Abstract

An area of artificial intelligence known as sentiment analysis focuses on interpreting data to convey human feelings and opinions. This paper focuses on the IMDB movie review sentiment analysis, and Stanford University provided the dataset. We analyse how the viewer articulates their positive or negative opinion. Because, at this time, we don't have an accurate system that can frame the structures in the study of random slang movies, the N-gram method was used. Along with that, we make a selection of standard features and use them for training multiple-label classifiers to tag reviews of movies accurately and further, choosing the most suitable classifier for our domain query by various categories approach comparison. Our process, which makes use of separation techniques, is 83% accurate.

References

1. NLTK: The Natural Language Toolkit. Edward Loper and Steven Bird Department of Computer and Information Science University of Pennsylvania, Philadelphia, PA 19104-6389, USA
2. Steven Bird NLTK Documentation Release 3.2.5. (English) Sep 28, 2017
3. Edward Loper,Steven Bird, NLTK: the natural language toolkit, Proceedings of the ACL 2004 on Interactive poster and demonstration sessions, p.31-es, July 21-26, 2004, Barcelona, Spain
4. Naive Bayes Scikit-Learnn.org. (English) Sep 28, 2017
5. Cortes, Corinna;Vapnik,VladimirN.(1995).'Support-vectornetworks'.Machine Learning. 20 (3): 273–297. CiteSeerX 10.1.1.15.9362
6. Guerini Marco Lorenzo Gatti Marco Turchi Sentiment analysis: How to derive prior polarities from SentiWordN et vol. 5843 2013.
7. Bhoir Purtata Shilpa Kolte 'Sentiment analysis of movie reviews using lexicon approach' 2015 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) pp. 1-6 2015.

Download PDF
Back