PVG at WASSA 2021: A Multi-Input, Multi-Task, Transformer-Based Architecture for Empathy and Distress Prediction

Atharva Kulkarni, Sunanda Somwase, Shivam Rajput, Manisha Marathe


Abstract
Active research pertaining to the affective phenomenon of empathy and distress is invaluable for improving human-machine interaction. Predicting intensities of such complex emotions from textual data is difficult, as these constructs are deeply rooted in the psychological theory. Consequently, for better prediction, it becomes imperative to take into account ancillary factors such as the psychological test scores, demographic features, underlying latent primitive emotions, along with the text’s undertone and its psychological complexity. This paper proffers team PVG’s solution to the WASSA 2021 Shared Task on Predicting Empathy and Emotion in Reaction to News Stories. Leveraging the textual data, demographic features, psychological test score, and the intrinsic interdependencies of primitive emotions and empathy, we propose a multi-input, multi-task framework for the task of empathy score prediction. Here, the empathy score prediction is considered the primary task, while emotion and empathy classification are considered secondary auxiliary tasks. For the distress score prediction task, the system is further boosted by the addition of lexical features. Our submission ranked 1st based on the average correlation (0.545) as well as the distress correlation (0.574), and 2nd for the empathy Pearson correlation (0.517).
Anthology ID:
2021.wassa-1.11
Volume:
Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
Month:
April
Year:
2021
Address:
Online
Venue:
WASSA
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
105–111
Language:
URL:
https://aclanthology.org/2021.wassa-1.11
DOI:
Bibkey:
Cite (ACL):
Atharva Kulkarni, Sunanda Somwase, Shivam Rajput, and Manisha Marathe. 2021. PVG at WASSA 2021: A Multi-Input, Multi-Task, Transformer-Based Architecture for Empathy and Distress Prediction. In Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 105–111, Online. Association for Computational Linguistics.
Cite (Informal):
PVG at WASSA 2021: A Multi-Input, Multi-Task, Transformer-Based Architecture for Empathy and Distress Prediction (Kulkarni et al., WASSA 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.wassa-1.11.pdf
Code
 mr-atharva-kulkarni/EACL-WASSA-2021-Empathy-Distress