Folksonomication: Predicting Tags for Movies from Plot Synopses using Emotion Flow Encoded Neural Network

Proceedings of the 27th International Conference on Computational Linguistics, pages 2879–2891 Santa Fe, New Mexico, USA, August 20-26, 2018. 2879 Folksonomication: Predicting Tags for Movies from Plot Synopses Using Emotion Flow Encoded Neural Network Sudipta Kar Suraj Maharjan Thamar Solorio Department of Computer Science University of Houston Houston, TX 77204-3010 {skar3, smaharjan2, tsolorio}@uh.edu Abstract Folksonomy of movies covers a wide range of heterogeneous information about movies, like the genre, plot structure, visual experiences, soundtracks, metadata, and emotional experiences from watching a movie. Being able to automatically generate or predict tags for movies can help recommendation engines improve retrieval of similar movies, and help viewers know what to expect from a movie in advance. In this work, we explore the problem of creating tags for movies from plot synopses. We propose a novel neural network model that merges information from synopses and emotion flows throughout the plots to predict a set of tags for movies. We compare our system with multiple baselines and found that the addition of emotion flows boosts the performance of the network by learning ≈18% more tags than a traditional machine learning system. 1 Introduction User generated tags for online items are beneficial for both of the users and content providers in modern web technologies. For instance, the capability of tags in providing a quick glimpse of items can assist users to pick items precisely based on their taste and mood. On the other hand, such strength of tags enables them to act as strong search keywords and efficient features for recommendation engines (Lam- biotte and Ausloos, 2006; Szomszor et al., 2007; Li et al., 2008; Borne, 2013). As a result, websites for different medias like photography1, literature2, film3, and music4 have adopted this system to make information retrieval easier. Such systems are often referred as Folksonomy (Vander Wal, 2005), social tagging, or collaborative tagging. In movie review websites, it is very common that people assign tags to movies after watching them. Tags for movies often represent summarized characteristics of the movies such as emotional experiences, events, genre, character types, and psychological impacts. As a consequence, tags for movies became re- markably convenient for recommending movies to potential viewers based on their personal preferences and user profiles. However, this situation is not the same for all of the movies. Popular movies usually have a lot of tags as they tend to reach a higher number of users in these sites. On the other hand, low profile movies that fail to reach such an audience have very small or empty tagsets. In an investigation, we found that ≈34% of the movies among the top ≈130K movies of 22 genres5 in IMDB do not have any tag at all. It is very likely that lack of descriptive tags negatively affects chances of movies being discovered. An automatic process to create tags for movies by analyzing the written plot synopses or scripts could help solve this problem. Such a process would reduce the dependency on humans to accumulate tags This …

Content truncated to 500 words