Open AccessCombining support vector machine with radial basis function kernel and information gain for sentiment analysis of movie reviews
Author(s) -
Zaheera Zainal Abidin,
W Destian,
Rahila Umer
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1918/4/042157
Subject(s) - support vector machine , radial basis function kernel , sentiment analysis , radial basis function , computer science , artificial intelligence , benchmark (surveying) , feature selection , kernel (algebra) , selection (genetic algorithm) , pattern recognition (psychology) , machine learning , feature (linguistics) , function (biology) , basis (linear algebra) , data mining , kernel method , mathematics , artificial neural network , geography , linguistics , philosophy , geometry , geodesy , combinatorics , evolutionary biology , biology
A movie review can be considered as an essential data source for both movie producers and potential consumers. The reviews are usually used as a benchmark for knowing the movie’s quality and are utilized as references to whether the film is worth watching. The study of sentiment analysis has received more attention from researchers. This current study aims to classify the sentiment analysis of movie reviews obtained from the IMDb site. The support vector machine (SVM) method was employed to classify the movie review’s sentiments. Meanwhile, the radial basis function (RBF) kernel and information gain (IG) were used to enhance classification. Feature selection was conducted by removing irrelevant features and selecting features with a strong correlation to classification. The IG algorithm was used for feature selection. The current study revealed that the classification accuracy of movie review sentiment analysis using the SVM algorithm, SVM + RBF kernel, and SVM+RBF Kernel+IG are 81.50%, 82.25%, and 87.25%, respectively.