Computerized natural language processing techniques can analyze psychotherapy sessions as texts, thus generating information about the therapy process and outcome and supporting the scaling-up of psychotherapy research. We used topic modeling to identify topics discussed in psychotherapy sessions and explored (a) which topics best identified clients' functioning and alliance ruptures and (b) whether changes in these topics were associated with changes in outcome. Transcripts of 873 sessions from 58 clients treated by 52 therapists were analyzed. Before each session, clients self-reported functioning and symptom level. After each session, therapists reported the extent of alliance rupture. Latent Dirichlet allocation was used to extract latent topics from psychotherapy textual data. Then a sparse multinomial logistic regression model was used to predict which topics best identified clients' functioning levels and the occurrence of alliance ruptures in psychotherapy sessions. Finally, we used multilevel growth models to explore the associations between changes in topics and changes in outcome. Session-based processing yielded a list of semantic topics. The model identified the labels above chance (65% to 75% accuracy). Change trajectories in topics were associated with change trajectories in outcome. The results suggest that topic models can exploit rich linguistic data within sessions to identify psychotherapy process and outcomes. Clinical Impact StatementQuestion: Can machine learning techniques identify the topics discussed in psychotherapy sessions and examine the associations between these topics and treatment process and outcome? Findings: Topic modeling yielded semantically meaningful topics that were then used to identify which topics were most closely associated with the level of clients' functioning and those that were most closely associated with rupture occurrence. Changes in these topics were associated with changes in outcome. Meaning: Topic modeling can enable therapists to be better attuned to specific topics that may signal important events in therapy. Using topic model output, therapists can access a summary of topics discussed in a session, locate specific themes associated with rupture or with clients' deterioration, and orient interventions to improve the situation. Next Steps: Future studies could use topic model output alongside existing monitoring tools to inform therapists of meaningful linguistic processes that occur within psychotherapy sessions.

Raw linguistic data within psychotherapy sessions may provide important information about clients' progress and well-being. In the current study, computerized text analytic techniques were applied to examine whether linguistic features were associated with clients' experiences of distress within and between clients and whether changes in linguistic features were associated with changes in treatment outcome. Transcripts of 729 psychotherapy sessions from 58 clients treated by 52 therapists were analyzed. Prior to each session, clients reported their distress level. Linguistic features were extracted automatically by using natural language parser for first-person singular identification and using positive and negative emotion words lexicon. The association between linguistic features and levels of distress was examined using multilevel models. At the within-client level, fewer first-person singular words, fewer negative emotional words and more positive emotional words were associated with lower distress in the same session; and fewer negative emotion words were associated with lower next session distress (rather small f 2 effect sizes ϭ 0.011 Ͻ f 2 Ͻ 0.022). At the between-client level, only first session use of positive emotion words was associated with first session distress ( p 2 effect size ϭ 0.08). A drop in the use of first-person singular words was associated with improved outcome from pre-to posttreatment (small p 2 effect size ϭ 0.05). The findings provide preliminary support for the association between clients' linguistic features and their fluctuating experience of distress. They point to the potential value of computerized linguistic measures to track therapeutic outcomes. Public Significance StatementThe current study explored whether utterances within sessions contain information about a client's progress. We used automated text analytic techniques to examine whether clients' linguistic features were associated with their experience of distress both relative to themselves and relative to others, and whether changes in these linguistic features were associated with treatment outcomes. The results indicated that when clients experienced less of distress in the days prior to a session they tended to use fewer first-person singular words, more positive emotion words and fewer negative emotion words in that session. In addition, when clients used fewer negative emotion words in a session, their distress in the days prior to the next session tended to be lower. Lastly, lesser use of first-person singular words in the later versus earlier stages of therapy was associated with improved treatment outcomes. These findings provide preliminary support for the potential use of raw linguistic data within psychotherapy session as a complement to standard monitoring systems to evaluate clients' progress.

Assume that a natural cyclic phenomenon has been measured, but the data is corrupted by errors. The type of corruption is application-dependent and may be caused by measurements errors, or natural features of the phenomenon. We assume that an appropriate metric exists, which measures the amount of corruption experienced. This article studies the problem of recovering the correct cycle from data corrupted by various error models, formally defined as the period recovery problem . Specifically, we define a metric property which we call pseudolocality and study the period recovery problem under pseudolocal metrics. Examples of pseudolocal metrics are the Hamming distance, the swap distance, and the interchange (or Cayley) distance. We show that for pseudolocal metrics, periodicity is a powerful property allowing detecting the original cycle and correcting the data, under suitable conditions. Some surprising features of our algorithm are that we can efficiently identify the period in the corrupted data, up to a number of possibilities logarithmic in the length of the data string, even for metrics whose calculation is NP-hard . For the Hamming metric, we can reconstruct the corrupted data in near-linear time even for unbounded alphabets. This result is achieved using the property of separation in the self-convolution vector and Reed-Solomon codes. Finally, we employ our techniques beyond the scope of pseudo-local metrics and give a recovery algorithm for the non-pseudolocal Levenshtein edit metric.

We study the phenomenon of linguistic synchrony between clients and therapists in a psychotherapy process. Linguistic Synchrony (LS) can be viewed as any observed interdependence or association between more than one person's linguistic behavior. Accordingly, we establish LS as a methodological task. We suggest a LS function that applies a linguistic similarity measure based on the Jensen-Shannon distance across the observed part-of-speech tag distributions (JSDuPos) of the speakers in different time frames. We perform a study over a unique corpus of 872 transcribed sessions, covering 68 clients and 59 therapists. After establishing the presence of client-therapist LS, we verify its association with therapeutic alliance and treatment outcome (measured using WAI and ORS), and additionally analyse the behavior of JSDuPos throughout treatment.Results indicate that (1) higher linguistic similarity at the session level associates with higher therapeutic alliance as reported by the client and therapist at the end of the session, (2) higher linguistic similarity at the session level associates with higher level of treatment outcome as reported by the client at the beginnings of the next sessions, (3) there is a significant linear increase in linguistic similarity throughout treatment, (4) surprisingly, higher LS associates with lower treatment outcome. Finally, we demonstrate how the LS function can be used to interpret and explore the mechanism for synchrony. 1

We present the first work on automatically capturing alliance rupture in transcribed therapy sessions, trained on the text and self-reported rupture scores from both therapists and clients. Our NLP baseline outperforms a strong majority baseline by a large margin and captures client reported ruptures unidentified by therapists in 40% of such cases.