Predicting the Genre and Rating of a Movie Based on its Synopsis

Predicting the Genre and Rating of a Movie Based on its Synopsis Varshit Battu, Vishal Batchu, Rama Rohit Reddy, Murali Krishna Reddy, Radhika Mamidi International Institute of Information Technology Hyderabad {battu.varshit, ramarohitreddy.g, murali.dakannagari}@research.iiit.ac.in vishal.batchu@students.iiit.ac.in radhika.mamidi@iiit.ac.in Abstract Movies are one of the most prominent means of entertainment. The widespread use of the Internet in recent times has led to large vol- umes of data related to movies being gener- ated and shared online. People often prefer to express their views online in English as com- pared to other local languages. This leaves us with a very little amount of data in languages apart from English to work on. To overcome this, we created the Multi-Language Movie Review Dataset (MLMRD). The dataset con- sists of genre, rating, and synopsis of a movie across multiple languages, namely Hindi, Tel- ugu, Tamil, Malayalam, Korean, French, and Japanese. The genre of a movie can be iden- tified by its synopsis. Though the rating of a movie may depend on multiple factors like the performance of actors, screenplay, direction etc but in most of the cases, synopsis plays a crucial role in the movie rating. In this work, we provide various model architectures that can be used to predict the genre and the rating of a movie across various languages present in our dataset based on the synopsis. 1 Introduction As the amount of data present online increases expo- nentially day by day, we have reached a point where a human cannot comprehend all of it in a meaning- ful manner due to its sheer size. This lead to work on automated recommender systems. The main is- sue with these kinds of methods is that not all the information is present online and all the information present need not be correct. Automated movie genre and rating prediction have a lot of applications. We can recommend same genre movies based on his previous watch history. Genre of a movie can be identified by its synopsis. Recommending a movie only based on its genre is not a good idea as the same genre can have both good and bad movies. So Rec- ommending movies based on both genre and rating would result in a proper recommendation system. But the main problem here is that people do not often tend to rate the movie they watch, thus automated rating prediction would be of great help for recom- mendation systems. Though the rating of a movie depends on multiple factors like actors, screenplay, direction etc. but that information is very difficult to capture through available data. In most of the cases, synopsis of the movie plays a crucial impact on audience rating. In this paper, we propose multi- ple deep-learning based methods to predict the genre and rating of a movie based on its synopsis. There is a very little amount of data in languages apart from English to work on. To overcome this, we created the Multi-Language Movie Review Dataset (MLMRD). The dataset consists of genre, rating, and synopsis …

Content truncated to 500 words