Total views : 181
Opinion Mining and Analysis of Movie Reviews
Background/Objective: Customer reviews are important for various fields (e.g. Movies,Products, Services). Moviereviews plays vital role in describing its success and failure. People have now become very specific on what movies to watch and what not to watch. Hence people don't want to waste time on a movie that has bad reviews. Nowadaysonline reviews are important for personal recommendation. Methods/Statistical Analysis: There are various works done on opinion mining and text mining. This paper focuses on analyzing sentiment from semantic orientation of words that occur in a text by manually defining dictionary for positive, negative and intensifier words stored in different text file. In this method we extract data from three different sources. Opinions that has to be analyzed is preprocessed and stored in text file. The data are then compared with our bag of words in order to find the number of positive and negative sentiments in the reviews of that particular movie. To predict movie rating three machine learning algorithms have been used to create three different classifier using a trained data set. Findings: After rating prediction, the accuracy of each classifier is calculated on the data set containing predicted rating of various movies given by each classifier. Out of all three machine learning algorithms used, Naive Bayes is found to be more accurate than Decision Tree and K Nearest Neighbour algorithm. Improvements: There can be more many ways where we understand how the users write reviews as the reviews only support English language. Hence we can also bring in multiple languages, so that we do not even miss out on a single review. Most of the time,a single user may not provide review for all the movies. So, our database will resemble a sparse matrix. A prediction algorithm may be designed to mathematically guess the rating for movies that are not originally reviewed by the user.
Machine Learning, Opinion Mining, Sentiment Analysis, Text Mining.
- Hajmohammadi MS, Ibrahim R, Ali Othman Z. Opinion mining and sentiment analysis survey. International Journal of Computers and Technology. 2012; 2(3):171–8.
- Vinodhini G, Chandrasekaran RM. Sentiment analysis and opinion mining. International Journal of Advanced Research in Computer Scienceand Software Engineering. 2012; 2 (6): 282–92.
- Virmani D, Malhotra V, Tyagi R. Sentiment analysis using collaborated opinion mining. Cornell University Library; 2014.
- Goyal A, Parulekar A. Sentiment analysis or movie reviews. Semantic Scholar. 2015.
- Andrew LM, Raymoi ED, Peter TP, Huang D, Ng AY, Potts C. Learning word vectors for sentiment analysis. ACM Publications. 2011; 1: 142–50.
- Amolik A, Jivane N, Bhandari M, Venkatesan M. Twitter sentiment analysis of movie reviews using machine learning techniques. International Journal of Engineering and Technology. 2016; 7 (6): 1–7.
- Kolchanya O, Souza TPT. Twitter sentiment analysis lexicon method machine learning method and their combination. Cornell University Library. 2015; 1: 1–32.
- Agarwal A, iXie B, Vovsha, Rambow O, Passonneau R. Sentiment analysis of Twitter data. ACM Publications; 2011.p. 30–8.
- Portugal I, Alencar P, Cowan D. The use of machine learning algorithms in recommender systems. A systematic review. Cornell UniversityLibrary. 2015; 1: 1–16.
- Gao M. Application of machine learning techniques to recommendation system. eScholarship University of California; 2015.
- Zang T, Iyenagar SV. Recommender systems using linear classifiers. Journal of Machine Learning Research. 2002; 2: 313–34.
- Khairnar J, Kinikar M. Machine learning algorithms for opinion mining and sentiment classification. International Journal of Scientific and Research Publications. 2013; 3(6): 274–609.
- Latif MH, Afzal H. Prediction of movies popularity using machine learning techniques. International Journal of Computer Science and Network Security. 2016; 16(8): 1–5.
- Mladen MaroviÂt’c, Marko Mihokovi. Automatic movie ratings prediction using machine learning. IEEE Conference Publications. 2011.p. 1640–45.
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.