Empathy Prediction from Diverse Perspectives
Francine Chen, Scott Carter, Tatiana Lau, Nayeli Suseth Bravo, Sumanta Bhattacharyya, Kate Sieck, Charlene C. Wu
Abstract
A person’s perspective on a topic can influence their empathy towards a story. To investigate the use of personal perspective in empathy prediction, we collected a dataset, EmpathyFromPerspectives, where a user rates their empathy towards a story by a person with a different perspective on a prompted topic. We observed in the dataset that user perspective can be important for empathy prediction and developed a model, PPEP, that uses a rater’s perspective as context for predicting the rater’s empathy towards a story. Experiments comparing PPEP with baseline models show that use of personal perspective significantly improves performance. A user study indicated that human empathy ratings of stories generally agreed with PPEP’s relative empathy rankings.
BibTeX
@inproceedings{chen-etal-2025-empathy,
title = "Empathy Prediction from Diverse Perspectives",
author = "Chen, Francine and
Carter, Scott and
Lau, Tatiana and
Bravo, Nayeli Suseth and
Bhattacharyya, Sumanta and
Sieck, Kate and
Wu, Charlene C.",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.439/",
doi = "10.18653/v1/2025.acl-long.439",
pages = "8959--8974",
ISBN = "979-8-89176-251-0"
}