Examining the Limitations of Computational Rumor Detection Models Trained on Static Datasets
This work addresses the problem of poor generalization in rumor detection for social media platforms, but it is incremental as it focuses on evaluating existing model types rather than introducing new methods.
The paper examined the generalization limitations of rumor detection models, finding that both content-based and context-based models struggle with detecting new, unseen rumors due to over-reliance on source posts and inadequate use of contextual information, and provided practical suggestions to mitigate temporal concept drift in static datasets.
A crucial aspect of a rumor detection model is its ability to generalize, particularly its ability to detect emerging, previously unknown rumors. Past research has indicated that content-based (i.e., using solely source posts as input) rumor detection models tend to perform less effectively on unseen rumors. At the same time, the potential of context-based models remains largely untapped. The main contribution of this paper is in the in-depth evaluation of the performance gap between content and context-based models specifically on detecting new, unseen rumors. Our empirical findings demonstrate that context-based models are still overly dependent on the information derived from the rumors' source post and tend to overlook the significant role that contextual information can play. We also study the effect of data split strategies on classifier performance. Based on our experimental results, the paper also offers practical suggestions on how to minimize the effects of temporal concept drift in static datasets during the training of rumor detection methods.