Improving Requirements Classification with SMOTE-Tomek Preprocessing

2025-01-11

AI Summary

In requirements engineering, severe class imbalance between functional and non-functional requirements hinders effective classification. To address this, this paper—using the PROMISE dataset (969 labeled requirements)—introduces SMOTE-Tomek Links sampling to this task for the first time, integrated with stratified k-fold cross-validation to ensure robust evaluation. The method preserves overall data distribution while substantially enhancing minority-class representation. Experiments employ a lightweight logistic regression classifier, achieving 76.16% accuracy—a 17.85-percentage-point improvement over baseline methods. Results demonstrate that: (1) SMOTE-Tomek Links effectively mitigates class skew in requirement texts; and (2) lightweight models offer strong interpretability, scalability, and practical utility without compromising performance.

Technology Category

• Machine Learning: Ensemble Methods
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

This study emphasizes the domain of requirements engineering by applying the SMOTE-Tomek preprocessing technique, combined with stratified K-fold cross-validation, to address class imbalance in the PROMISE dataset. This dataset comprises 969 categorized requirements, classified into functional and non-functional types. The proposed approach enhances the representation of minority classes while maintaining the integrity of validation folds, leading to a notable improvement in classification accuracy. Logistic regression achieved 76.16%, significantly surpassing the baseline of 58.31%. These results highlight the applicability and efficiency of machine learning models as scalable and interpretable solutions.

Problem

• Demand Classification
• Imbalanced Categories
• Functional and Non-functional Requirements

Innovation

• SMOTE-Tomek
• K-fold Cross Validation
• Imbalanced Dataset Handling