Computational psychotherapy research: scaling up the evaluation of patient–provider interactions
Open accessThe DOI matches its Crossref record; 67 of the 67 references it cites were found in a registry or an index.
Abstract
In psychotherapy, the patient-provider interaction contains the treatment's active ingredients. However, the technology for analyzing the content of this interaction has not fundamentally changed in decades, limiting both the scale and specificity of psychotherapy research. New methods are required to "scale up" to larger evaluation tasks and "drill down" into the raw linguistic data of patient-therapist interactions. In the current article, we demonstrate the utility of statistical text analysis models called topic models for discovering the underlying linguistic structure in psychotherapy. Topic models identify semantic themes (or topics) in a collection of documents (here, transcripts). We used topic models to summarize and visualize 1,553 psychotherapy and drug therapy (i.e., medication management) transcripts. Results showed that topic models identified clinically relevant content, including affective, relational, and intervention related topics. In addition, topic models learned to identify specific types of therapist statements associated with treatment-related codes (e.g., different treatment approaches, patient-therapist discussions about the therapeutic relationship). Visualizations of semantic similarity across sessions indicate that topic models identify content that discriminates between broad classes of therapy (e.g., cognitive-behavioral therapy vs. psychodynamic therapy). Finally, predictive modeling demonstrated that topic model-derived features can classify therapy type with a high degree of accuracy. Computational psychotherapy research has the potential to scale up the study of psychotherapy to thousands of sessions at a time. We conclude by discussing the implications of computational methods such as topic models for the future of psychotherapy research and practice.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“If a session were recorded, the labor intensiveness of human review would ensure most sessions would never be analyzed (8).”
From Key Considerations for Incorporating Conversational AI in Psychotherapy (2019) · cites this paper as [8]
In the citing paper
“Additionally, conversational AI is providing clinicians with feedback on their psychotherapy (8)”
From Key Considerations for Incorporating Conversational AI in Psychotherapy (2019) · cites this paper as [8]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“As is typical with large-scale psychotherapy clinical trials, there have already been published comments (Clark, 2013) and rejoinders (Leichsenring & Salzer, 2013) on possible explanations for the findings wherein Clark raised questions about the implementation of the CBT and Leichsenring reported…”
Background(2003) · Journal of Machine Learning Research · doi:10.5555/944919.944937 · Cited by 32,337
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2002) · Advances in Neural Information Processing Systems 14 · doi:10.7551/mitpress/1120.003.0082 · Cited by 12,223
Foundations of statistical natural language processing
Manning, C. D., & Schütze, H. (1999) · Cited by 9,816
Landauer, T. K., & Dumais, S. T. (1997) · Psychological Review · doi:10.1037/0033-295x.104.2.211 · Cited by 6,282
Griffiths, T. L., & Steyvers, M. (2004) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0307752101 · Cited by 6,049
The necessary and sufficient conditions of therapeutic personality change.
Rogers, C. R. (1957) · Journal of Consulting Psychology · doi:10.1037/h0045357 · Cited by 5,599
Bergin and Garfield's Handbook of Psychotherapy and Behavior Change
Lambert, M. J. (2003) · Cited by 3,383
Feature-rich part-of-speech tagging with a cyclic dependency network
Toutanova, K., Klein, D., Manning, C. D., & Singer, Y. (2003) · Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - NAACL '03 · doi:10.3115/1073445.1073478 · Cited by 2,844
Motivational Interviewing: Preparing People for Change, 2nd ed.
Miller, W., & Rollnick, S. (2003) · Journal For Healthcare Quality · doi:10.1097/01445442-200305000-00013 · Cited by 2,634
Research works printed but not linked: 1
- Wampold BE. The great psychotherapy debate: Models, methods, and findings. Erlbaum; Mahwah, NJ: 2001. [Google Scholar]
Cited by
Items 101–145 of 145
Automated Utterance Labeling of Conversations Using Natural Language Processing
Laricheva, M., Zhang, C., Liu, Y., Chen, G., Tracey, T. J. G., Young, R. A., & Carenini, G. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17114-7_23 · Cited by 2
Mylläri, S., Saarni, S. E., Joffe, G., Ritola, V., Stenberg, J., & Rosenström, T. H. (2025) · Psychotherapy Research · doi:10.1080/10503307.2025.2473921 · Cited by 3
“Topic modeling has shown potential in the psychotherapy context, where it has been used to extract meaningful information from face-to-face psychotherapy transcripts and iCBT task data (Atkins et al., 2012; Atzil-Slonim et al., 2021; Imel et al., 2015; Mylläri et al., 2022).”
Markin, R. D., Kivlighan, D. M., Marmarosh, C. L., Ge, S. Y. J., & Hewitt, P. L. (2025) · International Journal of Group Psychotherapy · doi:10.1080/00207284.2025.2456006 · Cited by 2
“For instance, Imel et al. (2015) trained topic models on the speech turns of patients and therapists in different therapy approaches and found that this linguistic information could be used to classify which form of therapy was used in a particular session.”
