Large-scale Analysis of Counseling Conversations: An Application of Natural Language Processing to Mental Health
Open accessThe DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
Mental illness is one of the most pressing public health issues of our time. While counseling and psychotherapy can be effective treatments, our knowledge about how to conduct successful counseling conversations has been limited due to lack of large-scale data with labeled outcomes of the conversations. In this paper, we present a large-scale, quantitative study on the discourse of text-message-based counseling conversations. We develop a set of novel computational discourse analysis methods to measure how various linguistic aspects of conversations are correlated with conversation outcomes. Applying techniques such as sequence-based conversation models, language model comparisons, message clustering, and psycholinguistics-inspired word frequency analyses, we discover actionable conversation strategies that are associated with better conversation outcomes.
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
Figures










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?
In the citing paper
“For example, innovations in computer science (e.g., natural language processing and machine learning) are being used to assess language patterns of successful crisis interventions in text-based mental health conversations (18, 35).”
From Key Considerations for Incorporating Conversational AI in Psychotherapy (2019) · cites this paper as [18]
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
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 1×
“We also used distributed word embeddings (e.g., (Mikolov et al., 2013)) instead of TF-IDF vectors but found the latter to produce better clusters.”
MethodVADER: a parsimonious rule-based model for sentiment analysis of social media text
Hutto, C., & Gilbert, E. (2014) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v8i1.14550 · Cited by 6,087
The Psychological Meaning of Words: LIWC and Computerized Text Analysis Methods
Tausczik, Y. R., & Pennebaker, J. W. (2010) · Journal of Language and Social Psychology · doi:10.1177/0261927x09351676 · Cited by 5,774 · cited 1×
“Texters start explaining their issue largely in terms of the past and present but over time talk more about the future (see Figure 9A; each plot shows the relative amount of words in the LIWC past, present, and future categories (Tausczik and Pennebaker, 2010)).”
Psychological Aspects of Natural Language Use: Our Words, Our Selves
Pennebaker, J. W., Mehl, M. R., & Niederhoffer, K. G. (2003) · Annual Review of Psychology · doi:10.1146/annurev.psych.54.101601.145041 · Cited by 2,624
Concreteness ratings for 40 thousand generally known English word lemmas
Brysbaert, M., Warriner, A. B., & Kuperman, V. (2014) · Behavior Research Methods · doi:10.3758/s13428-013-0403-5 · Cited by 1,821
Lenggenhager, J. (1947) · PubMed · Cited by 1,772
Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
Stolcke, A., Ries, K., Coccaro, N., Shriberg, E., Bates, R., Jurafsky, D., Taylor, P., Martin, R., Ess-Dykema, C. V., & Meteer, M. (2000) · Computational Linguistics · doi:10.1162/089120100561737 · Cited by 1,108
Therapeutic Discourse: Psychotherapy as Conversation
Tannen, D., Labov, W., & Fanshel, D. (1981) · Language · doi:10.2307/413709 · Cited by 938
Pyszczynski, T., & Greenberg, J. (1987) · Psychological Bulletin · doi:10.1037/0033-2909.102.1.122 · Cited by 825 · cited 4×
“Figure 9B shows that a smaller amount of self-focus is associated with more successful conversations (providing support for the self-focus model of depression (Pyszczynski and Greenberg, 1987)).”
BackgroundResultInfluentialLinguistic Style Matching in Social Interaction
Niederhoffer, K. G., & Pennebaker, J. W. (2002) · Journal of Language and Social Psychology · doi:10.1177/026192702237953 · Cited by 562
Research works printed but not linked: 5
- Levitt Dana Heller, 2005, The Journal of Humanistic Counseling, Education and Development, 44(1).
- Niederhoffer Kate G., 2002, Journal of Language and Social Psychology, 21(4).
- Pyszczynski Tom, 1987, Journal of Personality and Social Psychology, 52(5).
- Ren Shiquan, 2010, Journal of Applied Statistics, 37(9).
- Tausczik Yla R., 2010, Journal of Language and Social Psychology, 29(1).
Cited by
Items 101–200 of 319
Woo, K., Song, J., Adams, V., Block, L. J., Currie, L. M., Shang, J., & Topaz, M. (2021) · International Wound Journal · doi:10.1111/iwj.13623 · Cited by 25
PAIR: Prompt-Aware margIn Ranking for Counselor Reflection Scoring in Motivational Interviewing
Min, D. J., Pérez‐Rosas, V., Resnicow, K., & Mihalcea, R. F. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.11 · Cited by 29
“We believe that developing an Natural Language Processing (NLP) model capable of assessing the quality of verbal behavior observed in counselor language can improve the quality and efficiency of Motivational Interviewing (MI) training by allowing counselors to practice in real-time their reflective listening skills, a…”
Developing a Social Support Framework: Understanding the Reciprocity in Human-Chatbot Relationship
Pan, S., & de Graaf, M. M. A. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713503 · Cited by 48
“Natural language processing models have the potential to generate high-quality support dialogues [3].”
