Investigation of Opinion Polarization in Online Communication: Towards an Integration of Explanation and Prediction

点击翻译按钮获取中文摘要

This project attempts to explore the causal mechanism and construct a predictive model of opinion polarization in online communication. In the first year, two studies were processed.The first study employs large-scale social media data and advanced computational method to demonstrate how interparty hostility is associated with the partisan identity of both the message sender and the target in the interaction. The disparity in the extent of received offensive speech is argued to result from individuals' tendency to maintain their partisan identification by expressing hostility toward representative individuals of opposing partisan groups. The analysis also provides insights into how political polarization and inter-party hostility can mutually reinforce each other, thus contributing to the understanding of political polarization on social media.Second, based on the social survey in which respondents’ Twitter accounts were acquired, I have collected a wide range of social media data, including users’ profile information, published content, and network. The amalgamated dataset of social media data and survey data facilitates the development of a predictive model for opinion polarization in the future.