{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:47:22Z","timestamp":1787024842577,"version":"build-2736575974"},"reference-count":36,"publisher":"JMIR Publications Inc.","issue":"11","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>Text mining methods such as topic modeling can offer valuable information on how and to whom internet-delivered cognitive behavioral therapies (iCBT) work. Although iCBT treatments provide convenient data for topic modeling, it has rarely been used in this context.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Our aims were to apply topic modeling to written assignment texts from iCBT for generalized anxiety disorder and explore the resulting topics\u2019 associations with treatment response. As predetermining the number of topics presents a considerable challenge in topic modeling, we also aimed to explore a novel method for topic number selection.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We defined 2 latent Dirichlet allocation (LDA) topic models using a novel data-driven and a more commonly used interpretability-based topic number selection approaches. We used multilevel models to associate the topics with continuous-valued treatment response, defined as the rate of per-session change in GAD-7 sum scores throughout the treatment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our analyses included 1686 patients. We observed 2 topics that were associated with better than average treatment response: \u201cwell-being of family, pets, and loved ones\u201d from the data-driven LDA model (B=\u20130.10 SD\/session\/\u2206topic; 95% CI \u2013016 to \u20130.03) and \u201cchildren, family issues\u201d from the interpretability-based model (B=\u20130.18 SD\/session\/\u2206topic; 95% CI \u20130.31 to \u20130.05). Two topics were associated with worse treatment response: \u201cmonitoring of thoughts and worries\u201d from the data-driven model (B=0.06 SD\/session\/\u2206topic; 95% CI 0.01 to 0.11) and \u201cinternet therapy\u201d from the interpretability-based model (B=0.27 SD\/session\/\u2206topic; 95% CI 0.07 to 0.46).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The 2 LDA models were different in terms of their interpretability and broadness of topics but both contained topics that were associated with treatment response in an interpretable manner. Our work demonstrates that topic modeling is well suited for iCBT research and has potential to expose clinically relevant information in vast text data.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/38911","type":"journal-article","created":{"date-parts":[[2022,11,9]],"date-time":"2022-11-09T10:45:16Z","timestamp":1667990716000},"page":"e38911","source":"Crossref","is-referenced-by-count":11,"title":["Text Topics and Treatment Response in Internet-Delivered Cognitive Behavioral Therapy for Generalized Anxiety Disorder: Text Mining Study"],"prefix":"10.2196","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4059-9268","authenticated-orcid":false,"given":"Sanna","family":"Myll\u00e4ri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3555-9958","authenticated-orcid":false,"given":"Suoma Eeva","family":"Saarni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9065-4347","authenticated-orcid":false,"given":"Ville","family":"Ritola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0782-6812","authenticated-orcid":false,"given":"Grigori","family":"Joffe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1327-7757","authenticated-orcid":false,"given":"Jan-Henry","family":"Stenberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8341-0560","authenticated-orcid":false,"given":"Ole Andr\u00e9","family":"Solbakken","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3713-653X","authenticated-orcid":false,"given":"Nikolai Olavi","family":"Czajkowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8277-3776","authenticated-orcid":false,"given":"Tom","family":"Rosenstr\u00f6m","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2022,11,9]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/da.23115"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2196\/29384"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.janxdis.2018.01.001"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2196\/18100"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1037\/cou0000213"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/16506073.2014.952773"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2019.01186"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2014.01.005"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2010.04.011"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/0261927X09351676"},{"issue":"1","key":"ref11","first-page":"30","volume":"3","author":"Blei, D","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1037\/a0029607"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1037\/pst0000362"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1037\/a0036841"},{"key":"ref15","author":"Wasserman, L","year":"2006","journal-title":"All of Nonparametric Statistics"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/10503307.2017.1395922"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-clinpsy-050718-095424"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2016.2601123"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2018.1558063"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1001\/archinte.166.10.1092"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/10731911211062500"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/1073191120976863"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.genhosppsych.2015.11.005"},{"key":"ref24","unstructured":"PerryPOcorpus: Text Corpus Analysis20212021-09-01https:\/\/CRAN.R-project.org\/package=corpus"},{"key":"ref25","author":"Silge, J","year":"2017","journal-title":"Text Mining With R: A Tidy Approach"},{"key":"ref26","unstructured":"JonesTDoaneWAttbomMtextmineR: Functions for Text Mining and Topic Modeling20212021-09-01https:\/\/CRAN.R-project.org\/package=textmineR"},{"key":"ref27","author":"Gelman, A","year":"2007","journal-title":"Data Analysis Using Regression and Multilevel\/Hierarchical Models"},{"key":"ref28","unstructured":"R Core TeamR: A Language and Environment for Statistical Computing20222021-09-01ViennaR Foundation for Statistical Computinghttps:\/\/www.R-project.org\/"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2015.01564"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.128.4.638"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.107.2.156"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1037\/a0014333"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1186\/s12888-018-1736-5"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1037\/h0101777"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.beth.2016.05.002"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.2196\/15732"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2022\/11\/e38911","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:35:28Z","timestamp":1782840928000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2022\/11\/e38911"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,9]]},"references-count":36,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.2196\/38911","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,9]]}}}