach,SS Tan - dr.ntu.edu.sg,"Tan, S. S. (2020). Automatic lexicon construction for domain‑specific sentiment analysis : a frame‑based approach. Doctoral thesis, Nanyang Technological University, Singapore … This work is licensed under a Creative Commons Attribution‑NonCommercial 4.0 International License …",https://dr.ntu.edu.sg/bitstream/10356/143088/2/Final%20thesis.pdf, [CITATION][C] Semi-Automatic Thai Computational Lexicon Construction: KULEX,DNMSA Kawtrakul,,, ,,,,

Sentiment analysis in health and well-being: Systematic review

 

Abstract

Background: 

Sentiment analysis (SA) is a subfield of natural language processing whose aim is to automatically classify the sentiment expressed in a free text. 

It has found practical applications across a wide range of societal contexts including marketing, economy, and politics. 

This review focuses specifically on applications related to health, which is defined as “a state of complete physical, mental, and social well-being and not merely the absence of disease or infirmity.”

 Objective: 

This study aimed to establish the state of the art in SA related to health and well-being by conducting a systematic review of the recent literature. 

To capture the perspective of those individuals whose health and well-being are affected, we focused specifically on spontaneously generated content and not necessarily that of health care professionals.

Methods: 

Our methodology is based on the guidelines for performing systematic reviews. 

In January 2019, we used PubMed, a multifaceted interface, to perform a literature search against MEDLINE. 

We identified a total of 86 relevant studies and extracted data about the datasets analyzed, discourse topics, data creators, downstream applications, algorithms used, and their evaluation. 

Results: 

The majority of data were collected from social networking and Web-based retailing platforms. 

The primary purpose of online conversations is to exchange information and provide social support online. 

These communities tend to form around health conditions with high severity and chronicity rates.

Different treatments and services discussed include medications, vaccination, surgery, orthodontic services, individual physicians, and health care services in general. 

We identified 5 roles with respect to health and well-being among the authors of the types of spontaneously generated narratives considered in this review: a sufferer, an addict, a patient, a carer, and a suicide victim. 

Out of 86 studies considered, only 4 reported the demographic characteristics. 

A wide range of methods were used to perform SA. 

Most common choices included support vector machines, naïve Bayesian learning, decision trees, logistic regression, and adaptive boosting. 

In contrast with general trends in SA research, only 1 study used deep learning. 

The performance lags behind the state of the art achieved in other domains when measured by F-score, which was found to be below 60% on average. 

In the context of SA, the domain of health and well-being was found to be resource poor: few domain-specific corpora and lexica are shared publicly for research purposes. 

Conclusions: 

SA results in the area of health and well-being lag behind those in other domains. 

It is yet unclear if this is because of the intrinsic differences between the domains and their respective sublanguages, the size of training datasets, the lack of domain-specific sentiment lexica, or the choice of algorithms.

REFERENCES

1. Wiebe J, Bruce R. Probabilistic classifiers for tracking point of view. Progress in communication sciences 1995:125-142

[FREE Full text]

2. Hatzivassiloglou V, McKeown KR. Predicting the Semantic Orientation of Adjectives. In: Proceedings of the 35th Annual

Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association

for Computational Linguistics. 1997 Presented at: ACL'98/EACL'98; July 7-12, 1997; Madrid, Spain p. 174-181 URL:

https://www.aclweb.org/anthology/P97-1023/ [doi: 10.3115/979617.979640]

3. Wiebe JM, Bruce RF, O'Hara TP. Development and Use of a Gold-standard Data Set for Subjectivity Classifications. In:

Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics.

1999 Presented at: ACL'99; June 20-26, 1999; College Park, Maryland, USA p. 246-253 URL: https://www.aclweb.org/

anthology/P99-1032/ [doi: 10.3115/1034678.1034721]

4. Hu M, Liu B. Mining Opinion Features in Customer Reviews. In: Proceedings of the 19th national conference on Artifical

intelligence. 2004 Presented at: AAAI'04; July 25 - 29, 2004; San Jose, California, USA p. 755-760 URL: https://dl.acm.org/

citation.cfm?id=1597269

5. Hu M, Liu B. Mining and Summarizing Customer Reviews. In: Proceedings of the tenth ACM SIGKDD international

conference on Knowledge discovery and data mining. 2004 Presented at: KDD'04; August 22 - 25, 2004; Seattle, Washington,

USA p. 168-177 URL: https://dl.acm.org/citation.cfm?id=1014073 [doi: 10.1145/1014052.1014073]

6. Bollen J, Mao H, Zeng X. Twitter mood predicts the stock market. J Comput Sci 2011;2(1):1-8. [doi:

10.1016/j.jocs.2010.12.007]

7. Efron M. Cultural orientation: Classifying subjective documents by cociation analysis. In: Proceedings of the AAAI Fall

Symposium on Style and Meaning in Language, Art, and Music. 2004 Presented at: AAAI'04; July 25-29, 2004; San Jose,

California p. 41-48.

8. Ramteke J, Shah S, Godhia D, Shaikh A. Election Result Prediction Using Twitter Sentiment Analysis. In: Proceedings of

the 2016 International Conference on Inventive Computation Technologies. 2016 Presented at: ICICT'16; August 26-27,

2016; Coimbatore, India p. 1-5. [doi: 10.1109/inventive.2016.7823280]

9. World Health Organisation. Geneva, Switzerland: World Health Organisation; 2006. Constitution of the World Health

Organisation URL: https://www.who.int/governance/eb/who_constitution_en.pdf [accessed 2019-11-12]

10. Huber M, Knottnerus JA, Green L, van der Horst H, Jadad AR, Kromhout D, et al. How should we define health? Br Med

J 2011 Jul 26;343:d4163. [doi: 10.1136/bmj.d4163] [Medline: 21791490]

11. Berg O. Health and quality of life. Acta Sociologica 1975;18(1):3-22. [doi: 10.1177/000169937501800102]

12. Denecke K, Deng Y. Sentiment analysis in medical settings: new opportunities and challenges. Artif Intell Med 2015

May;64(1):17-27. [doi: 10.1016/j.artmed.2015.03.006] [Medline: 25982909]

