TL;DR
This paper introduces a high-quality dataset of movie reviews containing spoilers, aiming to facilitate research on automatic spoiler detection in user-generated media reviews.
Contribution
It provides a new, curated dataset specifically designed for developing and evaluating spoiler detection methods in movie reviews.
Findings
Dataset enables effective training of spoiler detection models
Preliminary experiments show promising results in identifying spoilers
Dataset covers diverse genres and spoiler types
Abstract
User-generated reviews are often our first point of contact when we consider watching a movie or a TV show. However, beyond telling us the qualitative aspects of the media we want to consume, reviews may inevitably contain undesired revelatory information (i.e. 'spoilers') such as the surprising fate of a character in a movie, or the identity of a murderer in a crime-suspense movie, etc. In this paper, we present a high-quality movie-review based spoiler dataset to tackle the problem of spoiler detection and describe various research questions it can answer.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Analysis and Summarization · Digital Media Forensic Detection · Generative Adversarial Networks and Image Synthesis