A Lightweight Approach for User and Keyword Classification in Controversial Topics

2025-01-21

AI Summary

Existing stance analysis methods for controversial topics typically rely on large-scale annotated datasets or user social graphs, making them ill-suited for lightweight, real-time public opinion monitoring. To address this, we propose an unsupervised random-walk-based stance modeling approach requiring only a single seed word. Our method constructs a heterogeneous graph from keyword co-occurrence and employs a customized random walk to jointly propagate and classify user stances and keyword concerns. It operates without labeled data, user interaction information, or pre-trained models—significantly reducing both data dependency and computational overhead. Evaluated on multiple controversial-topic datasets, our method outperforms state-of-the-art unsupervised and weakly supervised baselines in both user stance classification and keyword concern identification. It demonstrates high efficiency, robustness, and scalability, making it well-suited for large-scale, real-time舆情 analysis.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Machine Learning: Learning Preferences or Rankings

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Classifying the stance of individuals on controversial topics and uncovering their concerns is crucial for social scientists and policymakers. Data from Online Social Networks (OSNs), which serve as a proxy to a representative sample of society, offers an opportunity to classify these stances, discover society's concerns regarding controversial topics, and track the evolution of these concerns over time. Consequently, stance classification in OSNs has garnered significant attention from researchers. However, most existing methods for this task often rely on labelled data and utilise the text of users' posts or the interactions between users, necessitating large volumes of data, considerable processing time, and access to information that is not readily available (e.g. users' followers/followees). This paper proposes a lightweight approach for the stance classification of users and keywords in OSNs, aiming at understanding the collective opinion of individuals and their concerns. Our approach employs a tailored random walk model, requiring just one keyword representing each stance, using solely the keywords in social media posts. Experimental results demonstrate the superior performance of our method compared to the baselines, excelling in stance classification of users and keywords, with a running time that, while not the fastest, remains competitive.

Problem

• Controversial Topics
• User Stance Classification
• Minimal Labeled Data

Innovation

• Social Network Analysis
• Position Classification
• Random Walk Model