A Computational Approach to Measure Empathy and Theory-of-Mind from Written Texts

TL;DR

This paper introduces ToM-Diary, a large annotated Korean text dataset, and evaluates transformer models like BERT for measuring theory-of-mind levels to advance computational empathy assessment.

Contribution

It provides a new large-scale dataset with ToM annotations and demonstrates the potential of NLP models to quantify perspective-taking in written texts.

Findings

BERT better detects self-focused sentences than other-focused ones

High ToM level sentences are more challenging for models to predict

The dataset enables large-scale analysis of empathy and perspective-taking

Abstract

Theory-of-mind (ToM), a human ability to infer the intentions and thoughts of others, is an essential part of empathetic experiences. We provide here the framework for using NLP models to measure ToM expressed in written texts. For this purpose, we introduce ToM-Diary, a crowdsourced 18,238 diaries with 74,014 Korean sentences annotated with different ToM levels. Each diary was annotated with ToM levels by trained psychology students and reviewed by selected psychology experts. The annotators first divided the diaries based on whether they mentioned other people: self-focused and other-focused. Examples of self-focused sentences are "I am feeling good". The other-focused sentences were further classified into different levels. These levels differ by whether the writer 1) mentions the presence of others without inferring their mental state(e.g., I saw a man walking down the street), 2) fails to take the perspective of others (e.g., I don't understand why they refuse to wear masks), or 3) successfully takes the perspective of others (It must have been hard for them to continue working). We tested whether state-of-the-art transformer-based models (e.g., BERT) could predict underlying ToM levels in sentences. We found that BERT more successfully detected self-focused sentences than other-focused ones. Sentences that successfully take the perspective of others (the highest ToM level) were the most difficult to predict. Our study suggests a promising direction for large-scale and computational approaches for identifying the ability of authors to empathize and take the perspective of others. The dataset is at [URL](https://github.com/humanfactorspsych/covid19-tom-empathy-diary)