Text classification for assisting moderators in online health communities
Journal of Biomedical InformaticsPublished 8 September 2013Open access
Jina Huh, Meliha Yetisgen-Yildiz, Wanda Pratt
Citations95
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This work explores low-cost text classification methods to this new domain of determining whether a thread in an online health forum needs moderators' help and shows how feature selection methods and balanced training data can improve the overall classification performance.
Abstract
Social media environments provide popular venues in which patients gain health-related information. Our work contributes to understanding scalable solutions for providing moderators' expertise in these large-scale, social media environments.
Keywords
Computer ScienceHealth ProfessionsSocial Sciences
ACM SIGKDD Explorations NewsletterThe WEKA data mining software
17,849 Citations2009Mark Hall, Eibe Frank +4 more
This paper provides an introduction to the WEKA workbench, reviews the history of the project, and, in light of the recent 3.6 stable release, briefly discusses what has been added since the last stable version (Weka 3.4) released in 2003.
Foundations of statistical natural language processing
9,996 Citations1999Christopher D. Manning, Hinrich Schütze
ACM Computing SurveysMachine learning in automated text categorization
7,899 Citations2002Fabrizio Sebastiani
This survey discusses the main approaches to text categorization that fall within the machine learning paradigm and discusses in detail issues pertaining to three different problems, namely, document representation, classifier construction, and classifier evaluation.
Journal of Language and Social PsychologyThe Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods
5,776 Citations2009Yla Tausczik, James W. Pennebaker
Empirical results using LIWC demonstrate its ability to detect meaning in a wide variety of experimental settings, including to show attentional focus, emotionality, social relationships, thinking styles, and individual differences.
Diabetes CareAssessing Psychosocial Distress in Diabetes
1,554 Citations2005William H. Polonsky, Lawrence Fisher +5 more
The Diabetes Distress Scale has a consistent, generalizable factor structure and good internal reliability and validity across four different clinical sites, and may serve as a valuable measure of diabetes-related emotional distress for use in research and clinical practice.
Journal of the American Medical Informatics AssociationAn overview of MetaMap: historical perspective and recent advances
1,540 Citations2010Alan R. Aronson, François-Michel Lang
This study reports on MetaMap's evolution over more than a decade, concentrating on those features arising out of the research needs of the biomedical informatics community both within and outside of the National Library of Medicine.
Computational IntelligenceA Multiple Resampling Method for Learning from Imbalanced Data Sets
1,022 Citations2004Andrew Estabrooks, Taeho Jo +1 more
It is concluded that combining different expressions of the resampling approach is an effective solution to the tuning problem and the proposed combination scheme is evaluated on imbalanced subsets of the Reuters‐21578 text collection and is shown to be quite effective for these problems.
Cognition & EmotionCognitive, Emotional, and Language Processes in Disclosure
998 Citations1996James W. Pennebaker, Martha E. Francis
An evaluation of phrasal and clustered representations on a text categorization task
547 Citations1992David Lewis
It is shown that optimal effectiveness occurs when using only a small proportion of the indexing terms available, and that effectiveness peaks at a higher feature set size and lower effectiveness level for a syntactic phrase indexing than for word-based indexing.
Predicting postpartum changes in emotion and behavior via social media
472 Citations2013Munmun De Choudhury, Scott Counts +1 more
The opportunity to use social media to identify mothers at risk of postpartum depression, an underreported health concern among large populations, and to inform the design of low-cost, privacy-sensitive early-warning systems and intervention programs aimed at promoting wellness post partum is motivated by the opportunity.
Psychological ScienceThe Secret Life of Pronouns
432 Citations2003R. Sherlock Campbell, James W. Pennebaker
The writing samples from three previously published studies were reanalyzed using Latent Semantic Analysis to explore possible relationships of writing content and style to changes in frequency of physician visits following the disclosure intervention and revealed flexibility in the use of common words when writing about traumatic memories was related to positive health outcomes.
