CoChat

Large-scale Analysis of Counseling Conversations: An Application of Natural Language Processing to Mental Health

Open access
Althoff, Tim, Clark, Kevin, Leskovec, Jure · 2016 · Transactions of the Association for Computational Linguistics

The 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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1162/tacl_a_00111

Cites

31 of 31 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Differences in counselor message length (in #tokens) over the course of the conversation are larger between more and less successful counselors (blue circle/red square) than between positive and negative conversations (solid/dashed). Error bars in all plots correspond to bootstrapped 95% confidence intervals using the member bootstrapping technique from Ren et al. (2010).
Figure 1 Differences in counselor message length (in #tokens) over the course of the conversation are larger between more and less successful counselors (blue circle/red square) than between positive and negative conversations (solid/dashed). Error bars in all plots correspond to bootstrapped 95% confidence intervals using the member bootstrapping technique from Ren et al. (2010).CC BY · PubMed Central
Figure 2 More successful counselors are more varied in their language across positive/negative conversations, suggesting they adapt more. All differences between more successful and less successful counselors except for the 0–20 bucket were found to be statistically significant (p < 0.05; bootstrap resampling test).
Figure 2 More successful counselors are more varied in their language across positive/negative conversations, suggesting they adapt more. All differences between more successful and less successful counselors except for the 0–20 bucket were found to be statistically significant (p < 0.05; bootstrap resampling test).CC BY · PubMed Central
Figure 3 More ambiguous situations (length of situation setter) are less likely to result in positive conversations.
Figure 3 More ambiguous situations (length of situation setter) are less likely to result in positive conversations.CC BY · PubMed Central
Figure 4 All counselors react to short, ambiguous messages by writing more (relative to the texter message) but more successful counselors do it more than less successful counselors.
Figure 4 All counselors react to short, ambiguous messages by writing more (relative to the texter message) but more successful counselors do it more than less successful counselors.CC BY · PubMed Central
Figure 5 More successful counselors use less common/templated responses (after the texter first explains the situation). This suggests that they respond in a more creative way. There is no significant difference between positive and negative conversations.
Figure 5 More successful counselors use less common/templated responses (after the texter first explains the situation). This suggests that they respond in a more creative way. There is no significant difference between positive and negative conversations.CC BY · PubMed Central
Figure 6 Our conversation model generates a particular conversation Ck by first generating a sequence of hidden states S0, S1,… according to a Markov model. Each state Si then generates a message as a bag of words Wi, 0, Wi, 1 … according a unigram language model WSi.
Figure 6 Our conversation model generates a particular conversation Ck by first generating a sequence of hidden states S0, S1,… according to a Markov model. Each state Si then generates a message as a bag of words Wi, 0, Wi, 1 … according a unigram language model WSi.CC BY · PubMed Central
Figure 7 Allowed state transitions for the conversation model. Counselor and texter messages are produced by distinct states and conversations must progress through the stages in increasing order.
Figure 7 Allowed state transitions for the conversation model. Counselor and texter messages are produced by distinct states and conversations must progress through the stages in increasing order.CC BY · PubMed Central
Figure 8 More successful counselors are quicker to get to know texter and issue (stage 2) and use more of their time in the “problem solving” phase (stage 4).
Figure 8 More successful counselors are quicker to get to know texter and issue (stage 2) and use more of their time in the “problem solving” phase (stage 4).CC BY · PubMed Central
Figure 9 A: Throughout the conversation there is a shift from talking about the past to future, where in positive conversations this shift is greater; B: Texters that talk more about others more often feel better after the conversation; C: More positive sentiment by the texter throughout the conversation is associated with successful conversations.
Figure 9 A: Throughout the conversation there is a shift from talking about the past to future, where in positive conversations this shift is greater; B: Texters that talk more about others more often feel better after the conversation; C: More positive sentiment by the texter throughout the conversation is associated with successful conversations.CC BY · PubMed Central
Figure 10 Prediction accuracies vs. percent of the conversation seen by the model (without texter features).
Figure 10 Prediction accuracies vs. percent of the conversation seen by the model (without texter features).CC BY · PubMed Central

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.

A few free checks a day · papers already verified open instantly · results are public

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?

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

Research works printed but not linked: 5

  1. Levitt Dana Heller, 2005, The Journal of Humanistic Counseling, Education and Development, 44(1).
  2. Niederhoffer Kate G., 2002, Journal of Language and Social Psychology, 21(4).
  3. Pyszczynski Tom, 1987, Journal of Personality and Social Psychology, 52(5).
  4. Ren Shiquan, 2010, Journal of Applied Statistics, 37(9).
  5. Tausczik Yla R., 2010, Journal of Language and Social Psychology, 29(1).

Cited by

See all 322

Metadata

Authors
Althoff, T., Clark, K., & Leskovec, J.
Affiliations
Stanford University (US)
Venue
Transactions of the Association for Computational Linguistics
Published
2016-12
Volume
4
Pages
463-476
ISSN
2307-387X (ISSN-L)
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
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.