A Spoken Dialogue Analysis Platform for Effective Counselling

This paper proposes a spoken dialogue analysis platform (SDAP) that could assist counsellors in person-to-person counselling by analysing counselling conversations and providing key information that could enhance the counsellors' understanding of the counselees' conditions and situations. The proposed platform has two main modules: a speech recognition module and a text analysis module that are specifically built for the Korean language. The speech recognition module uses NAVER CLOVA Speech service to convert voice recordings of counselling dialogues into text. The Korean text analysis environment of the text analysis module was built using NLTK, KoNLPy and scikit-learn library, and, for now, the module provides two types of text analysis: keyword analysis and sentiment analysis. The results of the text analyses that provide keywords and analysis of customers' emotional state can help counsellors to provide appropriate feedback to the counselees easily and more quickly, making the counselling fast and effective and reducing the counselees' waiting time. In the experiments, the text analysis module building process is elaborated in detail, and the usefulness of the proposed SDAP is exemplified by case studies on actual counselling conversations at a dental clinic and a fitness centre.