13. Gohil S, Vuik S, Darzi A. Sentiment analysis of health care tweets: review of the methods used. JMIR Public Health Surveill

2018 Apr 23;4(2):e43 [FREE Full text] [doi: 10.2196/publichealth.5789] [Medline: 29685871]

14. Kitchenham B. Procedures for performing systematic reviews. Keele University, Keele 2004;33(2004):1-26 [FREE Full

text]

15. Cochrane Library: Cochrane Reviews. URL: https://www.cochranelibrary.com/ [accessed 2019-11-12]

16. National Library of Medicine. MEDLINE: Description of the Database URL: https://www.nlm.nih.gov/bsd/medline.html

[accessed 2019-11-12]

17. Embase. URL: https://www.embase.com [accessed 2019-11-12]

18. EBSCO Health. CINAHL Database URL: https://health.ebsco.com/products/the-cinahl-database [accessed 2019-11-12]

19. Cohen J. A Coefficient of Agreement for Nominal Scales. Educ Psychol Meas 1960;20(1):37-46. [doi:

10.1177/001316446002000104]

20. Yoon S, Bakken S. Methods of knowledge discovery in tweets. NI 2012 (2012) 2012;2012:463 [FREE Full text] [Medline:

24199142]

21. Mishra MV, Bennett M, Vincent A, Lee OT, Lallas CD, Trabulsi EJ, et al. Identifying barriers to patient acceptance of

active surveillance: content analysis of online patient communications. PLoS One 2013;8(9):e68563 [FREE Full text] [doi:

10.1371/journal.pone.0068563] [Medline: 24039699]

22. Ramagopalan S, Wasiak R, Cox AP. Using Twitter to investigate opinions about multiple sclerosis treatments: a descriptive,

exploratory study. F1000Res 2014;3:216 [FREE Full text] [doi: 10.12688/f1000research.5263.1] [Medline: 25520780]

23. Wiley MT, Jin C, Hristidis V, Esterling KM. Pharmaceutical drugs chatter on Online Social Networks. J Biomed Inform

2014 Jun;49:245-254 [FREE Full text] [doi: 10.1016/j.jbi.2014.03.006] [Medline: 24637141]

24. Tighe PJ, Goldsmith RC, Gravenstein M, Bernard HR, Fillingim RB. The painful tweet: text, sentiment, and community

structure analyses of tweets pertaining to pain. J Med Internet Res 2015 Apr 2;17(4):e84 [FREE Full text] [doi:

10.2196/jmir.3769] [Medline: 25843553]

25. Zhou X, Coiera E, Tsafnat G, Arachi D, Ong M, Dunn AG. Using social connection information to improve opinion mining:

identifying negative sentiment about HPV vaccines on Twitter. Stud Health Technol Inform 2015;216:761-765. [doi:

10.3233/978-1-61499-564-7-761] [Medline: 26262154]

26. Daniulaityte R, Chen L, Lamy FR, Carlson RG, Thirunarayan K, Sheth A. 'When 'Bad' is 'Good'': identifying personal

communication and sentiment in drug-related tweets. JMIR Public Health Surveill 2016 Oct 24;2(2):e162 [FREE Full text]

[doi: 10.2196/publichealth.6327] [Medline: 27777215]

27. Korkontzelos I, Nikfarjam A, Shardlow M, Sarker A, Ananiadou S, Gonzalez GH. Analysis of the effect of sentiment

analysis on extracting adverse drug reactions from tweets and forum posts. J Biomed Inform 2016 Aug;62:148-158 [FREE

Full text] [doi: 10.1016/j.jbi.2016.06.007] [Medline: 27363901]

28. Ofoghi B, Mann M, Verspoor K. Towards early discovery of salient health threats: a social media emotion classification

technique. Pac Symp Biocomput 2016;21:504-515 [FREE Full text] [doi: 10.1142/9789814749411_0046] [Medline:

26776213]

29. Palomino M, Taylor T, Göker A, Isaacs J, Warber S. The online dissemination of nature-health concepts: lessons from

sentiment analysis of social media relating to 'Nature-deficit disorder'. Int J Environ Res Public Health 2016 Jan 19;13(1):pii:

E142 [FREE Full text] [doi: 10.3390/ijerph13010142] [Medline: 26797628]

30. Bian J, Zhao Y, Salloum RG, Guo Y, Wang M, Prosperi M, et al. Using social media data to understand the impact of

promotional information on laypeople's discussions: a case study of lynch syndrome. J Med Internet Res 2017 Dec

13;19(12):e414 [FREE Full text] [doi: 10.2196/jmir.9266] [Medline: 29237586]

31. Davis MA, Zheng K, Liu Y, Levy H. Public response to Obamacare on Twitter. J Med Internet Res 2017 May 26;19(5):e167

[FREE Full text] [doi: 10.2196/jmir.6946] [Medline: 28550002]

32. Du J, Xu J, Song H, Liu X, Tao C. Optimization on machine learning based approaches for sentiment analysis on HPV

vaccines related tweets. J Biomed Semantics 2017 Mar 3;8(1):9 [FREE Full text] [doi: 10.1186/s13326-017-0120-6]

[Medline: 28253919]

33. Du J, Xu J, Song H, Tao C. Leveraging machine learning-based approaches to assess human papillomavirus vaccination

sentiment trends with Twitter data. BMC Med Inform Decis Mak 2017 Jul 5;17(Suppl 2):69 [FREE Full text] [doi:

10.1186/s12911-017-0469-6] [Medline: 28699569]

34. Gruebner O, Lowe SR, Sykora M, Shankardass K, Subramanian SV, Galea S. A novel surveillance approach for disaster

mental health. PLoS One 2017;12(7):e0181233 [FREE Full text] [doi: 10.1371/journal.pone.0181233] [Medline: 28723959]

