Forecasting the Growth of Social Media Information Cascades: Towards Human-in-the-Loop Misinformation Triage

2026-10-05

AI Summary

This study addresses the challenge of predicting propagation potential during early misinformation triage by proposing a human-AI collaborative framework grounded in early cascade growth prediction on social media. Leveraging activity data from the first 30 minutes, the method constructs an ensemble model integrating structural depth and temporal arrival entropy, combined with reply pattern analysis and evidence retrieval to enable multimodal early warning. Technically, the framework incorporates propagation tree feature engineering, logistic regression, LLM-based factuality analysis, reciprocal rank fusion, and sentence reranking. Experimental results demonstrate that for highly active propagation trees, the model achieves an R² of 0.395, reducing prediction error by 11.7%, while evidence retrieval attains a Top-5 hit rate of 74.2%. These findings indicate that the proposed approach significantly enhances early misinformation triage efficacy.

Abstract

Limited review teams must identify which emerging claims are likely to keep growing before their eventual reach is known. We center early misinformation triage on this continuation-forecasting problem: predicting subsequent recorded propagation-tree growth from the first 30 minutes of activity. On FibVID, we compare early node count with structural depth entropy, temporal arrival entropy, and their pair while keeping all propagation trees from each original claim in one partition. Across 352 test trees from 59 claim groups separate from training, the combined model raises $R^2$ for log-transformed future growth from 0.307 to 0.323 and reduces log-MAE by 2.4% (95% claim-bootstrap CI, -0.4% to 5.2%). The gain is especially pronounced among 97 high-activity trees: $R^2$ rises from 0.248 to 0.395, Spearman's $ρ$ from 0.394 to 0.529, and log-MAE falls by 11.7% (95% CI, -1.9% to 23.9%). Complementing the 30-minute growth forecast, we analyze the first 15 replies in 563 PHEME threads. In this cohort, the 15th reply arrives after a median of 28.8 minutes; 52.0% reach the fixed reply prefix within 30 minutes and 71.6% within one hour. Even without the LLM-generated factual-accuracy dimension, the remaining stance, communicative, and affective state composition retains cross-event ranking signal (ROC-AUC 0.538); including that dimension increases ROC-AUC to 0.562. In a separate Check-COVID evaluation of 229 claims, reciprocal-rank fusion retrieves a gold evidence document within the top five for 74.2% of claims and within the top 20 for 94.3%; sentence reranking reaches Recall@20 of 58.1%. We propose an integrated human-review system that brings these early forecasts, response patterns, and retrieved evidence together for misinformation triage relying on the potential virality of claims.

Problem

• misinformation triage
• cascade growth forecasting
• social media
• early prediction
• information cascades

Innovation

• Information Cascade Forecasting
• Misinformation Triage
• Propagation Entropy
• Evidence Retrieval
• Human-in-the-Loop