Sentiment Analysis of IMDb Movie Reviews Using Long Short-Term Memory
Author:
- 13 October 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Abstract
The sentiment analysis is an emerging research area where vast amount of data are being analyzed, to generate useful insights in regards to a specific topic. It is an effective tool which can serve governments, corporations and even consumers. Text emotion recognizing lays a key role in this framework. Researchers in the fields of natural language processing (NLP) and machine learning (ML) have explored a variety of methods to implement the process with highest accuracy possible. In this paper the Long Short-Term Memory (LSTM) classifier is used for analyzing sentiments of the IMDb movie reviews. It is based on the Recurrent Neural Network (RNN) algorithm. The data is effectively preprocessed and partitioned to enhance the post classification performance. The classification performance is studied in terms of accuracy. Results show a best classification accuracy of 89.9%. It confirms the potential of integrating the designed solution in modern text based sentiments analyzers.Keywords
This publication has 7 references indexed in Scilit:
- Analyzing Performance of Different Machine Learning Approaches With Doc2vec for Classifying Sentiment of Bengali Natural Language2019
- Emotion detection from text and speech: a surveySocial Network Analysis and Mining, 2018
- Lexicon based feature extraction for emotion text classificationPattern Recognition Letters, 2017
- A multiobjective weighted voting ensemble classifier based on differential evolution algorithm for text sentiment classificationExpert Systems with Applications, 2016
- Sentiment Analysis using Support Vector Machine based on Feature Selection and Semantic AnalysisInternational Journal of Computer Applications, 2016
- Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification2016
- An Analysis for Unreplicated Fractional FactorialsTechnometrics, 1986