TY - JOUR
AU - Leskovec, Jure
AB - Mental illness is one of the most pressing public health issues of our time.While counseling and psychotherapy can be effective treatments, our knowledgeabout how to conduct successful counseling conversations has been limited due tolack of large-scale data with labeled outcomes of the conversations. In thispaper, we present a large-scale, quantitative study on the discourse oftext-message-based counseling conversations. We develop a set of novelcomputational discourse analysis methods to measure how various linguisticaspects of conversations are correlated with conversation outcomes. Applyingtechniques such as sequence-based conversation models, language modelcomparisons, message clustering, and psycholinguistics-inspired word frequencyanalyses, we discover actionable conversation strategies that are associatedwith better conversation outcomes.
TI - Large-scale Analysis of Counseling Conversations: An Application of Natural Language Processing to Mental Health
JF - Transactions of the Association for Computational Linguistics
DO - 10.1162/tacl_a_00111
DA - 2016-08-01
UR - https://www.deepdyve.com/lp/mit-press/large-scale-analysis-of-counseling-conversations-an-application-of-D7v8710szR
SP - 463
EP - 476
VL - 4
IS - 
DP - DeepDyve
ER -