Cura: Curation at Social Media Scale
He, W., Gordon, M., Popowski, L., & Bernstein, M. S. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3610186 · Cited by 26
“Researchers have already developed models for forecasting conversational events—what a piece of content might bring up, whether it will be perceived as helpful [3] or lead to derailment [14, 66], steps toward the proactive, discerning application of curation that we envision.”
BackgroundShameli, A., Althoff, T., Saberi, A., & Leskovec, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.07437 · Cited by 25
“Furthermore, researchers have studied social interactions to better understand how people could be most supportive of others [1, 2].”
BackgroundSelf-citationMentalChat16K: A Benchmark Dataset for Conversational Mental Health Assistance
Xu, J., Wei, T., Hou, B., Orzechowski, P., Yang, S., Jin, R., Paulbeck, R., Wagenaar, J., Demiris, G., & Shen, L. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3737393 · Cited by 26
Predicting Depression in Screening Interviews from Latent Categorization of Interview Prompts
Rinaldi, A., Tree, J. E. F., & Chaturvedi, S. (2020) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2020.acl-main.2 · Cited by 32
“For example, exploring correlations between counselor-patient interaction dynamics and counseling outcomes (Althoff et al., 2016); studying linguistic development of mental healthcare counsellors (Zhang et al., 2019); identifying differences in how people disclose mental illnesses across gender and…”
BackgroundDeva, R., Ramani, D., Divate, T., Jalota, S., & Ismail, A. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713362 · Cited by 45
“The use of LLM-based chatbots for healthcare started with a lot of attention on aiding conversations around mental health [9, 89, 95, 106], virtual caregiving [64, 81, 102] and personalized health information delivery [8, 37, 93].”
Measuring Linguistic Synchrony in Psychotherapy
Shapira, N., Atzil–Slonim, D., Tuval‐Mashiach, R., & Shapira, O. (2022) · Workshop on Computational Linguistics and Clinical Psychology (CLPsych) · doi:10.18653/v1/2022.clpsych-1.14 · Cited by 27
Learning to Become a Volunteer Counselor: Lessons from a Peer-to-Peer Mental Health Community
Yao, Z. Q., Zhu, H., & Kraut, R. E. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3555200 · Cited by 28
“Prior work found that successful counselors tend to adapt their linguistic style to those of their clients and monitor the progress of the conversation [2]; concrete, positive and supportive messages from volunteers are associated with better outcomes for the clients [12].”
BackgroundLeveraging Novel Technologies and Artificial Intelligence to Advance Practice-Oriented Research
Atzil–Slonim, D., Penedo, J. M. G., & Lutz, W. (2023) · Administration and Policy in Mental Health and Mental Health Services Research · doi:10.1007/s10488-023-01309-3 · Cited by 29
“Nevertheless, evidence suggests that these diagnosis-derived treatment recommendations are prone to errors and reliability issues (e.g., Deacon, 2013 ). analyzed and the results showed that specific conversation strategies were associated with better session outcomes (Althoff et al., 2016 ).”
Saha, T., Chopra, S., Saha, S., Bhattacharyya, P., & Kumar, P. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533924 · Cited by 28
Positivity Bias in Customer Satisfaction Ratings
Park, K., Cha, M., & Rhim, E. (2018) · Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW '18 · doi:10.1145/3184558.3186579 · Cited by 19
“asks of various domains, including live chat systems [19] and call centers [25]. In a recent study, n-grams have been used in predicting the success of counseling sessions for mental illness patients [2]. A regression model was constructed with L1 regularization, and unigram and bigram features were found to be the mo…”
BackgroundMethodInfluentialAI Chatbots for Mental Health Self-Management: Lived Experience–Centered Qualitative Study
Yoo, D. W., Shi, J. M., Rodriguez, V. J., & Saha, K. (2026) · JMIR Mental Health · doi:10.2196/78288 · Cited by 40
Understanding Client Reactions in Online Mental Health Counseling
Li, A., Ma, L., Mei, Y., He, H., Zhang, S., Qiu, H., & Lan, Z. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.577 · Cited by 65
Scoping review on natural language processing applications in counselling and psychotherapy
Laricheva, M., Liu, Y., Shi, E., & Wu, A. D. (2024) · British Journal of Psychology · doi:10.1111/bjop.12721 · Cited by 26
“For example, NLP has been used to examine the association of language patterns with conversational outcomes (Burkhardt et al., 2021) or treatment outcomes assessed by psychological scales (Althoff et al., 2016).”