35. Haghighi PD, Kang Y, Buchbinder R, Burstein F, Whittle S. Investigating subjective experience and the influence of

weather among individuals with fibromyalgia: a content analysis of Twitter. JMIR Public Health Surveill 2017 Jan 19;3(1):e4

[FREE Full text] [doi: 10.2196/publichealth.6344] [Medline: 28104577]

36. Kang Y, Wang Y, Zhang D, Zhou L. The public's opinions on a new school meals policy for childhood obesity prevention

in the US: a social media analytics approach. Int J Med Inform 2017 Jul;103:83-88. [doi: 10.1016/j.ijmedinf.2017.04.013]

[Medline: 28551006]

37. Lim S, Tucker CS, Kumara S. An unsupervised machine learning model for discovering latent infectious diseases using

social media data. J Biomed Inform 2017 Feb;66:82-94 [FREE Full text] [doi: 10.1016/j.jbi.2016.12.007] [Medline:

28034788]

38. Metwally O, Blumberg S, Ladabaum U, Sinha SR. Using social media to characterize public sentiment toward medical

interventions commonly used for cancer screening: an observational study. J Med Internet Res 2017 Jun 7;19(6):e200

[FREE Full text] [doi: 10.2196/jmir.7485] [Medline: 28592395]

39. Noll D, Mahon B, Shroff B, Carrico C, Lindauer SJ. Twitter analysis of the orthodontic patient experience with braces vs

Invisalign. Angle Orthod 2017 May;87(3):377-383. [doi: 10.2319/062816-508.1] [Medline: 28059576]

40. Oscar N, Fox PA, Croucher R, Wernick R, Keune J, Hooker K. Machine learning, sentiment analysis, and tweets: an

examination of Alzheimer's disease stigma on Twitter. J Gerontol B Psychol Sci Soc Sci 2017 Sep 1;72(5):742-751. [doi:

10.1093/geronb/gbx014] [Medline: 28329835]

41. Salas-Zárate MD, Medina-Moreira J, Lagos-Ortiz K, Luna-Aveiga H, Rodríguez-García MA, Valencia-García R. Sentiment

analysis on tweets about diabetes: an aspect-level approach. Comput Math Methods Med 2017;2017:5140631 [FREE Full

text] [doi: 10.1155/2017/5140631] [Medline: 28316638]

42. Cao X, MacNaughton P, Deng Z, Yin J, Zhang X, Allen JG. Using Twitter to better understand the spatiotemporal patterns

of public sentiment: a case study in Massachusetts, USA. Int J Environ Res Public Health 2018 Feb 2;15(2):pii: E250

[FREE Full text] [doi: 10.3390/ijerph15020250] [Medline: 29393869]

43. Gabarron E, Dorronzoro E, Rivera-Romero O, Wynn R. Diabetes on Twitter: a sentiment analysis. J Diabetes Sci Technol

2019 May;13(3):439-444. [doi: 10.1177/1932296818811679] [Medline: 30453762]

44. Pai RR, Alathur S. Assessing mobile health applications with Twitter analytics. Int J Med Inform 2018 May;113:72-84.

[doi: 10.1016/j.ijmedinf.2018.02.016] [Medline: 29602436]

45. Zhang L, Hall M, Bastola D. Utilizing Twitter data for analysis of chemotherapy. Int J Med Inform 2018 Dec;120:92-100.

[doi: 10.1016/j.ijmedinf.2018.10.002] [Medline: 30409350]

46. Roccetti M, Marfia G, Salomoni P, Prandi C, Zagari RM, Kengni FL, et al. Attitudes of Crohn's disease patients:

infodemiology case study and sentiment analysis of Facebook and Twitter posts. JMIR Public Health Surveill 2017 Aug

9;3(3):e51 [FREE Full text] [doi: 10.2196/publichealth.7004] [Medline: 28793981]

47. Islam MR, Kabir MA, Ahmed A, Kamal AR, Wang H, Ulhaq A. Depression detection from social network data using

machine learning techniques. Health Inf Sci Syst 2018 Dec;6(1):8. [doi: 10.1007/s13755-018-0046-0] [Medline: 30186594]

48. Ricard BJ, Marsch LA, Crosier B, Hassanpour S. Exploring the utility of community-generated social media content for

detecting depression: an analytical study on Instagram. J Med Internet Res 2018 Dec 6;20(12):e11817 [FREE Full text]

[doi: 10.2196/11817] [Medline: 30522991]

49. Oksanen A, Garcia D, Sirola A, Näsi M, Kaakinen M, Keipi T, et al. Pro-anorexia and anti-pro-anorexia videos on YouTube:

sentiment analysis of user responses. J Med Internet Res 2015 Nov 12;17(11):e256 [FREE Full text] [doi: 10.2196/jmir.5007]

[Medline: 26563678]

50. Livas C, Delli K, Pandis N. 'My Invisalign experience': content, metrics and comment sentiment analysis of the most popular patient testimonials on YouTube. Prog Orthod 2018 Jan 22;19(1):3 [FREE Full text] [doi: 10.1186/s40510-017-0201-1]

[Medline: 29354889]

51. Alada AE, Muderrisoglu S, Akbas NB, Zahmacioglu O, Bingol HO. Detecting suicidal ideation on forums: proof-of-concept

study. J Med Internet Res 2018 Jun 21;20(6):e215 [FREE Full text] [doi: 10.2196/jmir.9840] [Medline: 29929945]

52. Adams DZ, Gruss R, Abrahams AS. Automated discovery of safety and efficacy concerns for joint & muscle pain relief

treatments from online reviews. Int J Med Inform 2017 Apr;100:108-120. [doi: 10.1016/j.ijmedinf.2017.01.005] [Medline:

28241932]

53. Carrillo-de-Albornoz J, Vidal JR, Plaza L. Feature engineering for sentiment analysis in e-health forums. PLoS One

2018;13(11):e0207996 [FREE Full text] [doi: 10.1371/journal.pone.0207996] [Medline: 30496232]

