A Hybrid Machine Learning and Deep Learning-Based System for Text Sentiment Analysis of Movie Review Classification

DOI

10.2991/978-94-6239-674-6_36How to use a DOI?

Keywords

Sentiment Analysis; NLP; Machine Learning; Deep Learning; XGBoost; CNN; IMDB 50k

Abstract

Sentiment Analysis is a significant NLP task that focuses on identifying polarity (sentiment) and intention for an identifiable piece of textual data. Movie reviews are important in determining whether the movie is successful or unsuccessful. To analyze this unstructured data, we employ newly developed technological algorithms. Machine learning is a transformative technology that is used in practically every industry, with increasingly sophisticated algorithms that provide better, perfect outcomes. Previous research used NLP and ML to extract information from customer reviews. The IMDB 50k movie review dataset is used in this work to perform text sentiment analysis (SA) and assess the model’s performance using hybrid ML and DL approaches. The study focuses on two types of models: the utilizes a hybrid technique combining XGBoost and CNN, also single CNN model. Performance indicators like as f1-score, accuracy, precision, and AUC offer a thorough picture of each model’s performance. Experimental results show that CNN model get 94.21% and hybrid (XGBoost and CNN) achieved 96.59%, respectively, in text SA of IMDB 50k movie reviews. Researchers may use this study to find the optimal method for SA. Hybrid algorithms outperform single models according to accuracy and efficiency when compared to both the current and suggested methods.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Praveen Sharma
AU  - Divyarth Rai
PY  - 2026
DA  - 2026/05/28
TI  - A Hybrid Machine Learning and Deep Learning-Based System for Text Sentiment Analysis of Movie Review Classification
BT  - Proceedings of the International Conference on Sustainable Computing and Artificial Intelligence (ICSCAI 2025)
PB  - Atlantis Press
SP  - 431
EP  - 444
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-674-6_36
DO  - 10.2991/978-94-6239-674-6_36
ID  - Sharma2026
ER  -