Before It's Too Late: A State Space Model for the Early Prediction of Misinformation and Disinformation Engagement

2025-02-07

AI Summary

Addressing the challenges of early false information detection on social media—particularly difficulties in early warning, irregular sampling, and inadequate modeling of interval-censored data—this paper proposes IC-Mamba, the first temporal forecasting model to embed interval-censoring modeling within a state-space framework. Specifically designed for fine-grained engagement prediction (likes, shares, comments, reactions) within 15–30 minutes post-publication, IC-Mamba integrates multi-task learning with dynamic temporal embeddings. It supports both cross-scale forecasting (from 3–10-day observation windows to 28-day long-term predictions) and narrative-level (F1 = 0.508–0.751) and stance-level engagement prediction. Experiments demonstrate an RMSE of 0.118–0.143, achieving a 4.72% average improvement over state-of-the-art methods. This advancement significantly enhances the timeliness and accuracy of early false information identification and intervention.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In today's digital age, conspiracies and information campaigns can emerge rapidly and erode social and democratic cohesion. While recent deep learning approaches have made progress in modeling engagement through language and propagation models, they struggle with irregularly sampled data and early trajectory assessment. We present IC-Mamba, a novel state space model that forecasts social media engagement by modeling interval-censored data with integrated temporal embeddings. Our model excels at predicting engagement patterns within the crucial first 15-30 minutes of posting (RMSE 0.118-0.143), enabling rapid assessment of content reach. By incorporating interval-censored modeling into the state space framework, IC-Mamba captures fine-grained temporal dynamics of engagement growth, achieving a 4.72% improvement over state-of-the-art across multiple engagement metrics (likes, shares, comments, and emojis). Our experiments demonstrate IC-Mamba's effectiveness in forecasting both post-level dynamics and broader narrative patterns (F1 0.508-0.751 for narrative-level predictions). The model maintains strong predictive performance across extended time horizons, successfully forecasting opinion-level engagement up to 28 days ahead using observation windows of 3-10 days. These capabilities enable earlier identification of potentially problematic content, providing crucial lead time for designing and implementing countermeasures. Code is available at: https://github.com/ltian678/ic-mamba. An interactive dashboard demonstrating our results is available at: https://ic-mamba.behavioral-ds.science.

Problem

• Predicts social media engagement early.
• Handles irregularly sampled data effectively.
• Identifies problematic content quickly.

Innovation

• State space model for engagement prediction
• Interval-censored data temporal embeddings
• Early trajectory assessment in misinformation