54. Carrillo-de-Albornoz J, Aker A, Kurtic E, Plaza L. Beyond opinion classification: extracting facts, opinions and experiences

from health forums. PLoS One 2019;14(1):e0209961 [FREE Full text] [doi: 10.1371/journal.pone.0209961] [Medline:

30625206]

55. RateMDs. URL: https://www.ratemds.com/ [accessed 2019-11-12]

56. Alemi F, Torii M, Clementz L, Aron DC. Feasibility of real-time satisfaction surveys through automated analysis of patients' unstructured comments and sentiments. Qual Manag Health Care 2012;21(1):9-19. [doi: 10.1097/QMH.0b013e3182417fc4]

[Medline: 22207014]

57. Wallace BC, Paul MJ, Sarkar U, Trikalinos TA, Dredze M. A large-scale quantitative analysis of latent factors and sentiment in online doctor reviews. J Am Med Inform Assoc 2014;21(6):1098-1103 [FREE Full text] [doi:

10.1136/amiajnl-2014-002711] [Medline: 24918109]

58. Hopper AM, Uriyo M. Using sentiment analysis to review patient satisfaction data located on the internet. J Health Organ

Manag 2015;29(2):221-233. [doi: 10.1108/JHOM-12-2011-0129] [Medline: 25800334]

59. WebMD - Better information. Better health. URL: https://www.webmd.com/ [accessed 2019-11-12]

60. Huh J, Yetisgen-Yildiz M, Pratt W. Text classification for assisting moderators in online health communities. J Biomed

Inform 2013 Dec;46(6):998-1005 [FREE Full text] [doi: 10.1016/j.jbi.2013.08.011] [Medline: 24025513]

61. Noferesti S, Shamsfard M. Resource construction and evaluation for indirect opinion mining of drug reviews. PLoS One

2015;10(5):e0124993 [FREE Full text] [doi: 10.1371/journal.pone.0124993] [Medline: 25962135]

62. Ask a Patient. URL: https://www.askapatient.com/ [accessed 2019-11-12]

63. Noferesti S, Shamsfard M. Using Linked Data for polarity classification of patients' experiences. J Biomed Inform 2015

Oct;57:6-19 [FREE Full text] [doi: 10.1016/j.jbi.2015.06.017] [Medline: 26210363]

64. DrugLib. URL: http://www.druglib.com/ [accessed 2019-11-12]

65. Asghar MZ, Ahmad S, Qasim M, Zahra SR, Kundi FM. SentiHealth: creating health-related sentiment lexicon using hybrid

approach. Springerplus 2016;5(1):1139 [FREE Full text] [doi: 10.1186/s40064-016-2809-x] [Medline: 27504237]

66. Breast Cancer Information and Support. URL: https://www.breastcancer.org/ [accessed 2019-11-12]

67. Zhang S, Bantum E, Owen J, Elhadad N. Does sustained participation in an online health community affect sentiment?

AMIA Annu Symp Proc 2014;2014:1970-1979 [FREE Full text] [Medline: 25954470]

68. Cabling ML, Turner JW, Hurtado-de-Mendoza A, Zhang Y, Jiang X, Drago F, et al. Sentiment analysis of an online breast

cancer support group: communicating about tamoxifen. Health Commun 2018 Sep;33(9):1158-1165 [FREE Full text] [doi:

10.1080/10410236.2017.1339370] [Medline: 28678549]

69. MedHelp. URL: https://medhelp.org/ [accessed 2019-11-12]

70. Yang FC, Lee AJ, Kuo SC. Mining health social media with sentiment analysis. J Med Syst 2016 Nov;40(11):236. [doi:

10.1007/s10916-016-0604-4] [Medline: 27663246]

71. Lu Y, Wu Y, Liu J, Li J, Zhang P. Understanding health care social media use from different stakeholder perspectives: a

content analysis of an online health community. J Med Internet Res 2017 Apr 7;19(4):e109 [FREE Full text] [doi:

10.2196/jmir.7087] [Medline: 28389418]

72. DailyStrength. URL: https://www.dailystrength.org/

73. Cancer Survivor Network. URL: http://csn.cancer.org/ [accessed 2019-11-12]

74. Portier K, Greer GE, Rokach L, Ofek N, Wang Y, Biyani P, et al. Understanding topics and sentiment in an online cancer

survivor community. J Natl Cancer Inst Monogr 2013 Dec;2013(47):195-198. [doi: 10.1093/jncimonographs/lgt025]

[Medline: 24395991]

75. Zhao K, Yen J, Greer G, Qiu B, Mitra P, Portier K. Finding influential users of online health communities: a new metric

based on sentiment influence. J Am Med Inform Assoc 2014 Oct;21(e2):e212-e218 [FREE Full text] [doi:

10.1136/amiajnl-2013-002282] [Medline: 24449805]

76. Bui N, Yen J, Honavar V. Temporal causality analysis of sentiment change in a cancer survivor network. IEEE Trans

Comput Soc Syst 2016 Jun;3(2):75-87 [FREE Full text] [doi: 10.1109/TCSS.2016.2591880] [Medline: 29399599]

77. National Health Service. URL: https://www.nhs.uk/ [accessed 2019-11-12]

78. Greaves F, Ramirez-Cano D, Millett C, Darzi A, Donaldson L. Use of sentiment analysis for capturing patient experience

from free-text comments posted online. J Med Internet Res 2013 Nov 1;15(11):e239 [FREE Full text] [doi: 10.2196/jmir.2721]

[Medline: 24184993]

79. DiabetesDaily. URL: https://www.diabetesdaily.com [accessed 2019-11-12]

80. Akay A, Dragomir A, Erlandsson B. A novel data-mining approach leveraging social media to monitor consumer opinion

of sitagliptin. IEEE J Biomed Health Inform 2015 Jan;19(1):389-396. [doi: 10.1109/JBHI.2013.2295834] [Medline:

25561458]

81. Pestian JP, Matykiewicz P, Linn-Gust M, South B, Uzuner O, Wiebe J, et al. Sentiment analysis of suicide notes: a shared

task. Biomed Inform Insights 2012 Jan 30;5(Suppl 1):3-16 [FREE Full text] [doi: 10.4137/bii.s9042] [Medline: 22419877]