InfluentialBarroilhet, S. A., Pellegrini, A. M., McCoy, T. H., & Perlis, R. H. (2019) · Psychological Medicine · doi:10.1017/s0033291719002320 · Cited by 24
“, 2016) and mental health research (Althoff et al., 2016; Can et al., 2016; McCoy et al., 2016; Birnie et al., 2018; McCoy et al., 2018; Afshar et al., 2019).”
Roy, K., Gaur, M., Soltani, M., Rawte, V., Kalyan, A., & Sheth, A. (2023) · Frontiers in Big Data · doi:10.3389/fdata.2022.1056728 · Cited by 18
Saha, K., Jain, Y., Liu, C., Kaliappan, S., & Karkar, R. (2026) · ACM Transactions on Computing for Healthcare · doi:10.1145/3709366 · Cited by 53
What Makes Digital Support Effective? How Therapeutic Skills Affect Clinical Well-Being
Yang, W., Fang, A., Shah, R. S., Mathur, Y., Yang, D., Zhu, H., & Kraut, R. E. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3641029 · Cited by 25
Towards augmenting crisis counselor training by improving message retrieval
Demasi, O., Hearst, M. A., & Recht, B. (2019) · Proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology · doi:10.18653/v1/w19-3001 · Cited by 18
“Such datasets have been explored in prior work to understand effective hotline conversations (Althoff et al., 2016).”
BackgroundInfluentialA Computerized Text and Cluster Analysis Approach to Psychotherapy Talk
Tay, D. (2020) · Language and Psychoanalysis · doi:10.7565/landp.v9i1.1701 · Cited by 19
“…although general psychotherapy research has a rich and continuing tradition of using computerized and/or various forms of quantitative analysis (Althoff, Clark & Leskovec, 2016; He, Veldkamp, Glas et al., 2017; Mergenthaler & Bucci, 1999; Watson & Laffal, 1963), work oriented towards the…”
BackgroundHEAL: A Knowledge Graph for Distress Management Conversations
Welivita, A., & Pu, P. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i10.21398 · Cited by 28
“Real counseling conversation datasets used to conduct recent research (Althoff, Clark, and Leskovec 2016; Zhang and Danescu-Niculescu-Mizil 2020) are not directly accessible due to ethical reasons.”
MethodKanaparthi, S. D., Patle, A., & Naik, K. J. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15316-x · Cited by 17
Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches, and Future Directions
Jia, Q., Liu, Y., Ren, S., & Zhu, K. Q. (2023) · ACM Computing Surveys · doi:10.1145/3622933 · Cited by 30
Névéol, A., & Zweigenbaum, P. (2017) · Yearbook of Medical Informatics · doi:10.15265/iy-2017-027 · Cited by 26
“, [5] analyzed doctor-patient counseling interactions in text messages through a variety of techniques and evidence actionable conversation strategies that are liable to improve counseling practice.”
BackgroundInfluentialDetecting Institutional Dialog Acts in Police Traffic Stops
Prabhakaran, V., Griffiths, C. M., Su, H., Verma, P., Morgan, N. H., Eberhardt, J. L., & Jurafsky, D. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00031 · Cited by 24
“Prabhakaran et al. (2012) and Prabhakaran et al. (2014) employ dialog act analysis to study correlates of gender and power in work emails, while Althoff et al. (2016) studied structural aspects of successful counseling conversations, and Yang et al. (2013) and Chandrasekaran et al. (2017)…”
MethodAssessing Users' Mental Status from their Journaling Behavior through Chatbots
Kawasaki, M., Yamashita, N., Lee, Y., & Nohara, K. (2020) · ACM International Conference on Intelligent Virtual Agents (IVA) · doi:10.1145/3383652.3423870 · Cited by 22
“Research has shown that people who are deeply distressed prefer confiding their anxieties to chat-bots rather than to humans [14, 22] because they fear being rejected or judged [1].”
BackgroundSalmi, S., Mérelle, S. Y. M., Gilissen, R., & Brinkman, W. (2021) · Journal of Medical Internet Research · doi:10.2196/21690 · Cited by 18
“In this respect, Althoff et al [15] compared the chat conversations of more and less successful counselors with natural language processing techniques to discover the quality differences, defining actionable strategies to improve conversation quality.”
BackgroundUsing BERT for Qualitative Content Analysis in Psychosocial Online Counseling
Grandeit, P., Haberkern, C., Lang, M., Albrecht, J., & Lehmann, R. (2020) · Workshop on Natural Language Processing and Computational Social Science (NLP+CSS) · doi:10.18653/v1/2020.nlpcss-1.2 · Cited by 28
“Althoff et al. (2016) defined different models to measure general conversation strategies like adaptability, dealing with ambiguity, creativity, making progress or change in perspective and illustrated their applicability on a corpus of data from SMS counseling.”
