PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
March 29, 2026Психологический журнал / Psikhologicheskii zhurnal0 citations

Automatic Detection of Speech Intentions Using a Large Language Model

View Full Paper
AVA.V. VaninAVA.S. VlasovaEDE.N. Dymova

Key Points

  • This research focuses on developing a method to classify therapists' intentions in psychotherapy using a large language model.
  • Developed a methodology for classifying therapist's intentions.
  • Created optimal instructions for model interaction.
  • Analyzed impact of instruction completeness on accuracy.
  • Conducted independent assessments of 14 sessions by a team of experts.
  • Tested GPT-4 models for identifying therapist intentions.
  • Model achieved accuracy comparable to the best existing methods.
  • Improved instructions significantly enhanced model performance.
  • Variation in classification criteria influenced prediction accuracy.

Abstract

The article presents the results of a study of the capabilities of the large language model (GPT-4) to identify the intentional structure of the text. In the course of the research, the following tasks were solved: to develop a methodology for classifying therapists intentions in psychotherapeutic discourse; to create optimal instructions for working with the model; to analyze the impact of completeness of instructions on the accuracy of identifying intentions by the model; to study the relationship between the accuracy of the classification of intentions by the model with the frequency of occurrence of intentions in the text and the consistency of expert assessments. To analyze the intentional structure of texts, an original Methodology for classifying therapists intentions in psychotherapeutic discourse has been developed. Using this technique, a team of 3 experts who make decisions about the presence of intent in a remark independently of each other conducted marking up of 14 sessions in Russian (a total of 692 replicas of the therapist). The task of identifying the therapists intentions was solved by the GPT-4o-mini and GPT-o1 models. The model revealed the intentions of the psychotherapist, realized by him in specific speech utterances (replicas). The conducted research demonstrated the significant capabilities of the large GPT-4 language model in solving the problem of identifying the speakers speech intentions. The achieved accuracy in classifying the therapists intentions turned out to be at the level of the best indicators obtained in works on a similar subject. It is shown that improving the instructions significantly increases the quality of the models operation, and the complexity of the tasks assigned to the model is related to the accuracy of forecasts. Different criteria for the presence of intentions in the therapists remarks significantly changed the accuracy of the models predictions.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Vanin et al. (2025) studied this question.

synapsesocial.com/papers/69c8c277de0f0f753b39cd24https://doi.org/10.7868/s3034588x25060071
Ask AI
Helpful
Bookmark
Share
View Full Paper