@inproceedings{katki-etal-2025-automated,
    title = "Automated Coding of Counsellor and Client Behaviours in Motivational Interviewing Transcripts: Validation and Application",
    author = "Ali, Soliman  and
      Zhu, Jiading  and
      Guo, Alex  and
      Ye, Xiao Nan  and
      Gu, Qilin  and
      Wolff, Jodi  and
      Cooper, Carolynne  and
      Melamed, Osnat C.  and
      Selby, Peter  and
      Rose, Jonathan",
    editor = "Zechariah, Arun  and
      Krishna S, Balu  and
      Misra Sharma, Dipti  and
      Mary Thomas, Hannah  and
      Mammen, Joy  and
      Krishnamurthy, Parameswari  and
      Mujadia, Vandan",
    booktitle = "NLP-AI4Health",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/old-master/2025.nlpai4health-main.4/",
    pages = "25--54",
    ISBN = "979-8-89176-315-9",
    abstract = "Motivational Interviewing (MI) is a widely-used talk therapy approach employed by clinicians to guide clients toward healthy behaviour change. Both the automation of MI itself and the evaluation of human counsellors can benefit from high-quality automated classification of counsellor and client utterances. We show how to perform this ``coding'' of utterances using LLMs, by first performing utterance-level parsing and then hierarchical classification of counsellor and client language. Our system achieves an overall accuracy of 82{\%} for the upper (coarse-grained) hierarchy of the counsellor codes and 88{\%} for client codes. The lower (fine-grained) hierarchy scores at 68{\%} and 76{\%} respectively. We also show that these codes can be used to predict the session-level quality of a widely-used MI transcript dataset at 87{\%} accuracy. As a demonstration of practical utility, we show that the slope of the amount of change/sustain talk in client speech across 106 MI transcripts from a human study has significant correlation with an independently surveyed week-later treatment outcome ($r=0.28, p<0.005$). Finally, we show how the codes can be used to visualize the trajectory of client motivation over a session alongside counsellor codes. The source code and several datasets of annotated MI transcripts are released."
}