Zhou, Naitian, and David Jurgens. "Condolence and empathy in online communities." Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.

This research focuses on the dynamics of offering condolences online, analyzing 11.4 million expressions of distress and 2.8 million corresponding condolences to understand the quality and impact of online support. By leveraging computational tools and social psychology insights, the study develops a novel dataset to quantify empathy in online condolences using appraisal theory. Findings indicate a significant disparity in the types of distress that receive genuinely supportive responses versus mere engagement. Furthermore, the study highlights that the characteristics of helpful online condolences significantly differ from those valued in face-to-face interactions.