Journal of Medical Internet ResearchManaging the Personal Side of Health: How Patient Expertise Differs from the Expertise of Clinicians
263 Citations2011Andrea L. Hartzler, Wanda Pratt
Patients offer other patients substantial expertise that differs significantly from the expertise offered by health professionals, and the findings suggest that experienced patients do not necessarily serve as “amateur doctors” who offer more accessible but less comprehensive or detailed medical information.
Sage Pub. eBooksDescribing talk : a taxonomy of verbal response modes
255 Citations1992William B. Stiles
Journal of Biomedical InformaticsAskHERMES: An online question answering system for complex clinical questions
237 Citations2011Yong-gang Cao, Feifan Liu +6 more
A clinical question answering system named AskHERMES is built to perform robust semantic analysis on complex clinical questions and output question-focused extractive summaries as answers and demonstrates the potential to outperform both Google and UpToDate systems.
Decision Support SystemsPreprocessing unbalanced data using support vector machine
183 Citations2012M.A.H. Farquad, Indranil Bose
It is observed that the proposed approach not only balances the data effectively but also provides more number of instances for minority class, which in turn enhances the performance of the intelligence techniques.
Social media mining for drug safety signal detection
143 Citations2012Christopher C. Yang, Haodong Yang +2 more
This work proposes to use association mining and Proportional Reporting Ratios to mine the associations between drugs and adverse reactions from the user contributed content in social media and shows that the metrics leverage, lift, and PRR are all promising to detect the adverse drug reactions reported by FDA.
Journal of the American Medical Informatics AssociationApplying active learning to high-throughput phenotyping algorithms for electronic health records data
119 Citations2013Yukun Chen, Robert J. Carroll +5 more
This study demonstrated that AL can be useful in ML-based phenotyping methods and that AL and feature engineering based on domain knowledge could be combined to develop efficient and generalizable phenotypesing methods.
PubMedBeyond information retrieval--medical question answering.
99 Citations2006Minsuk Lee, James J. Cimino +5 more
The authors address physicians' information needs and described the design, implementation, and evaluation of the medical question answering system (MedQA), which aims to enable MedQA to answer all types of medical questions.
Get Online Support, Feel Better -- Sentiment Analysis and Dynamics in an Online Cancer Survivor Community
95 Citations2011Baojun Qiu, Kang Zhao +6 more
This first study of sentiment benefits and dynamics in a large-scale health-related electronic community finds that an estimated 75\%--85\% of CSN forum participants change their sentiment in a positive direction through online interactions with other community members.
The Journal of General PsychologyThe Relations Between Personality and Language Use
83 Citations2007Chang H. Lee, Kyungil Kim +2 more
Native Korean-speaking students at Pusan National University completed 2 personality tests and completed a stream-of-consciousness essay, which was analyzed using the Korean version of Linguistic Inquiry and Word Count, and personality traits were significantly correlated with linguistic variables.
Studies in health technology and informaticsTowards a Medical Question-Answering System: a Feasibility Study
64 Citations2003P Jacquemart, Zweigenbaum Pierre
The feasibility of a question-answering system for French in the health care domain, using UMLS Semantic Network relations, which is consistent with an existing QA prototype and covers 90% of the questions is studied.
Archives of General PsychiatryVerbal Behavior and Schizophrenia
59 Citations1979Stanley D. Rosenberg
The data shed light on qualities that delineate some aspects of "bizarreness" in speech of schizophrenics, provide some insight into the diversity of postulated "defects" in schizophrenic thinking, and provide further understanding of the diagnostic process in schizophrenia.
SAR and QSAR in environmental researchClassification ensembles for unbalanced class sizes in predictive toxicology
55 Citations2005J J Chen, Chen‐An Tsai +2 more
The effects of the ratio of positive-to-negative samples on the sensitivity, specificity, and concordance are investigated and an ensemble classification approach to adjust for differential class sizes in a binary classifier system is proposed.
Tackling dilemmas in supporting 'the whole person' in online patient communities
47 Citations2012Jina Huh, Rupa Patel +1 more
A sample of online patient communities found the communities fall short in supporting the whole person, because patient expertise and clinical expertise generated by health professionals are shared separately, and patients' quantified data are separate from narrative experiences.
