Sentiment Classification for Film Reviews in Gujarati Text Using Machine Learning and Sentiment Lexicons

Sentiment Classification for Film Reviews in Gujarati Text Using Machine Learning and Sentiment Lexicons

Gujarati text; lexicon; machine classifier; movie reviews; sentiment analysis

In this paper, two techniques for sentiment classification are proposed: Gujarati Lexicon Sentiment Analysis (GLSA) and Gujarati Machine Learning Sentiment Analysis (GMLSA) for sentiment classification of Gujarati text film reviews. Five differentdatasets were produced to validate the machine learning-basedand lexicon-based methods’accuracy. The lexicon-based approach employs a sentiment lexiconknown as GujSentiWordNet, which identifies sentiments with a sentiment score for feature generation, whilein the machine learning-based approach, five classifiers are used: logistic regression (LR), random forest (RF), k-nearestneighbors(KNN), support vector machine (SVM), naive Bayes (NB) with TF-IDF,and count vectorizer forfeature selection. Experiments were carried outand the results obtained were compared using accuracy, precision, recall, and F-score as performance evaluation criteria. According to the testresults, the machine learning-based technique improvedaccuracy by 3to 10% on average when compared to the lexicon-based approach

Parita Shah1,* Priya Swaminarayan2&Maitri Patel3

https://journals.itb.ac.id/index.php/jictra/article/view/17631/6149

Vidush Somany Institute of Technology and Research, Kadi, India

6 September 2022

Fajar bagus W

PDF

English

Text