DL based analysis of movie reviews

TL;DR

This paper develops deep learning models, specifically LSTM and CNN, to classify movie reviews from IMDb, achieving high accuracy and demonstrating LSTM's superior performance and efficiency.

Contribution

The study compares LSTM and CNN models for movie review classification, highlighting LSTM's higher accuracy and lower computational cost.

Findings

LSTM achieved 99.2% accuracy in review classification.

CNN achieved 97.4% accuracy.

LSTM outperforms CNN in accuracy and efficiency.

Abstract

Undoubtedly, social media are brainstormed by a tremendous volume of stories, feedback, reviews, and reactions expressed in various languages and idioms, even though some are factually incorrect. These motifs make assessing such data challenging, time-consuming, and vulnerable to misinterpretation. This paper describes a classification model for movie reviews founded on deep learning approaches. Almost 500KB pairs of balanced data from the IMDb movie review databases are employed to train the model. People's perspectives regarding movies were classified using both the long short-term memory (LSTM) and convolutional neural network (CNN) strategies. According to the findings, the CNN algorithm's prediction accuracy rate would be almost 97.4%. Furthermore, the model trained by LSTM resulted in accuracies of around and applying 99.2% within the Keras library. The model is investigated more by modification of model parameters. According to the outcomes, LTSM outperforms CNN in assessing IMDb movie reviews and is computationally less costly than LSTM.