Towards Explaining Subjective Ground of Individuals on Social Media

TL;DR

This paper introduces a neural model called Subjective Ground Attention that learns and explains individuals' subjective perspectives and moral judgments from social media text, enhancing interpretability of personal theory of mind.

Contribution

The paper presents a novel neural model that captures and explains individual subjective grounds and moral judgments from social media data, improving interpretability.

Findings

The model provides human-readable explanations of subjective preferences.

It effectively learns individuals' subjective orientations towards moral concepts.

Qualitative evaluation supports the model's ability to generate meaningful explanations.

Abstract

Large-scale language models have been reducing the gap between machines and humans in understanding the real world, yet understanding an individual's theory of mind and behavior from text is far from being resolved. This research proposes a neural model -- Subjective Ground Attention -- that learns subjective grounds of individuals and accounts for their judgments on situations of others posted on social media. Using simple attention modules as well as taking one's previous activities into consideration, we empirically show that our model provides human-readable explanations of an individual's subjective preference in judging social situations. We further qualitatively evaluate the explanations generated by the model and claim that our model learns an individual's subjective orientation towards abstract moral concepts