82. Cherry C, Mohammad SM, de Bruijn B. Binary classifiers and latent sequence models for emotion detection in suicide

notes. Biomed Inform Insights 2012;5(Suppl. 1):147-154 [FREE Full text] [doi: 10.4137/BII.S8933] [Medline: 22879771]

83. Desmet B, Hoste V. Combining lexico-semantic features for emotion classification in suicide notes. Biomed Inform Insights

2012;5(Suppl 1):125-128 [FREE Full text] [doi: 10.4137/BII.S8960] [Medline: 22879768]

84. Dzogang F, Lesot M, Rifqi M, Bouchon-Meunier B. Early fusion of low level features for emotion mining. Biomed Inform

Insights 2012;5(Suppl 1):129-136 [FREE Full text] [doi: 10.4137/BII.S8973] [Medline: 22879769]

85. Liakata M, Kim J, Saha S, Hastings J, Rebholz-Schuhmann D. Three hybrid classifiers for the detection of emotions in

suicide notes. Biomed Inform Insights 2012;5(Suppl 1):175-184 [FREE Full text] [doi: 10.4137/BII.S8967] [Medline:

22879774]

86. Luyckx K, Vaassen F, Peersman C, Daelemans W. Fine-grained emotion detection in suicide notes: a thresholding approach

to multi-label classification. Biomed Inform Insights 2012;5(Suppl 1):61-69 [FREE Full text] [doi: 10.4137/BII.S8966]

[Medline: 22879761]

87. McCart JA, Finch DK, Jarman J, Hickling E, Lind JD, Richardson MR, et al. Using ensemble models to classify the

sentiment expressed in suicide notes. Biomed Inform Insights 2012;5(Suppl 1):77-85 [FREE Full text] [doi:

10.4137/BII.S8931] [Medline: 22879763]

88. Nikfarjam A, Emadzadeh E, Gonzalez G. A hybrid system for emotion extraction from suicide notes. Biomed Inform

Insights 2012;5(Suppl 1):165-174 [FREE Full text] [doi: 10.4137/BII.S8981] [Medline: 22879773]

89. Pak A, Bernhard D, Paroubek P, Grouin C. A combined approach to emotion detection in suicide notes. Biomed Inform

Insights 2012;5(Suppl 1):105-114 [FREE Full text] [doi: 10.4137/BII.S8969] [Medline: 22879766]

90. Pedersen T. Rule-based and lightly supervised methods to predict emotions in suicide notes. Biomed Inform Insights

2012;5(Suppl 1):185-193 [FREE Full text] [doi: 10.4137/BII.S8953] [Medline: 22879775]

91. Read J, Velldal E, Ovrelid L. Labeling emotions in suicide notes: cost-sensitive learning with heterogeneous features.

Biomed Inform Insights 2012;5(Suppl 1):99-103 [FREE Full text] [doi: 10.4137/BII.S8930] [Medline: 22879765]

92. Roberts K, Harabagiu SM. Statistical and similarity methods for classifying emotion in suicide notes. Biomed Inform

Insights 2012;5(Suppl 1):195-204 [FREE Full text] [doi: 10.4137/BII.S8958] [Medline: 22879776]

93. Sohn S, Torii M, Li D, Wagholikar K, Wu S, Liu H. A hybrid approach to sentiment sentence classification in suicide notes.

Biomed Inform Insights 2012;5(Suppl 1):43-50 [FREE Full text] [doi: 10.4137/BII.S8961] [Medline: 22879759]

94. Spasi I, Burnap P, Greenwood M, Arribas-Ayllon M. A naïve Bayes approach to classifying topics in suicide notes. Biomed

Inform Insights 2012;5(Suppl 1):87-97 [FREE Full text] [doi: 10.4137/BII.S8945] [Medline: 22879764]

95. Wang W, Chen L, Tan M, Wang S, Sheth AP. Discovering fine-grained sentiment in suicide notes. Biomed Inform Insights

2012;5(Suppl 1):137-145 [FREE Full text] [doi: 10.4137/BII.S8963] [Medline: 22879770]

96. Wicentowski R, Sydes MR. Emotion detection in suicide notes using maximum entropy classification. Biomed Inform

Insights 2012;5(Suppl 1):51-60 [FREE Full text] [doi: 10.4137/BII.S8972] [Medline: 22879760]

97. Xu Y, Wang Y, Liu J, Tu Z, Sun J, Tsujii J, et al. Suicide note sentiment classification: a supervised approach augmented

by web data. Biomed Inform Insights 2012;5(Suppl 1):31-41 [FREE Full text] [doi: 10.4137/BII.S8956] [Medline: 22879758]

98. Yang H, Willis A, de Roeck A, Nuseibeh B. A hybrid model for automatic emotion recognition in suicide notes. Biomed

Inform Insights 2012;5(Suppl 1):17-30 [FREE Full text] [doi: 10.4137/BII.S8948] [Medline: 22879757]

99. Yeh E, Jarrold W, Jordan J. Leveraging psycholinguistic resources and emotional sequence models for suicide note emotion

annotation. Biomed Inform Insights 2012;5(Suppl 1):155-163 [FREE Full text] [doi: 10.4137/BII.S8979] [Medline:

22879772]

100. Yu N, Kübler S, Herring J, Hsu Y, Israel R, Smiley C. LASSA: emotion detection via information fusion. Biomed Inform

Insights 2012;5(Suppl. 1):71-76 [FREE Full text] [doi: 10.4137/BII.S8949] [Medline: 22879762]

101. Mammen JR, Java JJ, Rhee H, Butz AM, Halterman JS, Arcoleo K. Mixed-methods content and sentiment analysis of

adolescents' voice diaries describing daily experiences with asthma and self-management decision-making. Clin Exp Allergy

