Sentiment Analysis on IMDb Movie Reviews Using Hybrid Feature Extraction Method

Abstract

Social Networking sites have become popular and common places for sharing wide range of emotions through short texts. These emotions include happiness, sadness, anxiety, fear, etc. Analyzing short texts helps in identifying the sentiment expressed by the crowd. Sentiment Analysis on IMDb movie reviews identifies the overall sentiment or opinion expressed by a reviewer towards a movie. Many researchers are working on pruning the sentiment analysis model that clearly identifies and distinguishes between a positive review and a negative review. In the proposed work, we show that the use of Hybrid features obtained by concatenating Machine Learning features (TF, TF-IDF) with Lexicon features (Positive-Negative word count, Connotation) gives better results both in terms of accuracy and complexity when tested against classifiers like SVM, Naïve Bayes, KNN and Maximum Entropy. The proposed model clearly differentiates between a positive review and negative review. Since understanding the context of the reviews plays an important role in classification, using hybrid features helps in capturing the context of the movie reviews and hence increases the accuracy of classification.

How students emerge as learning leaders in small group online discussions

“…We used text messages in discussion boards as a proxy for determining students' emotions (Dehkharghani, 2018;Kumar, Harish, & Darshan, 2019;Garcia-Garcia, Penichet, & Lozano, 2017). In the context of online discussions, learning leaders use their text messages to express their emotions as well as recognize and respond to others' emotions (Author, 2019b).…”

Sentiment analysis on IMDB using lexicon and neural networks

“…Sentiment analysis is the technique of identifying significant and individual data from a collection of source materials that contain unacknowledged information of people's perspectives [1]. People usually go over blogs, social networking Web sites like Facebook and Twitter and review sites like IMDB and rotten tomatoes to know about the cast and crew of the movie, review, and ratings [2]. To automate the organization and categorization of sentiment from sentiments reviews, sentiment analysis uses text analysis, natural language processing (NLP), and computational techniques [3].…”

Feature-Level Sentiment Analysis Based on Rules and Fine-Grained Domain Ontology

“…Mining and utilizing these reviews are of great significance By analyzing the sentiment of user reviews, website operators or merchants can analyze the pros and cons of a product, speculate on users' preferences to develop a reasonable marketing strategy, and propose plans to improve the product's reputation and profitability. Producers of literary works such as movies (Kumar et al 2019) and the tourism industry (Afzaal et al 2019) can also understand popular trends and users' perceptions for the works. These reviews, which reflect users' opinions and sentimental tendencies, are increasingly of great value.…”