MMoE: Robust Spoiler Detection with Multi-modal Information and Domain-aware Mixture-of-Experts

TL;DR

This paper introduces MMoE, a multi-modal neural network that leverages heterogeneous data sources and a mixture-of-experts architecture to improve the robustness and domain generalization of spoiler detection in online movie reviews.

Contribution

The paper proposes MMoE, a novel multi-modal and domain-aware model that integrates graph, text, and metadata features for more effective spoiler detection across genres.

Findings

Achieves state-of-the-art accuracy and F1-score on two datasets.

Outperforms previous methods by 2.56% and 8.41%.

Demonstrates superior robustness and generalization capabilities.

Abstract

Online movie review websites are valuable for information and discussion about movies. However, the massive spoiler reviews detract from the movie-watching experience, making spoiler detection an important task. Previous methods simply focus on reviews' text content, ignoring the heterogeneity of information in the platform. For instance, the metadata and the corresponding user's information of a review could be helpful. Besides, the spoiler language of movie reviews tends to be genre-specific, thus posing a domain generalization challenge for existing methods. To this end, we propose MMoE, a multi-modal network that utilizes information from multiple modalities to facilitate robust spoiler detection and adopts Mixture-of-Experts to enhance domain generalization. MMoE first extracts graph, text, and meta feature from the user-movie network, the review's textual content, and the review's metadata respectively. To handle genre-specific spoilers, we then adopt Mixture-of-Experts architecture to process information in three modalities to promote robustness. Finally, we use an expert fusion layer to integrate the features from different perspectives and make predictions based on the fused embedding. Experiments demonstrate that MMoE achieves state-of-the-art performance on two widely-used spoiler detection datasets, surpassing previous SOTA methods by 2.56% and 8.41% in terms of accuracy and F1-score. Further experiments also demonstrate MMoE's superiority in robustness and generalization. Our code is available at https://github.com/zzqbjt/Spoiler-Detection.