BackgroundIndirect Identification of Perinatal Psychosocial Risks From Natural Language
Allen, K., Davis, A. L., & Krishnamurti, T. (2021) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2021.3079282 · Cited by 18
“In prior work, LIWC in particular has been effectively used in predicting mental health status from language [17], [20], [22], [24], [62], [63].”
MethodA Systematic Review of Machine Learning for Assessment and Feedback of Treatment Fidelity
Ahmadi, A., Noetel, M., Schellekens, M., Parker, P. D., Antczak, D., Beauchamp, M. R., Dicke, T., Diezmann, C. M., Maeder, A., Ntoumanis, N., et al. (2021) · Psychosocial Intervention · doi:10.5093/pi2021a4 · Cited by 20
“Counselling, (counsellors), (Althoff et al., 2016; Flemotomos et al., 2018; Gallo et al., 2015; Gaut et al., 2017; Goldberg et al., 2020; Malandrakis & Narayanan, 2015; Mieskes & Stiegelmayr, 2018; Nitti et al., 2010; Salvatore et al., 2012; Velasquez & Montiel, 2018) Medical care, (nurses) (Lacson & Barzilay, 2005)”
BackgroundMiner, A. S., Fleming, S. L., Haque, A., Fries, J., Althoff, T., Wilfley, D. E., Agras, W. S., Milstein, A. S., Hancock, J. T., Asch, S. M., et al. (2022) · npj Mental Health Research · doi:10.1038/s44184-022-00020-9 · Cited by 28
““ it sounds like ” , “ that seems ” , “ heard you correctly ” , “ you sound ” , “ let me make sure ” Therapist Tactics Althoff et al. 30 “ Demonstrating understanding ” phrases (active listening) “ I hear you ” , “ I see ” , “ I understand ” Therapist Tactics This study “ Hedging ” phrases (active…”
BackgroundMethodInfluentialSelf-citationEagle, T., Mehrotra, A., Sharma, A., Zuniga, A., & Whittaker, S. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3555155 · Cited by 28
“Machine learning has also been used to identify effective practices from therapeutic conversations [2,110,120,130].”
A Critical Reflection and Forward Perspective on Empathy and Natural Language Processing
Lahnala, A., WELCH, C. A., Jurgens, D., & Flek, L. (2022) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2022.findings-emnlp.157 · Cited by 44
“…al., 2016, 2017, 2018, 2019; Wu et al., 2021b; Shen et al., 2022), assistive writing systems for peer-to-peer mental health support (Sharma et al., 2021, 2022), and other counseling conversations (Althoff et al., 2016; Zhang and Danescu-Niculescu-Mizil, 2020; Zhang et al., 2020; Sun et al., 2021).”
Camp, N. P., Voigt, R., Hamedani, M. G., Jurafsky, D., & Eberhardt, J. L. (2024) · PNAS Nexus · doi:10.1093/pnasnexus/pgae359 · Cited by 26
“Computational analyses of language have already been used to understand disparities and develop actionable insights in other domains as varied as counseling conversations (26), medical patient survey responses (27), and judicial decisions (28).”
Population-Scale Pervasive Health
Althoff, T. (2017) · IEEE Pervasive Computing · doi:10.1109/mprv.2017.3971134 · Cited by 16
Self-citationPredicting user emotional tone in mental disorder online communities
Silveira, B., Assumpção, H. S., Murai, F., & da Silva, A. P. C. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2021.07.014 · Cited by 20
“In this context, the authors in [10] analyze conversations that took place via SMS of individuals related to the Crisis Trends organization 5.”
BackgroundMinding the AI: Ethical Challenges and Practice for AI Mental Health Care Tools
Martinez‐Martin, N. (2021) · Advances in neuroethics · doi:10.1007/978-3-030-74188-4_8 · Cited by 31
DHF-Net: A hierarchical feature interactive fusion network for dialogue emotion recognition
Gan, C., Yang, Y., Zhu, Q., Jain, D. K., & Štruc, V. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118525 · Cited by 17
Metrics for Peer Counseling: Triangulating Success Outcomes for Online Therapy Platforms
Wang, T., Shah, H. K., Shah, R. S., Wang, Y.-C., Kraut, R. E., & Yang, D. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581372 · Cited by 24
“In prior work, eighty percent of conversations in [3] and two-thirds of the samples in [20] are discarded because users did not provide any feedback.”
BackgroundMethodInfluentialCharacterizing Delusional Spirals through Human-LLM Chat Logs
Moore, J., Mehta, A., Agnew, W., Anthis, J. R., Louie, R., Mai, Y., Yin, P., Cheng, M., Paech, S. J., Klyman, K., et al. (2026) · Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3805689.3806443 · Cited by 15
“Researchers from a variety of fields have developed computational methods to classify text for indicators of mental health symptoms, conditions, and disclosures [4, 11, 13, 56, 77, 94].”
