🤖 AI Summary
In the digital age, “infodemics” proliferate, necessitating lightweight, interpretable, and content-agnostic methods for information quality assessment. To address this, we propose a diffusion-based framework grounded in three propagation dynamics principles—diversity, timeliness, and salience—enabling non-intrusive, cross-domain information quality evaluation without accessing content. In academic publishing, we construct heterogeneous paper diffusion networks and employ generalized additive models (GAMs) for both regression and classification tasks. Experiments demonstrate strong predictive performance: Pearson correlation of 0.8468 for forecasting next-year citation growth, and up to 97.8% accuracy in identifying high-impact papers. This work departs from conventional binary trustworthiness labeling, introducing the first continuous, dynamic, and content-free quantification of information quality—offering both interpretability and scalability.
📝 Abstract
The rapid and unregulated dissemination of information in the digital era has amplified the global "infodemic," complicating the identification of high quality information. We present a lightweight, interpretable and non-invasive framework for assessing information quality based solely on diffusion dynamics, demonstrated here in the context of academic publications. Using a heterogeneous dataset of 29,264 sciences, technology, engineering, mathematics (STEM) and social science papers from ArnetMiner and OpenAlex, we model the diffusion network of each paper as a set of three theoretically motivated features: diversity, timeliness, and salience. A Generalized Additive Model (GAM) trained on these features achieved Pearson correlations of 0.8468 for next-year citation gain and up to 97.8% accuracy in predicting high-impact papers. Feature relevance studies reveal timeliness and salience as the most robust predictors, while diversity offers less stable benefits in the academic setting but may be more informative in social media contexts. The framework's transparency, domain-agnostic design, and minimal feature requirements position it as a scalable tool for global information quality assessment, opening new avenues for moving beyond binary credibility labels toward richer, diffusion-informed evaluation metrics.