2019 Mar;49(3):299-307. [doi: 10.1111/cea.13250] [Medline: 30113733]

102. Asghar MZ, Khan A, Ahmad S, Qasim M, Khan IA. Lexicon-enhanced sentiment analysis framework using rule-based

classification scheme. PLoS One 2017;12(2):e0171649 [FREE Full text] [doi: 10.1371/journal.pone.0171649] [Medline:

28231286]

103. Cobb NK, Mays D, Graham AL. Sentiment analysis to determine the impact of online messages on smokers' choices to

use varenicline. J Natl Cancer Inst Monogr 2013 Dec;2013(47):224-230. [doi: 10.1093/jncimonographs/lgt020] [Medline:

24395996]

104. Cohn AM, Amato MS, Zhao K, Wang X, Cha S, Pearson JL, et al. Discussions of alcohol use in an online social network

for smoking cessation: analysis of topics, sentiment, and social network centrality. Alcohol Clin Exp Res 2019

Jan;43(1):108-114. [doi: 10.1111/acer.13906] [Medline: 30326140]

105. Chu KH, Valente TW. How different countries addressed the sudden growth of e-cigarettes in an online tobacco control

community. BMJ Open 2015 May 21;5(5):e007654 [FREE Full text] [doi: 10.1136/bmjopen-2015-007654] [Medline:

25998038]

106. Chen Z, Zeng DD. Mining online e-liquid reviews for opinion polarities about e-liquid features. BMC Public Health 2017

Jul 7;17(1):633 [FREE Full text] [doi: 10.1186/s12889-017-4533-z] [Medline: 28683797]

107. Doing-Harris K, Mowery D, Daniels C, Chapman W, Conway M. Understanding patient satisfaction with received healthcare

services: a natural language processing approach. AMIA Annu Symp Proc 2016;2016:524-533 [FREE Full text] [Medline:

28269848]

108. Alemi F, Jasper H. An alternative to satisfaction surveys: let the patients talk. Qual Manag Health Care 2014;23(1):10-19.

[doi: 10.1097/QMH.0000000000000014] [Medline: 24368718]

109. Diorio C, Afanasiev M, Salena K, Marjerrison S. 'A world of competing sorrows': a mixed methods analysis of media

reports of children with cancer abandoning conventional treatment. PLoS One 2018;13(12):e0209738 [FREE Full text]

[doi: 10.1371/journal.pone.0209738] [Medline: 30576389]

110. Corley C, Mihalcea R, Mikler A, Sanfilippo A. Predicting individual affect of health interventions to reduce HPV prevalence. In: Arabnia H, Tran QN, editors. Software Tools and Algorithms for Biological Systems. New York, New York, USA:

Springer; 2011:181-190.

111. Jung H, Park H, Song T. Ontology-based approach to social data sentiment analysis: detection of adolescent depression

signals. J Med Internet Res 2017 Jul 24;19(7):e259 [FREE Full text] [doi: 10.2196/jmir.7452] [Medline: 28739560]

112. Chen L, Gong T, Kosinski M, Stillwell D, Davidson RL. Building a profile of subjective well-being for social media users.

PLoS One 2017;12(11):e0187278 [FREE Full text] [doi: 10.1371/journal.pone.0187278] [Medline: 29135991]

113. Rastegar-Mojarad M, Ye Z, Wall D, Murali N, Lin S. Collecting and analyzing patient experiences of health care from

social media. JMIR Res Protoc 2015 Jul 2;4(3):e78 [FREE Full text] [doi: 10.2196/resprot.3433] [Medline: 26137885]

114. Liu R, Zhang X, Zhang H. Web-video-mining-supported workflow modeling for laparoscopic surgeries. Artif Intell Med

2016 Nov;74:9-20. [doi: 10.1016/j.artmed.2016.11.002] [Medline: 27964803]

115. SVM light. URL: http://svmlight.joachims.org/ [accessed 2019-11-12]

116. Cauchois B. pysvmlight. URL: https://bitbucket.org/wcauchois/pysvmlight [accessed 2019-11-12]

117. LIBSVM -- A Library for Support Vector Machines. URL: https://www.csie.ntu.edu.tw/~cjlin/libsvm/ [accessed 2019-11-12]

118. Dashtipour K, Poria S, Hussain A, Cambria E, Hawalah AY, Gelbukh A, et al. Multilingual sentiment analysis: state of the

art and independent comparison of techniques. Cognit Comput 2016;8:757-771 [FREE Full text] [doi:

10.1007/s12559-016-9415-7] [Medline: 27563360]

119. Department of Computer Science: University of Waikato. URL: https://www.cs.waikato.ac.nz/ml/weka/ [accessed 2019-11-12]

120. scikit-learn. URL: https://scikit-learn.org/ [accessed 2019-11-12]

121. Keras Documentation. URL: https://keras.io/ [accessed 2019-11-12]

122. TextBlob: Simplified Text Processing. URL: https://textblob.readthedocs.io/en/dev/ [accessed 2019-11-12]

123. Wolpert DH. The lack of a priori distinctions between learning algorithms. Neural Comput 1996;8(7):1341-1390 [FREE

Full text] [doi: 10.1162/neco.1996.8.7.1341]

124. Hutto C, Gilbert E. Vader: A parsimonious rule-based model for sentiment analysis of social media text. In: Proceedings

of Eighth International AAAI Conference on Weblogs and Social Media. 2014 Presented at: ICWSM-14; June 1–4, 2014;

Ann Arbor, Michigan, USA.

