Analyzing Sentiment of Movie Reviews in Bangla by Applying Machine Learning Techniques

Abstract

This paper proposes a process of sentiment analysis of movie reviews written in Bangla language. This process can automate the analysis of audience's reaction towards a specific movie or TV show. With more and more people expressing their opinions openly in the social networking sites, analyzing the sentiment of comments made about a specific movie can indicate how well the movie is being accepted by the general public. The dataset used in this experiment was collected and labeled manually from publicly available comments and posts from social media websites. Using Support Vector Machine algorithm, this model achieves 88.90% accuracy on the test set and by using Long Short Term Memory network [1] the model manages to achieve 82.42% accuracy. Furthermore, a comparison with some other machine learning approaches is presented in this paper.

Text Mining and Sentiment Analysis of Newspaper Headlines

“…Similarly, several proposed algorithms for Bangla newspaper sentiment analysis have been seen in the literature, including Supervised Machine Learning with Extended Lexicon Dictionary [42], Support Vector Machine (SVM) and Logistic Regression [41,43], Long Short-Term Memory (LSTM) Recurrent Neural Network [44]. Moreover, analyzing cricket supporter sentiment, online shopping reviews (Ismail Siddiqi) [45], microblog posts [46], movie reviews [12], E-commerce business [47] sentiment through text mining approaches have been seen in the literature.…”

“…Another imperative method of analysing the emotions of humans from text is sentiment analysis-a procedure of detecting or defining eight primary emotions of humans and animals, including anger, fear, sadness, disgust, surprise, anticipation, trust, and joy emotions (defined by the eminent psychologist Robert Plutchik) through words. In addition to emotional states, another straightforward approach is the polarity of a document, which develops the method of detecting polarity, particularly positive and negative explication, through distinct algorithms [12][13][14]. Moreover, the adaptation of this analysis led businesses to accumulate people's opinions to determine their following business policy and political parties to manipulate people through election strategies, newspapers, Twitter, Facebook, and blogs, along with the application to novels, movie reviews, and product reviews [15][16][17].…”

“…Moreover, the adaptation of this analysis led businesses to accumulate people's opinions to determine their following business policy and political parties to manipulate people through election strategies, newspapers, Twitter, Facebook, and blogs, along with the application to novels, movie reviews, and product reviews [15][16][17]. Similar to the word cloud, sentiment analysis concedes constraints, such as the number of data sets, measurements, distinct meanings for identical text, different languages, shortcut words written by the author, typing mistakes, and the rhetoric of writing [1,12,18]. However, besides these problems, sentiment analyses are still recognized as one of the most precise techniques to analyse texts in terms of emotion, where lexiconbased analysis techniques are primarily used [13].…”

Classification of Textual Sentiment Using Ensemble Technique

“…The developed ensemble model is compared with the three available methods [6,13,24] of sentiment classification in Bengali concerning three datasets. Figure 4b illustrates the results of the comparison.…”

“…5a). The confusion matrices of the existing methods [6,13,24] on BSaD are also presented in Fig. 5b-d techniques can be investigated with more diverse data to improve the system's predictive accuracy.…”