Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{168331,
        author = {Atharav Uttam Jagtap and Nilesh Balu Jadhav and Aryan Kishan Batra and Sarthak Vitthal Hase},
        title = {Subjective Answer Evaluation Using Deep Learning and Natural Language Processing},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {5},
        pages = {522-526},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=168331},
        abstract = {Subjective answer evaluation remains a challenging task due to its inherent complexity and susceptibility to human bias. This project explores the potential of Artificial Intelligence (AI) to address this challenge, specifically utilizing the power of Bidirectional Encoder Representations from Transformers (BERT). We present a novel BERT-based model for subjective answer evaluation. Our model is trained on a dataset containing sentence pairs labeled with their semantic similarity ("Contradiction", "Entailment", or "Neutral"). We meticulously clean and pre-process the data, define a BERT data generator, and build a BERT model to extract features from the sentences. These features are then used to train the model for classifying the semantic relationships between the sentences. The trained model achieves promising results on a separate test dataset. Finally, we showcase the practical implementation of the project by building a user interface and deploying the model as a web service using Flask. This work demonstrates the effectiveness of AI in subjective answer evaluation, paving the way for more efficient, consistent, and scalable assessment practices.},
        keywords = {Artificial Intelligence, BERT, Contradiction, Flask},
        month = {October},
        }