125. Yang Z, Dai Z, Yang Y, Carbonell J, Salakhutdinov R, Le QV. XLNet: Generalized autoregressive pretraining for language

understanding. arXiv 2019 [FREE Full text]

126. Howard J, Ruder S. Universal Language Model Fine-tuning for Text Classification. In: Proceedings of the 56th Annual

Meeting of the Association for Computational Linguistics. 2018 Presented at: ACL'18; July 15-20, 2018; Melbourne,

Australia p. 328-339. [doi: 10.18653/v1/p18-1031]

127. Gray S, Radford A, Kingma DP. GPU kernels for block-sparse weights. arXiv 2017 [FREE Full text]

128. Johnson R, Zhang T. Supervised and Semi-supervised Text Categorization Using LSTM for Region Embeddings. In:

Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48. 2016

Presented at: ICML'16; June 19 - 24, 2016; New York, New York, USA p. 526-534 URL: https://arxiv.org/abs/1602.02373

129. Xu H, Liu B, Shu L, Yu PS. BERT Post-training for review reading comprehension and aspect-based sentiment analysis.

In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:

Human Language Technologies, Volume 1. 2019 Presented at: NAACL'19; June 3-5, 2019; Minneapolis, USA p. 2324-2335

URL: https://arxiv.org/abs/1904.02232

130. Huang B, Ou Y, Carley K. Aspect Level Sentiment Classification With Attention-over-attention Neural Networks. In:

International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction and Behavior Representation

in Modeling and Simulation. 2018 Presented at: SBP-BRiMS'18; July 10-13, 2018; Washington, DC, USA p. 197-206

URL: https://arxiv.org/abs/1804.06536 [doi: 10.1007/978-3-319-93372-6_22]

131. Li X, Bing L, Lam W, Shi B. Transformation Networks for Target-oriented Sentiment Classification. In: Proceedings of

the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018 Presented at:

ACL'18; July 15-20, 2018; Melbourne, Australia p. 946-956 URL: https://arxiv.org/abs/1805.01086 [doi:

10.18653/v1/p18-1087]

132. Chen P, Sun Z, Bing L, Yang W. Recurrent Attention Network on Memory for Aspect Sentiment Analysis. In: Proceedings

of the 2017 Conference on Empirical Methods in Natural Language Processing. 2017 Presented at: the Conference on

Empirical Methods in Natural Language Processing; September 7–11, 2017; Copenhagen, Denmark p. 452-461 URL:

https://www.aclweb.org/anthology/D17-1047/ [doi: 10.18653/v1/d17-1047]

133. Xu H, Liu B, Shu L, Yu P. Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction. In: Proceedings

of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2018 Presented

at: ACL'18; July 15-20, 2018; Melbourne, Australia p. 592-598 URL: https://www.aclweb.org/anthology/P18-2094/ [doi:

10.18653/v1/p18-2094]

134. Li X, Lam W. Deep Multi-task Learning for Aspect Term Extraction With Memory Interaction. In: Proceedings of the

2017 Conference on Empirical Methods in Natural Language Processing. 2017 Presented at: EMNLP'17; September 7–11,

2017; Copenhagen, Denmark p. 2886-2892 URL: https://www.aclweb.org/anthology/D17-1310/ [doi: 10.18653/v1/d17-1310]

135. Wang W, Pan S, Dahlmeier D, Xiao X. Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis.

In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 2016 Presented at:

EMNLP'16; November 1–5, 2016; Austin, Texas, USA p. 616-626 URL: https://www.aclweb.org/anthology/D16-1059/

[doi: 10.18653/v1/d16-1059]

136. Manning C, Surdeanu M, Bauer J, Finkel J, Bethard S, McClosky D. The Stanford CoreNLP natural language processing

toolkit. In: Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations.

2014 Presented at: ACL'14; June 22-27, 2014; Baltimore, Maryland, USA p. 55-60 URL: https://www.aclweb.org/anthology/

P14-5010/ [doi: 10.3115/v1/p14-5010]

137. Bird S. NLTK: The Natural Language Toolkit. In: Proceedings of the COLING/ACL on Interactive presentation sessions.

2006 Presented at: COLING-ACL'06; July 17 - 18, 2006; Sydney, Australia p. 69-72 URL: https://www.aclweb.org/

anthology/P06-4018/ [doi: 10.3115/1225403.1225421]

138. Friedman C, Kra P, Rzhetsky A. Two biomedical sublanguages: a description based on the theories of Zellig Harris. J

Biomed Inform 2002 Aug;35(4):222-235 [FREE Full text] [doi: 10.1016/s1532-0464(03)00012-1] [Medline: 12755517]

139. Bodenreider O. The Unified Medical Language System (UMLS): integrating biomedical terminology. Nucleic Acids Res

2004 Jan 1;32(Database issue):D267-D270 [FREE Full text] [doi: 10.1093/nar/gkh061] [Medline: 14681409]

140. Demner-Fushman D, Rogers WJ, Aronson AR. MetaMap Lite: an evaluation of a new Java implementation of MetaMap.

J Am Med Inform Assoc 2017 Jul 1;24(4):841-844 [FREE Full text] [doi: 10.1093/jamia/ocw177] [Medline: 28130331]

141. Bradley MM, Lang PJ. The University of Vermont. 1999. Affective Norms for English Words (ANEW): Instruction Manual

and Affective Ratings URL: https://www.uvm.edu/pdodds/teaching/courses/2009-08UVM-300/docs/others/everything/

bradley1999a.pdf [accessed 2019-11-12]

142. Center for the Study of Emotion and Attention. ANEW Message URL: https://csea.phhp.ufl.edu/media/anewmessage.html

[accessed 2019-11-12]

143. Nielsen FA. A new ANEW: Evaluation of a word list for sentiment analysis in microblogs. In: Proceedings of the ESWC

2011 Workshop on 'Making Sense of Microposts': Big things come in small packages. 2011 Presented at: ESWC'11; 2011;

Heraklion, Greece p. 93-98 URL: https://arxiv.org/abs/1103.2903

144. AFINN. URL: http://www2.imm.dtu.dk/pubdb/views/publication_details.php?id=6010 [accessed 2019-11-12]

145. Stone PJ, Dunphy DC, Smith MS, Ogilvie DM. General Inquirer: A Computer Approach to Content Analysis. Cambridge,

Massachusetts, USA: MIT Press; 1966.

