{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T16:19:03Z","timestamp":1792426743621,"version":"4.5.0"},"reference-count":101,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Patient experience data from social media offer patient-centered perspectives on disease, treatments, and health service delivery. Current guidelines typically rely on systematic reviews, while qualitative health studies are often seen as anecdotal and nongeneralizable. This study explores combining personal health experiences from multiple sources to create generalizable evidence.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The study aims to (1) investigate how combining unsupervised natural language processing (NLP) and corpus linguistics can explore patient perspectives from a large unstructured dataset of modafinil experiences, (2) compare findings with Cochrane meta-analyses on modafinil\u2019s effectiveness, and (3) develop a methodology for analyzing such data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using 69,022 posts from 790 sources, we used a variety of NLP and corpus techniques to analyze the data, including data cleaning techniques to maximize post context, Python for NLP techniques, and Sketch Engine for linguistic analysis. We used multiple topic mining approaches, such as latent Dirichlet allocation, nonnegative matrix factorization, and word-embedding methods. Sentiment analysis used TextBlob and Valence Aware Dictionary and Sentiment Reasoner, while corpus methods including collocation, concordance, and n-gram generation. Previous work had mapped topic mining to themes, such as health conditions, reasons for taking modafinil, symptom impacts, dosage, side effects, effectiveness, and treatment comparisons.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Key findings of the study included modafinil use across 166 health conditions, most frequently narcolepsy, multiple sclerosis, attention-deficit disorder, anxiety, sleep apnea, depression, bipolar disorder, chronic fatigue syndrome, fibromyalgia, and chronic disease. Word-embedding topic modeling mapped 70% of posts to predefined themes, while sentiment analysis revealed 65% positive responses, 6% neutral responses, and 28% negative responses. Notably, the perceived effectiveness of modafinil for various conditions strongly contrasts with the findings of existing randomized controlled trials and systematic reviews, which conclude insufficient or low-quality evidence of effectiveness.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study demonstrated the value of combining NLP with linguistic techniques for analyzing large unstructured text datasets. Despite varying opinions, findings were methodologically consistent and challenged existing clinical evidence. This suggests that patient-generated data could potentially provide valuable insights into treatment outcomes, potentially improving clinical understanding and patient care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/54321","type":"journal-article","created":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T17:00:45Z","timestamp":1733936445000},"page":"e54321","source":"Crossref","is-referenced-by-count":23,"title":["Combining Topic Modeling, Sentiment Analysis, and Corpus Linguistics to Analyze Unstructured Web-Based Patient Experience Data: Case Study of Modafinil Experiences"],"prefix":"10.2196","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9787-0349","authenticated-orcid":false,"given":"Julia","family":"Walsh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9879-6507","authenticated-orcid":false,"given":"Jonathan","family":"Cave","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4173-1438","authenticated-orcid":false,"given":"Frances","family":"Griffiths","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2024,12,11]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2196\/publichealth.5789"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103770"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2196\/16023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-022-01610-z"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/phar.2151"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3109\/09540261.2015.1009419"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2196\/12876"},{"key":"ref8","unstructured":"SureshSPatient-generated health data can provide value in clinical care, research settingsAmerican Academy of Pediatrics News202007012021-05-05https:\/\/www.aappublications.org\/news\/2020\/07\/01\/hit070120"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbx010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41398-020-0780-3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1002\/mpr.1481"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15265\/IY-2016-017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0231422"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.6426"},{"key":"ref15","unstructured":"Number of social media users worldwide from 2017 to 2028Statista2024-11-25https:\/\/www.statista.com\/statistics\/278414\/number-of-worldwide-social-network-users\/"},{"key":"ref16","unstructured":"Social media fact sheetPew Research Center2021-08-09https:\/\/www.pewresearch.org\/internet\/fact-sheet\/social-media\/"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2196\/25736"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3328413.3328415"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/bcp.12746"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.1643"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2021.598431"},{"key":"ref22","author":"Greenhalgh, T","year":"2016","journal-title":"Cultural Contexts of Health: The Use of Narrative Research in the Health Sector"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.2196\/15772"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.infoandorg.2017.03.001"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.312.7023.71"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1185\/03007995.2014.925438"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1136\/jech-2019-213085"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s40290-017-0197-3"},{"key":"ref29","unstructured":"EBM+: integrating diverse evidence in evidence-based medicineUniversity of Kent2024-11-25https:\/\/ebmplus.org\/"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1003266"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-41239-5","author":"Anjum, RL","year":"2020","journal-title":"Rethinking Causality, Complexity and Evidence for the Unique Patient"},{"key":"ref32","unstructured":"Real-world evidenceU.S. Food and Drug Administration20249192024-11-15https:\/\/www.fda.gov\/science-research\/science-and-research-special-topics\/real-world-evidence"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.jamcollsurg.2016.10.025"},{"issue":"2","key":"ref34","first-page":"15","volume":"4","author":"Miani, C","year":"2014","journal-title":"Rand