In traditional student answer evaluation systems, assessment is primarily based on keyword matching, which often fails to capture the actual meaning and context of a student’s response. This leads to inaccurate grading, especially when students express correct answers using different wording. This paper proposes a semantic analysis–based approach for evaluating descriptive answers by understanding contextual meaning rather than relying solely on exact keywords. The proposed system utilizes natural language processing techniques to analyze the similarity between student responses and reference answers at a semantic level. It compares keyword-based evaluation with semantic-based evaluation to highlight the effectiveness of evaluating student responses more accurately. The study demonstrates that semantic analysis provides a more accurate and fair assessment by recognizing synonymous expressions and contextual relevance.
Keywords
Semantic Analysis, Natural Language Processing (NLP), Automated Answer Evaluation, Semantic Similarity, Keyword Matching, Deep Learning.
Conclusion
This paper presented a semantic analysis-based approach for evaluating
answers more effectively. Traditional keyword-based methods were found to be limited in understanding the actual meaning of responses as it completely relies on keyword matching leading to inaccurate grading in many cases.
The proposed system combines keyword matching with semantic similarity techniques to overcome these limitations and gives accurate results by not just comparing words but also understanding the context of the answers given by the students.By considering both important terms and contextual meaning, the system provides a more balanced and fair evaluation of student answers.
The study highlights the importance of integrating natural language processing techniques into educational systems. Future improvements can include the use of advanced deep learning models and larger datasets to further enhance accuracy and performance.
References
[1] T. K. Landauer, P. W. Foltz, and D. Laham, “An introduction to latent semantic analysis,” Discourse Processes, vol. 25, no. 2–3, pp. 259–284, 1998.
[2] T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” in Proc. Int. Conf. Learn. Representations (ICLR), 2013.
[3] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, 2019.
[4] G. Salton and M. J. McGill, Introduction to Modern Information Retrieval. New York, NY, USA: McGraw-Hill, 1983.
How to Cite This Paper
Nagesh Rathore, Mr. Ram Kumar Sharma (2026). A Semantic Analysis-Based Approach for Answer Evaluation. International Journal of Computer Techniques, 13(2). ISSN: 2394-2231.
