Sentiment Analysis using BERT

Rahul Raj Nayak; P.Sakthi Murugan

doi:10.36948/ijfmr.2026.v08i03.78083

Sentiment Analysis using BERT

Author(s)	Mr. Rahul Raj Nayak, Mr. P.Sakthi Murugan
Country	India
Abstract	Sentiment analysis has become a major research area in Natural Language Processing (NLP) due to theincreasing volume of textual data generated through online platforms, movie review systems, and socialmedia applications. Traditional machine learning approaches often fail to capture contextual relationshipsand long-term dependencies within text sequences. Transformer-based architectures such as BidirectionaEncoder Representations from Transformers (BERT) significantly improve contextual understanding through self-attention mechanisms.This research presents a Transformer-based sentiment analysis system using the IMDb Movie ReviewDataset for binary sentiment classification. The proposed model utilizes a pretrained BERT Transformerarchitecture fine-tuned on 50,000 labeled movie reviews. Thesystem performs data preprocessing,tokenization, contextual embedding generation, and sentiment classification using deep learningtechniques.Experimental evaluation demonstrates that the BERT-based model achieves high classification performancewith approximately 91% accuracy, 90% precision, 92% recall, and 91% F1-score. Visualization-basedexploratory data analysis was also performed to understand sentiment distribution, review characteristics,and vocabulary patterns. The findings indicate that Transformer models significantly outperform traditionalNLP models in contextual sentiment understanding and large-scale text classification tasks.The proposed system demonstrates practical applicability in real-world domains including recommendationsystems, social media monitoring, customer feedback analysis, and OTT platform analytics.
Keywords	Sentiment Analysis, BERT, Review analysis, customer Feedback, positive negative feedbackIMDb Movie Review Dataset Transformer Architecture Machine Learning Self-Attention Mechanism Contextual Embeddings Binary Classification Opinion Mining Artificial Intelligence PyTorch Hugging Face Transformers Movie Review Analysis Neural Networks Language Models Predictive Analytics Context-Aware Sentiment Prediction
Field	Computer > Data / Information
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-23
DOI	https://doi.org/10.36948/ijfmr.2026.v08i03.78083

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 8 Isu 3 Cover Page Vol 8 Isu 2 Cover Page Vol 8 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Sentiment Analysis using BERT

Share this