EUVIMEDEUVIMED entdecken
Open Access · CC BY-ND 4.0

A Comparative Study of Machine Learning Models for Sentiment Analysis of IMDb Movie Reviews

Anchal Verma, Sakshi Sharma, Vrinda Swarup, Preeti Tuli

International Journal on Advanced Computer Theory and Engineering · 25.05.2026 · 15 (1) · 242-248

DOI: 10.65521/ijacte.v15i1.3815 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal on Advanced Computer Theory and Engineering, online erschienen am 25.05.2026. Verfasst von Anchal Verma und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid growth of online platforms has resulted in an enormous volume of user-generated textual data, making automated sentiment analysis an essential task in Natural Language Processing (NLP). Movie review platforms such as IMDb generate large-scale opinionated text that provides valuable insights into audience perception, but manual analysis of such data is impractical. This project presents a comprehensive comparative study of classical machine learning and deep learning models for sentiment analysis of IMDb movie reviews.The proposed system implements a unified experimental framework in which classical machine learning models—Logistic Regression, Naïve Bayes, Support Vector Machine, and Random Forest—are compared against deep learning models including TextCNN, LSTM, BiLSTM, and LSTM with Attention. Classical models utilize TF-IDF based feature representation, while deep learning models rely on embedding-based sequence learning. All models are evaluated under identical preprocessing and testing conditions to ensure fairness and reproducibility. Performance evaluation is carried out using multiple metrics such as classification accuracy, training time, inference time, and model complexity. Experimental results reveal that classical machine learning models, particularly Logistic Regression and Linear SVM, achieve accuracy comparable to or higher than deep learning models while requiring significantly fewer computational resources. Among deep learning approaches, TextCNN demonstrates the best balance between accuracy and efficiency. The study highlights that increased model complexity does not necessarily guarantee superior performance.The findings of this research emphasize the importance of considering computational efficiency and deployment constraints alongside accuracy. This work provides practical guidelines for selecting suitable sentiment analysis models based on application requirements and resource availability, making it valuable for both academic research and real-world applications

Zitieren

APA

Verma, A., Sharma, S., Swarup, V., & Tuli, P. (2026). A Comparative Study of Machine Learning Models for Sentiment Analysis of IMDb Movie Reviews. International Journal on Advanced Computer Theory and Engineering, 15(1), 242-248. https://doi.org/10.65521/ijacte.v15i1.3815

Vancouver

Verma A, Sharma S, Swarup V, Tuli P. A Comparative Study of Machine Learning Models for Sentiment Analysis of IMDb Movie Reviews. International Journal on Advanced Computer Theory and Engineering. 2026;15(1):242-248. doi:10.65521/ijacte.v15i1.3815

BibTeX
@article{Verma2026,
  author = {Verma, Anchal and Sharma, Sakshi and Swarup, Vrinda and Tuli, Preeti},
  title = {A Comparative Study of Machine Learning Models for Sentiment Analysis of IMDb Movie Reviews},
  journal = {International Journal on Advanced Computer Theory and Engineering},
  year = {2026},
  volume = {15},
  number = {1},
  pages = {242--248},
  doi = {10.65521/ijacte.v15i1.3815}
}
Kostenlos starten →