146. Harvard General Inquirer. URL: http://www.wjh.harvard.edu/~inquirer/homecat.htm [accessed 2019-11-12]

147. Dodds PS, Harris KD, Kloumann IM, Bliss CA, Danforth CM. Temporal patterns of happiness and information in a global

social network: hedonometrics and Twitter. PLoS One 2011;6(12):e26752 [FREE Full text] [doi:

10.1371/journal.pone.0026752] [Medline: 22163266]

148. Language Assessment by Mechanical Turk (labMT) Sentiment Words. URL: https://trinker.github.io/qdapDictionaries/

labMT.html [accessed 2019-11-12]

149. Wilson T, Wiebe J, Hoffmann P. Recognizing Contextual Polarity in Phrase-level Sentiment Analysis. In: Proceedings of

the conference on Human Language Technology and Empirical Methods in Natural Language Processing. 2005 Presented

at: HLT'05; October 06 - 08, 2005; Vancouver, Canada p. 347-354 URL: https://dl.acm.org/citation.cfm?id=1220619 [doi:

10.3115/1220575.1220619]

150. MPQA. URL: http://mpqa.cs.pitt.edu/ [accessed 2019-11-12]

151. Mohammad SM, Turney PD. Crowdsourcing a word-emotion association lexicon. Comput Intel 2013;29(3):436-465 [FREE

Full text] [doi: 10.1111/j.1467-8640.2012.00460.x]

152. NRC Emotion Lexicon. URL: http://sentiment.nrc.ca/lexicons-for-research/ [accessed 2019-11-12]

153. OpinionKB. URL: https://doi.org/10.1371/journal.pone.0124993.s001

154. Opinion Lexicon. URL: https://www.cs.uic.edu/~liub/FBS/sentiment-analysis.html#lexicon [accessed 2019-11-12]

155. de Albornoz JC, Plaza L, Gervás P. SentiSense: An easily scalable concept-based affective lexicon for sentiment analysis.

In: Proceedings of the Eighth International Conference on Language Resources and Evaluation. 2012 Presented at: LREC'12;

May 21-27, 2012; Istanbul, Turkey p. 3562-3567 URL: https://www.aclweb.org/anthology/L12-1089/

156. SentiSense Affective Lexicon. URL: http://nlp.uned.es/~jcalbornoz/SentiSense.html [accessed 2019-11-12]

157. Baccianella S, Esuli A, Sebastiani F. SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion

Mining. In: Proceedings of the Seventh International Conference on Language Resources and Evaluation. 2010 Presented

at: LREC'10; May 17-23, 2010; Valletta, Malta p. 2200-2204 URL: https://www.aclweb.org/anthology/L10-1531/

158. SentiWordNet. URL: http://sentiwordnet.isti.cnr.it/ [accessed 2019-11-12]

159. Strapparava C, Valitutti A. WordNet Affect: An Affective Extension of WordNet. In: Proceedings of the Fourth International Conference on Language Resources and Evaluation. 2004 Presented at: LREC’04; May 26-28, 2004; Lisbon, Portugal

URL: https://www.aclweb.org/anthology/L04-1208/

160. WordNet Domains. WordNet-Affect URL: http://wndomains.fbk.eu/wnaffect.html [accessed 2019-11-12]

161. Turney PD, Littman ML. Measuring praise and criticism: Inference of semantic orientation from association. ACM Trans

Inf Syst 2003;21(4):315-346. [doi: 10.1145/944012.944013]

162. Taboada M, Anthony C, Voll K. Methods for Creating Semantic Orientation Dictionaries. In: Proceedings of the Fifth

International Conference on Language Resources and Evaluation. 2006 Presented at: LREC’06; May 22-28, 2006; Genoa,

Italy p. 427-432 URL: https://www.aclweb.org/anthology/L06-1250/

163. Du W, Tan S, Cheng X, Yun X. Adapting Information Bottleneck Method for Automatic Construction of Domain-oriented

Sentiment Lexicon. In: Proceedings of the third ACM international conference on Web search and data mining. 2010

Presented at: WSDM'10; February 4 - 6, 2010; New York, New York, USA p. 111-120 URL: https://dl.acm.org/citation.

cfm?id=1718502 [doi: 10.1145/1718487.1718502]

164. Miller GA. WordNet: a lexical database for English. Commun ACM 1995;38(11):39-41 [FREE Full text] [doi:

10.1145/219717.219748]

165. Kim S, Hovy E. Determining the Sentiment of Opinions. In: Proceedings of the 20th international conference on

Computational Linguistics. 2004 Presented at: COLING'04; August 23 - 27, 2004; Geneva, Switzerland URL: https://www.

aclweb.org/anthology/C04-1200/ [doi: 10.3115/1220355.1220555]

166. Kamps J, Marx M, Mokken R, Rijke M. Using WordNet to Measure Semantic Orientations of Adjectives. In: Proceedings

of the Fourth International Conference on Language Resources and Evaluation. 2004 Presented at: LREC’04; May 26-28,

2004; Lisbon, Portugal p. 1115-1118 URL: https://www.aclweb.org/anthology/L04-1473/

167. Hassan A, Radev D. Identifying Text Polarity Using Random Walks. In: Proceedings of the 48th Annual Meeting of the

Association for Computational Linguistics. 2010 Presented at: ACL'10; July 11 - 16, 2010; Uppsala, Sweden p. 395-403

URL: https://www.aclweb.org/anthology/P10-1041/

168. Dragut E, Yu C, Sistla P, Meng W. Construction of a Sentimental Word Dictionary. In: Proceedings of the 19th ACM

international conference on Information and knowledge management. 2010 Presented at: CIKM'10; October 26 - 30, 2010;

Toronto, Canada p. 1761-1764. [doi: 10.1145/1871437.1871723]

169. Lu Y, Castellanos M, Dayal U, Zhai C. Automatic Construction of a Context-aware Sentiment Lexicon: An Optimization

Approach. In: Proceedings of the 20th international conference on World wide web. 2011 Presented at: WWW'11; March 28 - April 1, 2011; Hyderabad, India p. 347-356 URL: https://dl.acm.org/citation.cfm?id=1963456 [doi:

10.1145/1963405.1963456]

https://medinform.jmir.org/2020/1/e16023