Learning affective meanings that derives the social behavior using Bidirectional Encoder Representations from Transformers

TL;DR

This paper introduces a BERT-based model to predict affective meanings in social behaviors, replacing costly survey methods and enhancing the scope of affective lexicons for better social behavior modeling.

Contribution

It develops a fine-tuned BERT model that accurately estimates affective meanings, expanding affective lexicons and improving social behavior prediction.

Findings

Achieves state-of-the-art accuracy in affective meaning estimation

Expands the affective lexicon beyond traditional survey limitations

Enables explanation of more social behaviors

Abstract

Predicting the outcome of a process requires modeling the system dynamic and observing the states. In the context of social behaviors, sentiments characterize the states of the system. Affect Control Theory (ACT) uses sentiments to manifest potential interaction. ACT is a generative theory of culture and behavior based on a three-dimensional sentiment lexicon. Traditionally, the sentiments are quantified using survey data which is fed into a regression model to explain social behavior. The lexicons used in the survey are limited due to prohibitive cost. This paper uses a fine-tuned Bidirectional Encoder Representations from Transformers (BERT) model to develop a replacement for these surveys. This model achieves state-of-the-art accuracy in estimating affective meanings, expanding the affective lexicon, and allowing more behaviors to be explained.