מרק לסט

Story types depict the development of movie stories in terms of the protagonist's character traits and the motivations that drive him in facing his challenges. We define a novel task of story type classification of movies and propose a lightweight machine learning solution. A crowdsourcing experiment was performed to label 45 movies for their perceived story types. We extract movie features that indicate different aspects of the movie characters and apply Decision Tree and Naive Bayes classification algorithms. Although the labeled dataset is relatively small, the story type classification accuracy is significantly above the baseline with the F1 measure in the range of [0.63-0.77]. The preliminary results suggest that simple movie features can be used by machine learning algorithms to detect the abstract concepts of story types.