A Scoping Review of Arabic Natural Language Processing for Mental Health
Alasmari, A. (2025) · Healthcare · doi:10.3390/healthcare13090963 · Cited by 15
Antoniou, M., Estival, D., Lam‐Cassettari, C., Li, W., Dwyer, A., & Neto, A. D. A. (2022) · JMIR Formative Research · doi:10.2196/33036 · Cited by 17
“single-item self-rating of mental health, “How would you rate your mental health now?” (adapted from the study by Althoff et al [58]) on a 5-point scale ranging from poor to excellent.”
BackgroundMishra, K., Priya, P., & Ekbal, A. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i12.26685 · Cited by 17
Modeling Therapeutic Alliance in the Age of Telepsychiatry
Ryu, J., Banthin, D., & Gu, X. (2020) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2020.10.001 · Cited by 16
On the hidden treasure of dialog in video question answering
Engin, D., Schnitzler, F., Duong, N. Q. K., & Avrithis, Y. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00207 · Cited by 15
“We train the HMM on the dialog sources of our video QA training set; otherwise, we use Sentence-BERT and BART as used/trained by [4].”
BackgroundGogoulou, E., Boman, M., Abdesslem, F. B., Isacsson, N. H., Kaldo, V., & Sahlgren, M. (2021) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2021.eacl-main.46 · Cited by 15
“Althoff et al. (2016) suggest that more references to the future, references to other individuals, and positive conversation perspective are all positively related to the success of counseling conversations.”
BackgroundResultInfluentialReal-World Case Studies: Transforming Mental Healthcare With Natural Language Processing
Rani, P., Yadav, S. P., Singh, P. N., & Almusawi, M. (2025) · IGI Global eBooks · doi:10.4018/979-8-3693-4203-9.ch016 · Cited by 17
Do Twitter users change their behavior after exposure to misinformation? An in-depth analysis
Wang, Y., Han, R. Y., Lehman, T. S., Lv, Q., & Mishra, S. (2022) · Social Network Analysis and Mining · doi:10.1007/s13278-022-00992-8 · Cited by 15
“Similar to prior work (Hessel et al 2016; Althoff et al 2016), we adopted the Jensen-Shannon Divergence (Fuglede and Topsoe 2004) to measure the unigram difference (hourly and monthly) in tweets as the language distance.”
MethodSmink, W. A. C., Sools, A. M., van der Zwaan, J. M., Wiegersma, S., Veldkamp, B. P., & Westerhof, G. J. (2019) · PLoS ONE · doi:10.1371/journal.pone.0225703 · Cited by 18
“For example, a comprehensive search string (‘regular expression’; [64, 65]) was used to detect whether an utterance contains a check question, suicide ideation, appreciation or surprise [66].”
MethodHarnessing the Web for Population-Scale Physiological Sensing: A Case Study of Sleep and PerformancePreprint
Althoff, T., Horvitz, E., White, R. W., & Zeitzer, J. M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1701.07083 · Cited by 16
“Large-scale interaction data have been used to gain insights into human behavior in the areas of mood rhythms [23], diet [45], conversation strategies [5], social networks and mobile games encouraging health behaviors [7, 8], and health and disease-related search behaviors [36, 46].”
BackgroundSelf-citationKöckritz, J., İlgen, B., Cohrdes, C., & Hattab, G. (2025) · Scientific Reports · doi:10.1038/s41598-025-18413-z · Cited by 14
“For example, NLP techniques have been used to analyze text-based communication in crisis support services to identify linguistic cues that indicate heightened emotional distress 45 , and to assess communication patterns in counseling 46 , helping to refine intervention strategies.”
Beyond English: Considering Language and Culture in Psychological Text Analysis
Kučera, D., & Mehl, M. R. (2022) · Frontiers in Psychology · doi:10.3389/fpsyg.2022.819543 · Cited by 20
Robo : A Counselor Chatbot for Opioid Addicted Patients
Moghadasi, M. N., Zhuang, Y., & Abu-gellban, H. (2020) · International Symposium on Signal Processing Systems (SSPS) · doi:10.1145/3421515.3421525 · Cited by 16
“The study [2] has done an analysis on various linguistic aspects of conversation and their correlation with conversation outcome.”
BackgroundDigital Art Therapy with Gen AI: Mind Palette
Yoo, D., Kim, D., & Lopes, E. (2023) · International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW) · doi:10.1109/aciiw59127.2023.10388174 · Cited by 13
“Also, Gener-ative AI can give sophisticated dialogue that can simulate a therapeutic conversation style with empathic support [10] and provide ambiguous situations and conversations [11], which are important in conventional art therapy with human therapists and counseling conversation.”