Health Q"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0277-8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.02243"},{"key":"ref38","unstructured":"LeeJWriting linguistic rules for natural language processingMedium201911282020-04-28https:\/\/towardsdatascience.com\/linguistic-rule-writing-for-nlp-ml-64d9af824ee8"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.463"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.9222"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1080\/19312458.2018.1430754"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1002\/asi.23786"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.2196\/21252"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.2721"},{"key":"ref45","author":"Kerry, R","year":"2020","journal-title":"Rethinking Causality, Complexity and Evidence for the Unique Patient"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.socscimed.2017.12.005"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-41239-5","author":"Anjum, RL","year":"2020","journal-title":"Rethinking Causality, Complexity and Evidence for the Unique Patient"},{"key":"ref48","unstructured":"EdwardsRLiving with complexity and big dataUppsala Monitoring Centre2018-11-06https:\/\/view.publitas.com\/uppsala-monitoring-centre\/uppsala-reports-78\/page\/28"},{"key":"ref49","author":"Neeleman, A","year":"2012","journal-title":"The Theta System: Argument Structure at the Interface"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1080\/02698595.2019.1630927"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-015-0437-x"},{"key":"ref52","unstructured":"DaviesNSocial media: the voice of the patientReuters Events20157272024-11-29https:\/\/www.reutersevents.com\/pharma\/commercial\/social-media-voice-patient#.VbX9zTjUk84.linkedin"},{"key":"ref53","unstructured":"van RossumGPython reference manualCentrum Wiskunde & Informatica19952024-11-15https:\/\/ir.cwi.nl\/pub\/5008"},{"key":"ref54","unstructured":"jupyterlabGitHub2024-05-03https:\/\/github.com\/jupyterlab\/jupyterlab"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2020.00042"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1136\/bmjhci-2020-100262"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.08.011"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.2196\/25431"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ciact.2017.7977281"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1186\/s40163-020-00127-4"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33232-7_25"},{"key":"ref62","unstructured":"RehurekRgensim: python framework for vector space modellingMachine Learning Open Source Software2010972020-06-23https:\/\/mloss.org\/revision\/view\/546\/"},{"key":"ref63","first-page":"2825","volume":"12","author":"Pedregosa, F","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref64","author":"Angelov, D","journal-title":"arXiv"},{"key":"ref65","unstructured":"A guide on word embeddings in NLPTuring2024-05-03https:\/\/www.turing.com\/kb\/guide-on-word-embeddings-in-nlp"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/w14-3110"},{"key":"ref67","unstructured":"LoriaSTextBlob: simplified text processingTextBlob2021-11-15https:\/\/textblob.readthedocs.io\/en\/dev\/index.html"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v8i1.14550"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.51983\/ajcst-2019.8.S2.2037"},{"key":"ref70","unstructured":"SomaJComparing sentiment analysis toolsData Science for Journalism2021-06-30https:\/\/investigate.ai\/investigating-sentiment-analysis\/comparing-sentiment-analysis-tools\/"},{"key":"ref71","unstructured":"CarenNWord lists and sentiment analysisNeal Caren2019512021-07-01https:\/\/nealcaren.org\/lessons\/wordlists\/"},{"key":"ref72","unstructured":"Sketch Engine2024-11-25https:\/\/www.sketchengine.eu\/"},{"key":"ref73","unstructured":"enTenTen: corpus of the English webSketch Engine2018-02-27https:\/\/www.sketchengine.eu\/ententen-english-corpus\/"},{"key":"ref74","unstructured":"What is an N-Gram?MathWorks2024-05-03https:\/\/uk.mathworks.com\/discovery\/ngram.html"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1111\/jebm.12161"},{"key":"ref76","unstructured":"Cochrane library homepageCochrane Library2024-11-26https:\/\/www.cochranelibrary.com\/"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD012197.pub2"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD007380.pub4"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD011376.pub3"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD009221.pub2"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD010925.pub2"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD006788.pub3"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD007818.pub3"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD011335.pub2"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD009695.pub2"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD008661.pub2"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD007813.pub3"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD011005.pub2"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD009776.pub2"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD008508"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD006722.pub2"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD003218.pub2"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.2196\/26781"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.3389\/fsoc.2022.886498"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1111\/psj.12343"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.2196\/resprot.3433"},{"key":"ref97","doi-asserted-by":"crossref","unstructured":"DirksonAVerberneSKraaijWLexical normalization of user-generated medical textProceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task2019SMM4H@ACL 2019August 2, 2019Florence, Italy","DOI":"10.18653\/v1\/W19-3202"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.5195\/jmla.2017.108"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.socscimed.2019.112552"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.15265\/iy-2017-037"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.2966"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2024\/1\/e54321","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:40:57Z","timestamp":1782841257000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2024\/1\/e54321"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,11]]},"references-count":101,"URL":"https:\/\/doi.org\/10.2196\/54321","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.54321","asserted-by":"object"}]},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,11]]}}}