Multi-source Heterogeneous Public Opinion Analysis via Collaborative Reasoning and Adaptive Fusion: A Systematically Integrated Approach

TL;DR

This paper presents CRAF, a comprehensive framework that systematically integrates multi-source heterogeneous public opinion data using collaborative reasoning and adaptive fusion, improving analysis accuracy and cross-platform adaptability.

Contribution

The paper introduces a novel multi-stage reasoning framework combining feature-based methods with LLMs, including cross-platform attention, hierarchical fusion, joint topic-sentiment learning, and multimodal content processing.

Findings

Achieves 4.1% higher topic clustering ARI than baselines.

Improves sentiment F1-score by 3.8% over existing methods.

Reduces labeled data needs for new platforms by 75%.

Abstract

The analysis of public opinion from multiple heterogeneous sources presents significant challenges due to structural differences, semantic variations, and platform-specific biases. This paper introduces a novel Collaborative Reasoning and Adaptive Fusion (CRAF) framework that systematically integrates traditional feature-based methods with large language models (LLMs) through a structured multi-stage reasoning mechanism. Our approach features four key innovations: (1) a cross-platform collaborative attention module that aligns semantic representations while preserving source-specific characteristics, (2) a hierarchical adaptive fusion mechanism that dynamically weights features based on both data quality and task requirements, (3) a joint optimization strategy that simultaneously learns topic representations and sentiment distributions through shared latent spaces, and (4) a novel multimodal extraction capability that processes video content from platforms like Douyin and Kuaishou by integrating OCR, ASR, and visual sentiment analysis. Theoretical analysis demonstrates that CRAF achieves a tighter generalization bound with a reduction of O(sqrt(d log K / m)) compared to independent source modeling, where d is feature dimensionality, K is the number of sources, and m is sample size. Comprehensive experiments on three multi-platform datasets (Weibo-12, CrossPlatform-15, NewsForum-8) show that CRAF achieves an average topic clustering ARI of 0.76 (4.1% improvement over best baseline) and sentiment analysis F1-score of 0.84 (3.8% improvement). The framework exhibits strong cross-platform adaptability, reducing the labeled data requirement for new platforms by 75%.