The Impact of Fake Reviews on Sentiment Analysis of IMDB Movie Reviews

Oluwatobi Abayomi Badmus

doi:10.22161/eec.105.1

Indexing and Abstracting

The Impact of Fake Reviews on Sentiment Analysis of IMDB Movie Reviews

Oluwatobi Abayomi Badmus

International Journal of Electrical, Electronics and Computers (IJECC), Vol-10,Issue-5, July - August 2025, Pages 1-19, 10.22161/eec.105.1

Download | Downloads : 4 | Total View : 1379

Article Info: Received: 30 May 2025; Accepted: 29 Jun 2025; Date of Publication: 06 Jul 2025

Abstract:

The objective of this work is to discuss the challenges and introduce techniques that are able to find and reduce distortions caused by fake or biased reviews in applying sentiment analysis to IMDb movie reviews. Sentiment analysis requires authentic user-generated content in order to obtain real insights into public opinion. The presence of fake reviews, in other words, intentionally misleading or exaggerated content, introduces noise and distorts the results of this analysis, degrading model accuracy. This paper presents a quantitative approach to the detection of fake reviews based on features about review length, extremity of sentiment expressed, and user behavior. Effective machine learning classifiers, such as Support Vector Machines and Random Forests, were assessed in order to classify genuine versus fake reviews. This work also explores MTL approaches coupling the task of Sentiment Analysis with that of fake review detection in order to enhance the robustness of models. From the experimental results, it could be seen that the inclusion of fake review detection increased the accuracy of sentiment analysis by reducing the error rate; therefore, it offers a more reliable interpretation of the IMDb review data. The results also point out the importance of considering the authenticity of reviews within the text in applications of sentiment analysis by providing a basis for higher-order methods in the treatment of user-generated content.

Keywords:

Sentiment Analysis, Fake Reviews, IMDb, Machine Learning, Review Authenticity

References:

[1] Ahmad, I., Qamar, S., & Adnan, A. (2017). Application of artificial neural network in predicting performance of students: A meta-analysis. Education Research International, 2017.
[2] Ahmad, I., Ting, I.-H., & Salim, N. (2017). Sentiment analysis techniques in recent years. Journal of Data Science, 15(1), 15–31.
[3] Ahmad, S., Aftab, S., & Ali, I. (2017). Sentiment analysis of tweets using SVM. International Journal of Computer Applications, 177(5), 25–29.
[4] Bird, S., Klein, E., & Loper, E. (2009). Natural Language Processing with Python: Analyzing text with the Natural Language Toolkit. O'Reilly Media.
[5] Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 NAACL-HLT.
[6] Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
[7] Kumar, R., & Jaiswal, A. (2021). Preprocessing techniques for sentiment analysis. International Journal of Data Science and Analytics, 9(3), 22–33.
[8] Li, J., Ma, H., Zhang, M., & Liu, Y. (2020). Fake review detection via modeling temporal and behavioral patterns. IEEE Transactions on Neural Networks and Learning Systems.
[9] Liu, B. (2012). Sentiment analysis and opinion mining. Morgan & Claypool Publishers.
[10] Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.
[11] Mukherjee, A., Liu, B., & Glance, N. (2013). Spotting fake reviewer groups in consumer reviews. Proceedings of the 22nd International Conference on World Wide Web.
[12] Moussa, M., Farah, J., & Herre, J. (2018). Movie reviews sentiment analysis using machine learning and NLP. Computational Linguistics Journal, 10(2), 45–67.
[13] Moussa, S. E., Ahmad, A. S., & Hassan, A. A. (2018). IMDb movie reviews for sentiment analysis using machine learning. Journal of Web Development and Web Designing, 3(3), 1–8.
[14] Ortigosa, A., Martín, J. M., & Carro, R. M. (2014). Sentiment analysis in Facebook and its application to e-learning. Computers in Human Behavior, 31, 527–531.
[15] Pennington, J., Socher, R., & Manning, C. D. (2014). GloVe: Global vectors for word representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1532–1543.
[16] Saito, T., & Rehmsmeier, M. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PloS ONE, 10(3), e0118432.
[17] Santos, A., & Gatti, M. (2014). Deep convolutional neural networks for sentiment analysis of short texts. Proceedings of the ACL Workshop on Language Technologies for the Socio-Political Sphere, 23–29.
[18] Santos, V. B., & Gatti, M. (2014). Deep convolutional neural networks for sentiment analysis of short texts. Proceedings of the International Conference on Web Intelligence, Mining, and Semantics, 1(1), 21.
[19] Singh, S., & Bansal, S. (2022). Heuristic approaches for fake review detection: A comparative analysis. Journal of Applied Linguistics and Computational Methods, 18(1), 10–24.
[20] Stine, M. (2019). Sentiment analysis of IMDb reviews: Methods, results, and applications. Journal of Film and Digital Media Analysis, 5(2), 30–45.
[21] Stine, T. (2019). Machine learning for fake review detection. Journal of Data Science and Artificial Intelligence, 7(2), 113–120.
[22] Taprial, V., & Kanwar, P. (2012). Understanding social media. Booktango.

International Journal Of Electrical, Electronics And Computers(IJEEC)

For Authors

Issues

Downloads

Indexing and Abstracting

The Impact of Fake Reviews on Sentiment Analysis of IMDB Movie Reviews

Abstract:

Keywords:

References: