Towards Explaining Subjective Ground of Individuals on Social Media
This work addresses the challenge of interpreting individual theory of mind from text for social media analysis, but it appears incremental as it builds on existing attention mechanisms without broad SOTA claims.
The paper tackles the problem of understanding individuals' subjective judgments on social media by proposing a neural model called Subjective Ground Attention, which learns subjective grounds and provides human-readable explanations for their preferences in social situations, with qualitative evaluation showing it captures orientation towards moral concepts.
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