Abstract :

Ambiguity In Software Requirements Is A Substantial Difficulty In Software Engineering, Resulting In Conflicting Interpretations, Developmental Errors, And Quality Hazards. A Machine Learning-based System Is Proposed For The Automatic Detection Of Ambiguity Utilizing The Software Requirements Dataset From Kaggle. The Methodology Incorporates Sophisticated Natural Language Processing Techniques, Including TF-IDF And Bag-of-Words Vectorization, Alongside Various Classification Algorithms Such As Decision Tree, Random Forest, Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), K-Nearest Neighbor (KNN), Logistic Regression, Multinomial Naïve Bayes, TF-IDF Voting (RF+LR+SVM), Bag-of-Words Naïve Bayes, Bag-of-Words Voting (NB+LR), Bagof-Words Random Forest, SMOTE-enhanced Decision Tree, And SMOTE XGBoost. Data Balance Was Accomplished By SMOTEENN, Guaranteeing Strong Model Generalization. The Experimental Evaluation Revealed That SMOTE XGBoost Attained Exceptional Performance, Achieving 99.6% Accuracy, 100% Precision, And 99.1% Recall, Surpassing Alternative Models. Additionally, Explainable Artificial Intelligence (XAI) Techniques, Particularly LIME And SHAP, Were Utilized To Emphasize Essential Linguistic Elements That Influence Ambiguity Classification, Thus Improving Interpretability And Transparency. The Suggested Method Enhances Ambiguity Identification And Offers Actionable Insights Into Requirement Patterns, Facilitating More Accurate And Informed Decision-making In Software Engineering.

Published:

08-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1743-1756

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite