2013 Annual Meeting
Montréal, Québec, Canada | November 1-5, 2013
Jordan Boyd-Graber, University of Maryland
Kimberly A. Glasgow, University of Maryland
Jackie S. Zajac, University of Maryland
Spoilers---critical plot information about works of fiction that ``spoil'' a viewer's enjoyment---have prompted elaborate social conventions on social media to allow readers to insulate themselves from spoilers. However, these solutions depend on the contentiousness of Internet posters and are thus an imperfect system. We create an automatic alternative that could alert users when a piece of text contains a spoiler. An automated spoiler detector serves not only as an additional protection against spoilers, but it also contributes to important problems in computational linguistics. We develop a new dataset of spoilers gathered from social media and create automatic classifiers using machine learning techniques. After establishing baseline performance using lexical features, we develop metadata-based features that substantially improve performance on the spoiler detection task.