Technology of text analysis in the big data era: Application of the topic model
Ben, C., Xia, M., Zhihong, R., Xiubin, L., Xu, S. Y., Lai, L., Wang, Q., & Guangrong, J. (2018) · Advances in Psychological Science · doi:10.3724/sp.j.1042.2018.00770 · Cited by 2
Psychotherapy is Not One Thing: Simultaneous Modeling of Different Therapeutic Approaches
Mehta, M., Caperton, D. D., Axford, K., Weitzman, L. M., Atkins, D. C., Srikumar, V., & Imel, Z. E. (2022) · Workshop on Computational Linguistics and Clinical Psychology (CLPsych) · doi:10.18653/v1/2022.clpsych-1.5 · Cited by 2
“In this paper, we study an application of Natural Language Processing (NLP) to mental health, and focus on therapists’ approach to psychotherapy (Imel et al., 2015).”
MethodSelf-citationRubel, J. A., Lutz, W., & Bickman, L. (2024) · Administration and Policy in Mental Health and Mental Health Services Research · doi:10.1007/s10488-024-01392-0 · Cited by 2
“The last two papers of this special issue focus on the potential of technology for automated coding, an advantage that has been envisioned a couple of years ago (e.g., Imel et al., 2015) and which has been used in more and more appli - cations recently (e.g., Eberhardt et al., 2024 ).”
Markin, R. D., Kivlighan, D. M., Marmarosh, C. L., Ge, S. Y. J., Kealy, D., & Hewitt, P. L. (2025) · Psychotherapy Research · doi:10.1080/10503307.2025.2506653 · Cited by 1
“For instance, Imel et al. (2015) trained topic models on the speech turns of patients and therapists in different therapy approaches and found that this linguistic information could be used to classify which form of therapy was used in a particular session.”
Liccione, D., & Siciliano, L. (2025) · Psychotherapy Research · doi:10.1080/10503307.2025.2500504 · Cited by 2
“In our model, each conversational turn was treated as a separate document (Atkins et al., 2012; Imel et al., 2015).”
InfluentialGrazioli, S., Ocera, A., Notaristefano, I., Piron, R., Fanfoni, M., Terrazzan, L., Ruggiero, G. M., Sassaroli, S., & Caselli, G. (2025) · Psychological Reports · doi:10.1177/00332941251409157 · Cited by 1
Evaluating AI-based Mental Health Interventions
Sharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749733 · Cited by 1
Solution-Focused Therapy through the Lens of Discourse Analysis
Zatloukal, L., & Wiesner, A. (2021) · Journal of Constructivist Psychology · doi:10.1080/10720537.2021.1955780 · Cited by 2
“Another promising approach is the application of machine-learning procedures that enable language analysis of conversations (Imel et al., 2015).”
Pereira, P. E. C. (2022) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.47.2022.tde-07122022-082556 · Cited by 1
Chaoua, I., Consoli, S., Härmä, A., Helaoui, R., & Recupero, D. R. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-12738-1_5 · Cited by 1
Thomas, L. (2020) · Digital Repository Service (Northeastern University) · doi:10.17760/d20403637 · Cited by 1
Liu, Y., Laricheva, M., Zhang, C., Boutet, P., Chen, G., Tracey, T. J. G., Carenini, G., & Young, R. A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17114-7_21
Luo, W., Li, R., Guo, Z., Jia, S., Sun, Q., & Ren, Z. (2025) · Psychology and Psychotherapy Theory Research and Practice · doi:10.1111/papt.12604
“ML is transforming psychotherapeutic data processing in clinical psychology and psychiatry research (Imel et al., 2015).”
Recursive Frame Analysis as a Method of Psychotherapy Change Process Research
Zatloukal, L., Jurníčková, P., & Szczepkowski, J. (2025) · Contemporary Family Therapy · doi:10.1007/s10591-025-09754-y
“In the future, it may be possible to observe discursive changes between acts using AI-based automated systems (Imel et al., 2015; Smink et al., 2019).”
Bruno, S., Mastropietro, I., Todini, L., & Velotti, P. (2025) · International Journal of Group Psychotherapy · doi:10.1080/00207284.2025.2538019
“This line of study looks at the linguistic exchanges that characterize the therapeutic work (Imel et al., 2015) as a new direct observation of the therapeutic process (Smink et al., 2019).”
Cunningham, P. B., Gilmore, J., Naar, S., Preston, S. D., Eubanks, C. F., Hubig, N., McClendon, J. L., Ghosh, S., & Ryan-Pettes, S. R. (2025) · Gezinstherapie Wereldwijd · doi:10.1007/s12440-025-00258-7
“…in de ontwikkeling van methoden om psychotherapeuti-sche processen te onderzoeken, is een gevolg van dat het meten van interpersoon-lijke interacties vrijwel altijd complex is en dan gaat het met name over het bidi-rectionele en synergetische karakter van dergelijke interacties (Imel et al. 2015).”
