Large-scale Analysis of Counseling Conversations: An Application of Natural Language Processing to Mental Health

By Tim Althoff, Kevin Clark, Jure Leskovec. Transactions of the Association for Computational Linguistics, 2016

347 citations recorded by the source corpus.

Mental illness is one of the most pressing public health issues of our time. While counseling and psychotherapy can be effective treatments, our knowledge about how to conduct successful counseling conversations has been limited due to lack of large-scale data with labeled outcomes of the conversations. In this paper, we present a large-scale, quantitative study on the discourse of text-message-based counseling conversations. We develop a set of novel computational discourse analysis methods to measure how various linguistic aspects of conversations are correlated with conversation outcomes. Applying techniques such as sequence-based conversation models, language model comparisons, message clustering, and psycholinguistics-inspired word frequency analyses, we discover actionable conversation strategies that are associated with better conversation outcomes.

Subfields: Artificial Intelligence, Social Psychology

View Paper: https://www.semanticscholar.org/paper/c151f144c2c0e8d3b176edaf2ce5369c7707bd31

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Social Psychology

Citations in the corpus

COSMIC: COmmonSense knowledge for eMotion Identification in Conversations (2020, neutral): “, 2016; Azab, 2019), health conversations (Althoff et al., 2016; Pérez-Rosas et al., 2017) and others.”
It’s going to be okay: Measuring Access to Support in Online Communities (2018, neutral): “Prior works have also examined the language of support in online support forums for health-related issues (Biyani et al., 2014; Wang et al., 2012; De Choudhury and De, 2014; Althoff et al., 2016; De Choudhury and Kiciman, 2017), often with the aim of improving people’s access.”
Artificial Intelligence for Mental Health and Mental Illnesses: An Overview (2019, background): “DL is ideal for discovering intricate structures in high-dimensional data like those contained in clinician notes in EHRs [45], or clinical and non-clinical data provided by patients [47, 48].”
Challenges in Building Intelligent Open-domain Dialog Systems (2019, background): “This issue is mainly about how to optimize the behaviors and strategies of a dialog system to maximize long-term user engagement and accomplish long-term, complex goals such as providing emotional comfort or even psychological counseling [3, 12, 101, 171].”
Ethical by Design: Ethics Best Practices for Natural Language Processing (2017, background): “Althoff, Clark and Leskovec (2016) describe an analysis of counseling conversations using NLP meth-ods; here, perhaps because the patients are still alive, even stronger privacy protection is indicated.”
A Computational Approach to Understanding Empathy Expressed in Text-Based Mental Health Support (2020, background): “Previous work in NLP for mental health has focused on analysis of effective conversation strategies (Althoff et al., 2016; Pérez-Rosas et al., 2019; Zhang and Danescu-Niculescu-Mizil, 2020), identification of therapeutic actions (Lee et al.”
Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach (2021, background): “These efforts have predominantly focused on analyzing techniques that are effective for seeking and providing conversational support such as adaptability to various contexts and diversity of responses [1, 49, 60, 71, 72].”