How Do Social Bots Participate in Misinformation Spread? A Comprehensive Dataset and Analysis

TL;DR

This paper presents a large-scale, multimodal dataset from Sina Weibo that includes annotations of misinformation and social bots, enabling comprehensive analysis of how social bots contribute to misinformation spread and echo chambers.

Contribution

The paper introduces a novel, extensive dataset with annotations for misinformation and social bots, facilitating detailed analysis of their roles in social media misinformation dynamics.

Findings

Social bots are heavily involved in spreading misinformation.

Misinformation on similar topics tends to have similar content, fostering echo chambers.

Social bots generate content aimed at manipulating public opinion.

Abstract

Social media platforms provide an ideal environment to spread misinformation, where social bots can accelerate the spread. This paper explores the interplay between social bots and misinformation on the Sina Weibo platform. We construct a large-scale dataset that includes annotations for both misinformation and social bots. From the misinformation perspective, the dataset is multimodal, containing 11,393 pieces of misinformation and 16,416 pieces of verified information. From the social bot perspective, this dataset contains 65,749 social bots and 345,886 genuine accounts, annotated using a weakly supervised annotator. Extensive experiments demonstrate the comprehensiveness of the dataset, the clear distinction between misinformation and real information, and the high quality of social bot annotations. Further analysis illustrates that: (i) social bots are deeply involved in information spread; (ii) misinformation with the same topics has similar content, providing the basis of echo chambers, and social bots would amplify this phenomenon; and (iii) social bots generate similar content aiming to manipulate public opinions.