ReINTEL Challenge 2020: A Multimodal Ensemble Model for Detecting Unreliable Information on Vietnamese SNS
This work provides a competitive solution for identifying unreliable information on Vietnamese social media, which is a domain-specific problem for social media users and platforms.
The paper addresses the task of classifying information as reliable or unreliable on Vietnamese social networks. Their proposed multimodal ensemble model achieved an ROC AUC score of 0.9445 on the private test set of the ReINTEL Challenge 2020.
In this paper, we present our methods for unrealiable information identification task at VLSP 2020 ReINTEL Challenge. The task is to classify a piece of information into reliable or unreliable category. We propose a novel multimodal ensemble model which combines two multimodal models to solve the task. In each multimodal model, we combined feature representations acquired from three different data types: texts, images, and metadata. Multimodal features are derived from three neural networks and fused for classification. Experimental results showed that our proposed multimodal ensemble model improved against single models in term of ROC AUC score. We obtained 0.9445 AUC score on the private test of the challenge.