BackgroundAugust, T., Lo, K., Smith, N. A., & Reinecke, K. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642289 · Cited by 39
Utilizing External Knowledge to Enhance Semantics in Emotion Detection in Conversation
Ren, F., & She, T. (2021) · IEEE Access · doi:10.1109/access.2021.3128277 · Cited by 13
“The task is important to research in several areas, such as affective dialogue systems [1]–[3], healthcare [4], [5] recommendation system [6], and so on.”
BackgroundConversation Model Fine-Tuning for Classifying Client Utterances in Counseling Dialogues
Park, S., Kim, D., & Oh, A. H. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1148 · Cited by 13
“…to analyzing the dynamic patterns of relationship between the counselor and the client by focusing on the language of counselors (Imel et al., 2015; Althoff et al., 2016), clustering topics of client issues (Dinakar et al., 2014), and looking at therapy outcomes (Howes et al., 2014; Hull, 2015).”
BackgroundA Bibliometric Review of Natural Language Processing Applications in Psychology from 1991 to 2023
Chen, G., Tan, B., Laham, N., Tracey, T. J. G., Lapinski, S., & Liu, Y. (2024) · Basic and Applied Social Psychology · doi:10.1080/01973533.2024.2433720 · Cited by 14
“With the increase in available text data and the advance of computation methods, NLP has been shown to be a promising approach to analyzing large-scale text data (Althoff et al., 2016; Carenini et al., 2011; Y. Goldberg, 2017; Jurafsky & Martin, 2019).”
Li, F., Li, J., & Abza, F. (2025) · Scientific Reports · doi:10.1038/s41598-025-85392-6 · Cited by 11
Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Tasks
Chawla, K., Shi, W., Zhang, J., Lucas, G., Zhou, Y., & Gratch, J. S. (2023) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.53 · Cited by 35
“A counselor needs to be adaptive, personalized, should understand the core issues, and should facilitate a change in patient’s perspective (Althoff et al., 2016).”
BackgroundInfluentialSong, D. (2024) · American Journal of Education and Learning · doi:10.55284/ajel.v9i1.1024 · Cited by 12
Hierarchical and Multi-View Dependency Modelling Network for Conversational Emotion Recognition
Ruan, Y.-P., Zheng, S., Li, T., Wang, F., & Pei, G. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9747123 · Cited by 11
Examining Artificial Intelligence Policies in Counsellor Education
Campbell, L. O., Frawley, C., Lambie, G. W., Cabrera, K. S., & Vizcarra, B. D. (2025) · Counselling and Psychotherapy Research · doi:10.1002/capr.12880 · Cited by 15
Telepsychology: Applications, advantages, and challenges
Yuchang, J. I. N., Zhang, Z., Zheng, P., & Junxiu, A. N. (2021) · Advances in Psychological Science · doi:10.3724/sp.j.1042.2022.00141 · Cited by 12
Rojewska, K., Maćkowska, S., Maćkowski, M., Różańska, A., Barańska, K., Dzieciątko, M., & Spińczyk, D. (2022) · Applied Sciences · doi:10.3390/app12094702 · Cited by 10
Hornstein, S., Scharfenberger, J., Lueken, U., Wundrack, R., & Hilbert, K. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01121-9 · Cited by 17
“A study from 2016 applied NLP techniques to identify counseling strategies associated with better outcomes, utilizing a sample of 80.000 text-based counseling conversations 26 .”
InfluentialLearning How Spectator Reactions Affect Popularity on Twitch
Kim, J., Park, K., Song, H., Park, J. Y., & Cha, M. (2020) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp48618.2020.00-84 · Cited by 13
“• Auxiliary words (3 variables): Based on the previous report on online conversations [16], we count the fraction of chat utterances of popular linguistic markers for hedge (e.g., ‘maybe’, ‘fairly’) from the word list in github.com/words/hedges, question, and exclamation.”
BackgroundRestatement and Question Generation for Counsellor Chatbot
Lee, J. S. Y., Liang, B., & Fong, H. (2021) · Workshop on NLP for Positive Impact (NLP4PI) · doi:10.18653/v1/2021.nlp4posimpact-1.1 · Cited by 18
“Further research is needed to take into account the progress of the counselling session when selecting a reply (Althoff et al., 2016; Zhang and Danescu-Niculescu-Mizil, 2020), and to measure correlation with counselling outcomes.”
BackgroundTrouble on the Horizon: Forecasting the Derailment of Online Conversations as they DevelopPreprint
Chang, J. P., & Danescu-Niculescu-Mizil, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.01362 · Cited by 19
“terances (Althoff et al., 2016), sentiment imbalance (Niculae et al.”
