Learning Word Ratings for Empathy and Distress from Document-Level User Responses
This work addresses the need for interpretable and robust emotion analysis tools in NLP, specifically for psychological constructs like empathy, though it is incremental as it applies deep learning to an existing problem of learning word ratings from higher-level supervision.
The paper tackles the problem of automatically creating empathy and distress word lexica from document-level user responses, which are difficult to manually construct, and introduces a Mixed-Level Feed Forward Network (MLFFN) that outperforms other approaches, resulting in the first-ever publicly available empathy lexicon.
Despite the excellent performance of black box approaches to modeling sentiment and emotion, lexica (sets of informative words and associated weights) that characterize different emotions are indispensable to the NLP community because they allow for interpretable and robust predictions. Emotion analysis of text is increasing in popularity in NLP; however, manually creating lexica for psychological constructs such as empathy has proven difficult. This paper automatically creates empathy word ratings from document-level ratings. The underlying problem of learning word ratings from higher-level supervision has to date only been addressed in an ad hoc fashion and has not used deep learning methods. We systematically compare a number of approaches to learning word ratings from higher-level supervision against a Mixed-Level Feed Forward Network (MLFFN), which we find performs best, and use the MLFFN to create the first-ever empathy lexicon. We then use Signed Spectral Clustering to gain insights into the resulting words. The empathy and distress lexica are publicly available at: http://www.wwbp.org/lexica.html.