Cross-Lingual Cross-Platform Rumor Verification Pivoting on Multimedia Content
This addresses the challenge of automated rumor detection for social media users and platforms, but it is incremental as it builds on existing verification methods by introducing new features.
The paper tackled the problem of verifying rumors with multimedia content on social networks by proposing a method that finds external information from other news platforms based on multimedia, rather than using multimedia as input features. The approach achieved state-of-the-art results in rumor verification.
With the increasing popularity of smart devices, rumors with multimedia content become more and more common on social networks. The multimedia information usually makes rumors look more convincing. Therefore, finding an automatic approach to verify rumors with multimedia content is a pressing task. Previous rumor verification research only utilizes multimedia as input features. We propose not to use the multimedia content but to find external information in other news platforms pivoting on it. We introduce a new features set, cross-lingual cross-platform features that leverage the semantic similarity between the rumors and the external information. When implemented, machine learning methods utilizing such features achieved the state-of-the-art rumor verification results.