Zhang, Z., Fitzgerald, K. D., Chang, S., Monk, C. S., Phan, K. L., & Iturra-Mena, A. M. (2026) · Research Square · doi:10.21203/rs.3.rs-9682555/v1
“In psychotherapy, linguistic markers have been used to quantify therapeutic processes and patient engagement within sessions 21,22 .”
Elsayed, M., Belisario, K. L., Blakely, A., Syan, S. K., Levitt, E., Garber, M. L., MacKillop, E., Balodis, I. M., Sweet, L. H., & MacKillop, J. M. (2026) · Alcohol and Alcoholism · doi:10.1093/alcalc/agag033
“Prior work in this domain has used NLP to evaluate MI fidelity ( Atkins et al. 2014), assess therapist–client interactions ( Imel et al. 2014), classify behavioural codes in MI ( Tavabi et al. 2021), and compare automated coding strategies ( Tanana et al. 2016).”
Urmanche, A. A., & Eubanks, C. F. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-29009-1.00056-1
Lalk, C., Steinbrenner, T., & Rubel, J. (2026) · Die Psychotherapie · doi:10.1007/s00278-026-00860-2
Natural Language Processing and Psychological Sciences
Kovač, N., Ratković, K., Marovac, U., Farahani, H., Blagojević, M., & Watson, P. (2026) · Springer eBooks · doi:10.1007/978-3-032-18312-5_19
Vancappel, A., Dufour, J., Angeneau, L., Brennstuhl, M., El‐Hage, W., Gandolphe, M., Hiton, S., Khalfla, S., Nandrino, J., Raffard, S., et al. (2026) · Annales Médico-psychologiques revue psychiatrique · doi:10.1016/j.amp.2026.06.022
Supplementary Material for Evaluating AI-Based Mental Health Interventions
Sharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749737
Human–AI Collaboration to Empower People Seeking Support
Sharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749732
(2026) · ACM eBooks · doi:10.1145/3749728.3749738
(2026) · ACM eBooks · doi:10.1145/3749728.3749739
Supplementary Materials for Human–AI Collaboration to Empower People Providing Support
Sharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749735
Human–AI Collaboration to Empower People Providing Support
Sharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749731
Sharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749730
(2026) · ACM eBooks · doi:10.1145/3749728.3749729
Supplementary Materials for Human–AI Collaboration to Empower People Seeking Support
Sharma, A. (2026) · ACM eBooks · doi:10.1145/3749728.3749736
(2026) · ACM eBooks · doi:10.1145/3749728.3749734
Haber, Y., Refoua, E., Yirmiya, K., Rafaeli, E., Yinon, D., Atzil–Slonim, D., Fonagy, P., Meinlschmidt, G., Hadar‐Shoval, D., Simon, T., et al. (2026) · doi:10.2196/preprints.110192
Förderung persönlicher Kompetenzen in der psychotherapeutischen Aus- und Weiterbildung
Rief, W., Schramm, E., & Strauss, B. M. (2026) · Elsevier eBooks · doi:10.1016/b978-3-437-21352-6.00002-x
The AI-Enhanced Assistance: Redefining Clinical Competence in Psychology Education
Rajput, S., & Mehta, R. B. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-9109-0.ch008
Segmentation and Classification in Therapeutic Transcripts with Fine-Tuned BERT and SBERT
de Almeida, C. P., Bernardino, H. S., de Souza, J. F., & Martins, L. F. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-39904-5_39
Metadata
- Authors
- Imel, Z. E., Steyvers, M., & Atkins, D. C.
- Affiliations
- University of Utah (US)
- University of California, Irvine (US)
- University of Washington (US)
- Corresponding author
- Imel, Zac E.
- Venue
- Psychotherapy
- Published
- 2015
- Volume
- 52
- Issue
- 1
- Pages
- 19-30
- ISSN
- 0033-3204 (ISSN-L)
- 1939-1536
- PMC
- PMC4245387
- OpenAlex
- W2314271279
- Cited by
- 146
- References
- 65
- Citations by year
- 2026: 24 · 2025: 14 · 2024: 9 · 2023: 12 · 2022: 16 · 2021: 12 · 2020: 16 · 2019: 11 · 2018: 6 · 2017: 6 · 2016: 10 · 2015: 9
- FWCI
- 53.99
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- Psychotherapy (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- eScholarship (California Digital Library) (submittedVersion)
- Funders
- National Institutes of Health (R34/DA034860)
- National Institute on Alcohol Abuse and Alcoholism (R01/AA018673)
- University of Utah
- Topics
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Social Sciences › Psychology › Clinical Psychology › Psychotherapy Techniques and Applications
- Social Sciences › Psychology › Social Psychology › Mental Health via Writing
- Keywords
- topic modeling, patient-therapist interaction, psychotherapy transcripts, cognitive behavioral therapy, psychodynamic psychotherapy, therapeutic relationship, medication management, semantic similarity
- MeSH terms
- Humans, Linguistics, Professional-Patient Relations, Psychotherapy, Research, Semantics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.