engleski

Sentiment Analysis of Movie Reviews

This paper addresses the problem of sentiment analysis and text sentiment prediction using a weight-oriented method applied on the dataset consisted of movie reviews provided within Kaggle Bag of Words Meets Bags of Popcorns competition. The method utilizes traditional Bag of Words model for vocabulary synthesis and further applies weight-oriented classifier for sentiment prediction. Finally, as different sets of N-grams i.e. unigrams, bigrams and trigrams were used, sentiment prediction accuracy is presented, compared and discussed for optimal approach selection

sentiment analysis, opinion mining, n-grams, weight method

nije evidentirano