Search papers, labs, and topics across Lattice.
This study investigates the relationship between counselor behaviors and dialogue quality in AI-assisted text-based counseling, focusing on the role of Affirmation compared to Reflection. Utilizing a large-scale dataset of Japanese text counseling sessions, the authors find that Affirmation is a stronger predictor of session quality than Reflection, which has been the traditional focus in related research. Additionally, cross-dataset experiments indicate that this quality signal is also present in English counseling contexts, suggesting broader applicability of the findings.
Affirmation, not Reflection, emerges as the key behavioral marker for high-quality text-based counseling sessions, challenging established norms in the field.
While AI-assisted text-based counseling is gaining attention, it remains empirically unclear which counselor behaviors are associated with higher dialogue quality. Existing research often focuses heavily on Reflection, borrowing frameworks from Motivational Interviewing. To address this gap, we conduct a multi-layered analysis using KokoroChat, a large-scale Japanese text counseling dataset conducted by professional counselors and trainees, newly annotated with counselor strategy tags and client distress levels. Our results show that, under the quality indicators used in this study, Affirmation is more consistently associated with session quality than Reflection among the analyzed strategies. Cross-dataset transfer experiments further suggest that this quality signal can be observed to some extent on ESConv, an English dataset with non-expert supporters. These findings provide empirical implications for counselor training and emotional support system design. We release the additional KokoroChat annotations and experimental source code at https://github.com/UEC-InabaLab/BeyondReflection.