Medical WordNet
46 Citations2004Barry Smith, Christiane Fellbaum
An ongoing project to create a new lexical database called Medical WordNet (MWN), consisting of medically relevant terms used by and intelligible to non-expert subjects and supplemented by a corpus of natural-language sentences that is designed to provide medically validated contexts for MWN terms.
PubMedPatient moderator interaction in online health communities.
40 Citations2013Jina Huh, David W. McDonald +2 more
It is shown that patients use the community as an integral part of their health management practices and suggest enhancements to moderated online health communities for their unique role to support patient care.
Journal of Biomedical InformaticsToward automated consumer question answering: Automatically separating consumer questions from professional questions in the healthcare domain
37 Citations2011Feifan Liu, Lamont Antieau +1 more
Healthcare consumer questions posted at Yahoo online communities can be reliably classified from professional questions posted by point-of-care clinicians and online physicians, and the supervised machine-learning models are robust for this task.
Journal of Medical Internet ResearchText Mining and Natural Language Processing Approaches for Automatic Categorization of Lay Requests to Web-Based Expert Forums
35 Citations2009Wolfgang Himmel, Ulrich Reincke +1 more
The approach suggests a way of automatically classifying and analyzing unstructured information in Internet expert forums and can perform a preliminary categorization of new requests and help Internet medical experts to better handle the mass of information and to give professional feedback.
Journal of the American Medical Informatics AssociationUse of a support vector machine for categorizing free-text notes: assessment of accuracy across two institutions
34 Citations2013Adam Wright, Allison B. McCoy +3 more
It is possible to use a SVM-based classifier to identify EHR progress notes pertaining to diabetes, and the model generalizes well.
Automatic Detection of Psychological Distress Indicators and Severity Assessment from Online Forum Posts
27 Citations2012Shirin Saleem, Rohit Prasad +7 more
A novel system that analyses forum posts to detect distress indicators that directly map to the Diagnostic and Statistical Manual of Mental Disorders (DSM) IV constructs and assess the severity of distress for prioritizing individuals who should seek clinical help (i.e. triage).
Journal of Medical Internet ResearchBiomedical Informatics Techniques for Processing and Analyzing Web Blogs of Military Service Members
26 Citations2010Sergiy Konovalov, Matthew Scotch +2 more
Natural language processing and automated information retrieval might potentially provide valuable tools for retrieving and analyzing military blog posts and uncovering military service members’ emotions and experiences of combat exposure.
Nursing StandardThe whole person
18 Citations2004Alison Kitson
Mary Jackson, a Nursing Standard Nurse of the Year Award winner at the Labour Party conference this year, had created a drop-in centre and, through her activities, had reduced the teenage pregnancy rate in the area.
PubMedSupervised approach to recognize question type in a QA system for health.
17 Citations2008Sarah Cruchet, Arnaud Gaudinat +1 more
A bilingual French/English question answering system adapted to the health domain and more particularly the detection of the question's model is described, which was good to identify the type of answer expected and could be enhanced for the medical type.
Proceedings of the International AAAI Conference on Web and Social MediaWhat Catches Your Attention? An Empirical Study of Attention Patterns in Community Forums
16 Citations2021Claudia Wagner, Matthew Rowe +2 more
Adaptive Agents and Multi-Agents SystemsUsing machine learning to augment collaborative filtering of community discussions
13 Citations2010Michael Brennan, Stacey Wrazien +1 more
This work extracts a wide variety of features from the Slashdot metadata and posts' linguistic contents to identify features that can predict the community rating, and finds that author reputation, use of pronouns, and author sentiment are salient.
AMIAText Classification to Weave Medical Advice with Patient Experiences.
5 Citations2012Jina Huh, Meliha Yetisgen-Yildiz +4 more
Using unigrams, a system is able to predict with 91.9% accuracy whether an answer was written by a health professional or a patient, and classify authorship of answers in online patient community settings.