Fine-Grained Spoiler Detection from Large-Scale Review Corpora
This addresses spoiler detection for media consumers and platforms, though it is incremental as it builds on existing computational approaches.
The paper tackled the problem of automatically detecting plot twist spoilers in book reviews by creating a large-scale annotated dataset and developing a neural network architecture, achieving substantial performance improvements over existing baselines.
This paper presents computational approaches for automatically detecting critical plot twists in reviews of media products. First, we created a large-scale book review dataset that includes fine-grained spoiler annotations at the sentence-level, as well as book and (anonymized) user information. Second, we carefully analyzed this dataset, and found that: spoiler language tends to be book-specific; spoiler distributions vary greatly across books and review authors; and spoiler sentences tend to jointly appear in the latter part of reviews. Third, inspired by these findings, we developed an end-to-end neural network architecture to detect spoiler sentences in review corpora. Quantitative and qualitative results demonstrate that the proposed method substantially outperforms existing baselines.