BackgroundMethodInfluentialAhne, A., Fagherazzi, G., Tannier, X., Czernichow, T., & Orchard, F. (2022) · Journal of Medical Internet Research · doi:10.2196/27434 · Cited by 9
“High-quality clinical decision support capabilities for clinicians are needed to appropriately interpret the exponentially growing data [6,7], such as electronic health records, laboratory results, doctor-patient interactions, social media, and biomedical literature [8-11], to improve clinical knowledge in the decisio…”
Natural Language Processing in Mental Health Research and Practice
Henry, S., Yetişgen, M., & Uzuner, Ö. (2021) · Health informatics · doi:10.1007/978-3-030-70558-9_13 · Cited by 15
Automation of Protocoling Advanced MSK Examinations Using Natural Language Processing Techniques.
Eghbali, N., Siegal, D. S., Klochko, C. L., & Ghassemi, M. M. (2023) · PubMed Central · Cited by 9
Critical behavioral traits foster peer engagement in Online Mental Health Communities
Srivastava, A., Gupta, T., Cerezo, A., Lord, S. P., Akhtar, M. S., & Chakraborty, T. (2025) · PLoS ONE · doi:10.1371/journal.pone.0316906 · Cited by 10
Li, M., Gu, D., Li, R., Gu, Y., Hu, L., Su, K., Wang, X., & Zhang, G. (2025) · Journal of Medical Internet Research · doi:10.2196/60292 · Cited by 10
“Research has shown that similar to the factor of self, described in the previous section, when counselors talk about the future and help support seekers shift their viewpoint toward the future, it increases the likelihood that the support seekers will experience an altered perspective [16].”
Yusufov, M., Pirl, W. F., Braun, I. M., Tulsky, J. A., & Lindvall, C. J. (2022) · Journal of Pain and Symptom Management · doi:10.1016/j.jpainsymman.2022.06.007 · Cited by 12
Huang, Y., Liu, H., Li, S., Wang, W., & Zhou, Z. (2022) · Frontiers in Public Health · doi:10.3389/fpubh.2022.817570 · Cited by 8
“This format facilitates both counselees and counselors to provide help-seeking information at one time as much as possible, in which context counselors want to circumvent the ambiguity of response (32) or to highlight their authorship differing from other counselors’ responses (80).”
BackgroundInfluentialCognitive Internet of Things (IoT) and computational intelligence for mental well-being
Thapa, S., Ghimire, A., Adhikari, S., Bhoi, A. K., & Barsocchi, P. (2022) · Elsevier eBooks · doi:10.1016/b978-0-323-85751-2.00004-9 · Cited by 13
Zainal, N. H., Eckhardt, R., Rackoff, G. N., Fitzsimmons‐Craft, E. E., Rojas-Ashe, E. E., Taylor, C. B., Funk, B., Eisenberg, D., Wilfley, D. E., & Newman, M. G. (2025) · Psychological Medicine · doi:10.1017/s0033291725000340 · Cited by 12
“For instance, a study found that NLP sentiment analysis yielded an AUC of .708 to predict face to face therapist fidelity (Althoff, Clark, & Leskovec, 2016).”
Huang, Y., Liu, H., Chi, M., Meng, S., & Wang, W. (2025) · Digital Health · doi:10.1177/20552076251333480 · Cited by 12
“65 In the context of Chinese culture, which emphasizes collectivism and relationship-building, these linguistic markers may also re fl ect the cultural values of harmony and indirect communication.”
Priyadarshi, A., & Saha, S. K. (2020) · Network Modeling Analysis in Health Informatics and Bioinformatics · doi:10.1007/s13721-019-0216-2 · Cited by 8
Analyzing behavioral changes of Twitter users after exposure to misinformation
Wang, Y., Han, R. Y., Lehman, T. S., Lv, Q., & Mishra, S. (2021) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1145/3487351.3492718 · Cited by 8
“Similar to prior work [36], [37], we adopted the Jensen-Shannon Divergence [38] to measure the unigram difference (hourly”
Empathetic Response Generation for Distress Support
Welivita, A., Yeh, C.-H., & Pu, P. (2023) · Annual Meeting of the Special Interest Group on Discourse and Dialogue · doi:10.18653/v1/2023.sigdial-1.59 · Cited by 22
“Recent research has curated and conducted analysis on real counseling conversations (Althoff et al., 2016; Zhang and Danescu-Niculescu-Mizil, 2020).”
