DisTrack: a new Tool for Semi-automatic Misinformation Tracking in Online Social Networks

TL;DR

This paper addresses the challenge of tracking misinformation in Online Social Networks by proposing DisTrack, a semi-automated tool that combines NLP with Social Network Analysis and graph visualization. Its three-module pipeline retrieves OSN content, applies Natural Language Inference via a semi-automated fact-checking database (FacTeR-Check), and builds cascade graphs to visualize propagation and actor influence. Three case studies on discredit/hate, antivaccine, and Russia-Ukraine misinformation demonstrate the system's ability to extract conversations, distinguish posts that entail or contradict falsehoods, and trace misinformation lifecycles. DisTrack offers researchers and practitioners a visualization-enabled framework for monitoring, understanding, and mitigating online misinformation across OSNs.

Abstract

Introduction: This article introduces DisTrack, a methodology and a tool developed for tracking and analyzing misinformation within Online Social Networks (OSNs). DisTrack is designed to combat the spread of misinformation through a combination of Natural Language Processing (NLP) Social Network Analysis (SNA) and graph visualization. The primary goal is to detect misinformation, track its propagation, identify its sources, and assess the influence of various actors within the network. Methods: DisTrack's architecture incorporates a variety of methodologies including keyword search, semantic similarity assessments, and graph generation techniques. These methods collectively facilitate the monitoring of misinformation, the categorization of content based on alignment with known false claims, and the visualization of dissemination cascades through detailed graphs. The tool is tailored to capture and analyze the dynamic nature of misinformation spread in digital environments. Results: The effectiveness of DisTrack is demonstrated through three case studies focused on different themes: discredit/hate speech, anti-vaccine misinformation, and false narratives about the Russia-Ukraine conflict. These studies show DisTrack's capabilities in distinguishing posts that propagate falsehoods from those that counteract them, and tracing the evolution of misinformation from its inception. Conclusions: The research confirms that DisTrack is a valuable tool in the field of misinformation analysis. It effectively distinguishes between different types of misinformation and traces their development over time. By providing a comprehensive approach to understanding and combating misinformation in digital spaces, DisTrack proves to be an essential asset for researchers and practitioners working to mitigate the impact of false information in online social environments.

Figures (8)

• Figure 1: Visualization of the misinformation cascade. The $t$ axis represents time from left to right, vertices are claims made by actors in any OSN, while edges represent a relation whether implicit (semantic similarity) or explicit (a repost of another piece of content).
• Figure 2: DisTrack modules, top to bottom: 1) Information Retrieval, 2) Natural Language Inference, 3) OSN Tracking Visualization.
• Figure 3: Distribution of the groups of posts according to their type of NLI-based alignment (entailment or contradiction), in each of the three cases.
• Figure 4: Distribution of the groups of posts according to their number of retweets and number of likes, in each of the three cases, with only original tweets into account.
• Figure 5: Distribution of the groups of posts according to their number of followers, in each of the three cases.