A DATA MINING APPROACH TO LANGUAGE SUCCESS PREDICTION OF A FEATURE FILM

The paper aims to develop a tool, which can predict the success of movie being a hit or flop. As this factor is important for everyone involved in the movie, for example : If a movie is flop, it exacerbates the image of actor or director. The tool will use searching algorithms and then use of bespoke system to predict the percentage of success of movie which is yet to be released. This paper details our analysis of the data collected from various resources like IMDb, Kaggle. We gather a series of interesting facts and relationships using a variety of data mining techniques such as Bayes Classification Algorithm, Decision Tree etc. Subsequently, a classifier is learned and used to classify new movies with respect to their predicted box-office collection. Experimental results show that the proposed approach improves the classification accuracy as compared to a fully independent setting . In particular, we discover the rate of success with respect to various parameters such as language, country, budget, Facebook likes of the actors and actresses etc and focus on relevant details such as the relationship between the budget of the movie and rating of the movie, language and rating, facebook likes and rating etc. The data mining techniques used will enable us to uncover information which will both confirm or disprove common assumptions about movies, and also allow us to predict the success of a future film given select information about the film before its release