Innovations in Computer Science and Engineering | 2021
Effect of J48 and LMT Algorithms to Classify Movies in the Web—A Comparative Approach
Abstract
Social Media websites such as Facebook, YouTube, twitter, etc., are the convenient platforms to share one’s views about the multimedia. Videos getting uploaded on YouTube every day are millions in number. Videos can be of different category such as comedy video, sports video, news, advertisement, movie trailer video, etc. Nowadays, data mining researchers are attracted towards different classification techniques of data mining to discover hidden information as well as to discover knowledge from huge video data. The goal of this research is, classifying and predicting movies trailer videos as poor movie, good movie, very good movie and excellent movie based on the meta data such as likes, dislikes, comments, ratings, budget, etc. An attempt is made in the present work to provide an effective mining result about classifying Social Media movies. These movies are labelled based on a particular class and other related attributes of the same dataset. 10 folds cross-validation test is applied on J48 and LMT decision tree algorithm, and comparison analysis is made based on confusion matrix and accuracy rate.