BackgroundRefusing to Fall Behind: The Ethical Obligation to Embrace AI in Mental Health Social Work
Flaherty, H. B., & Krishnan, P. (2025) · Journal of Evidence-Based Social Work · doi:10.1080/26408066.2025.2553018 · Cited by 8
Nikzad, A. H., Lysaker, P. H., Minor, K. S., Leonhardt, B. L., Liberman, M., Vohs, J. L., Wiesepape, C. N., & Tang, S. X. (2024) · Early Intervention in Psychiatry · doi:10.1111/eip.13628 · Cited by 10
“…of NLP include identification of successful conversational strategies, evaluation and improvement of therapeutic skills of psychotherapists and better detection of high-risk clinical conditions such as suicidality (Althoff, Clark, and Leskovec 2016; Flemotomos et al. 2022; Levis et al. 2021).”
Yim, S. H., Yoo, D. W., Polymerou, A., Liu, Y., & Saha, K. (2025) · International Journal of Eating Disorders · doi:10.1002/eat.24604 · Cited by 11
Artificial Intelligence to Support Human-Provided Mental Health Treatment
Soma, C. S., Kuo, P. B., Mehta, M., Srikumar, V., Imel, Z. E., & Atkins, D. C. (2026) · Annual Review of Clinical Psychology · doi:10.1146/annurev-clinpsy-061724-075336 · Cited by 9
Enhancing Depression Detection from Narrative Interviews Using Language Models
Sood, P., Yang, X., & Wang, P. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10385480 · Cited by 6
“This will greatly foster a supportive environment with a sense of belonging and understanding [2], [3].”
BackgroundMilligan, G., Bernard, A., Dowthwaite, L., Vallejos, E. P., Davis, J. N., Salhi, L., & Goulding, J. (2024) · Counselling and Psychotherapy Research · doi:10.1002/capr.12766 · Cited by 7
Chatbot-Based Mood and Activity Journaling for Resource-Oriented CBT Support of Students
Striegl, J., Fekih, F., Weber, G., & Loitsch, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-61063-9_12 · Cited by 6
Phrase-level pairwise topic modeling to uncover helpful peer responses to online suicidal crises
Jiang, M., Ammerman, B. A., Zeng, Q., Jacobucci, R., & Brodersen, A. S. (2020) · Humanities and Social Sciences Communications · doi:10.1057/s41599-020-0513-5 · Cited by 9
“…that has been conducted in this area has worked to improve automatic suicide risk determinations of users posting as a way to triage resources (Althoff et al., 2016; Coppersmith et al., 2018; De Choudhury et al., 2016; DeMasi et al., 2019; Milne et al., 2016, 2019; Morris, 2015; Shing et al.,…”
BackgroundPrediction of Chinese clients’ satisfaction with psychotherapy by machine learning
Yao, L., Wang, Z., Gu, H., Zhao, X., Chen, Y., & Liu, L. (2023) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2023.947081 · Cited by 6
“(45) found that actionable conversation strategies were linked with clients’ higher therapy satisfaction.”
BackgroundMalgaroli, M., Tseng, E., Hull, T. D., Jennings, E. L. M., Choudhury, T., & Simon, N. M. (2023) · JMIR AI · doi:10.2196/47223 · Cited by 7
“Similar work has been conducted in the context of crisis counseling platforms to analyze patients’ messages for suicidal ideation [65,66].”
BackgroundJapanese Dictionary for Sentiment Analysis of Counselling Text
Nakayama, M., Hatanakaka, C., Konakawa, H., Suzuki, Y., Koh, A. H. Q., Sugihara, Y., & Kawai, T. (2021) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3472307.3484663 · Cited by 6
“Given its text-based nature, chat-based counselling provides an opportunity for machine-based analysis [1].”
BackgroundTrends and Overview: The Potential of Conversational Agents in Digital Health
Saha, T., Tiwari, A. S., & Saha, S. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-28241-6_36 · Cited by 6
Metadata
- Authors
- Althoff, T., Clark, K., & Leskovec, J.
- Affiliations
- Stanford University (US)
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press - Journals
- Published
- 2016-12
- Volume
- 4
- Pages
- 463-476
- ISSN
- 2307-387X (ISSN-L)
- PMC
- PMC5361062
- OpenAlex
- W2484061479
- Cited by
- 322
- References
- 31
- Citations by year
- 2026: 33 · 2025: 38 · 2024: 25 · 2023: 39 · 2022: 44 · 2021: 37 · 2020: 40 · 2019: 28 · 2018: 18 · 2017: 18 · 2016: 1
- FWCI
- 34.02
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by
- Locations
- Transactions of the Association for Computational Linguistics (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1010921, 1149837)
- National Institutes of Health
- Defense Advanced Research Projects Agency
- Multidisciplinary University Research Initiative
- National Institute of Biomedical Imaging and Bioengineering (U54EB020405)
- Army Research Office
- Topics
- Social Sciences › Psychology › Social Psychology › Mental Health via Writing
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Keywords
- counseling conversations, psychotherapy, computational discourse analysis, conversational strategies, message clustering, psycholinguistics, word frequency analysis, language model comparison, mental health
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.