"A Tale of Two Movements": Identifying and Comparing Perspectives in #BlackLivesMatter and #BlueLivesMatter Movements-related Tweets using Weakly Supervised Graph-based Structured Prediction

TL;DR

This paper introduces a weakly supervised, graph-based method for analyzing perspectives in #BlackLivesMatter and #BlueLivesMatter tweets, leveraging social-linguistic representations and large language models to outperform baselines.

Contribution

It presents a novel approach combining graph-based structured prediction with social-linguistic data and language models, requiring minimal labeled data.

Findings

Achieves comparable performance to manual annotation using artificial data.

Outperforms multitask baselines significantly.

Successfully characterizes perspectives supporting and opposing BLM.

Abstract

Social media has become a major driver of social change, by facilitating the formation of online social movements. Automatically understanding the perspectives driving the movement and the voices opposing it, is a challenging task as annotated data is difficult to obtain. We propose a weakly supervised graph-based approach that explicitly models perspectives in #BackLivesMatter-related tweets. Our proposed approach utilizes a social-linguistic representation of the data. We convert the text to a graph by breaking it into structured elements and connect it with the social network of authors, then structured prediction is done over the elements for identifying perspectives. Our approach uses a small seed set of labeled examples. We experiment with large language models for generating artificial training examples, compare them to manual annotation, and find that it achieves comparable performance. We perform quantitative and qualitative analyses using a human-annotated test set. Our model outperforms multitask baselines by a large margin, successfully characterizing the perspectives supporting and opposing #BLM.