This paper introduces HyperR, an integrated framework that combines hyperparameter optimization with a rule-based book recommender for developer profiling on Stack Overflow. The proposed optimizationmethod employs a cost-bounded, accuracy-aware strategy with early stopping and adaptive search to balance computational efficiency and search effectiveness. The framework evaluates both model-free (Grid Search, Random Search, Nelder–Mead, DEoptim) and model-based (Bayesian Optimization, AutoFT, mlrMBO,TuRBO) optimizers across multiple classifiers on a dataset of 20,000 Stack Overflow questions, using stratified 70/30 train-test splits with 20 repeated runs per configuration. Experimental results show that the proposed method achieves the highest macro-averaged precision (0.671) and significantly outperformsclassical baselines (adjusted p < 0.008), while remaining competitive with state-of-the-art modelbased approaches (adjusted p > 0.05). In addition, it reduces peak memory usage by up to 25% compared with exhaustive search methods. The recommendation module achieves strong performance (Precision@3= 0.82 and Recall@3 = 0.77), demonstrating the effectiveness of the proposed framework in delivering personalized learning resources.
Fatma Altınsoy, Muhammed Maruf Öztürk· Informatica· 0 citations
Software vulnerabilities remain a critical threat to modern software systems, while existing detection approaches often suffer from high computational cost, limited scalability, and severe class imbalance in real-world datasets. To address these challenges, this study proposes H-LLM-IM, an adaptive imbalance-aware hybrid framework for efficient software vulnerability detection. The proposed framework leverages semantic code embeddings extracted from a pre-trained code language model (CodeBERT) and integrates them with lightweight machine learning classifiers, thereby avoiding expensive fine-tuning of large language models.A key contribution of H-LLM-IM is an adaptive imbalance-aware learning mechanism that dynamically regulates imbalance mitigation intensity through controlled oversampling and adaptive reweighting based on minority-class performance feedback. Extensive experiments conducted on the Big-Vul benchmark dataset evaluate four classifiers (Logistic Regression, SVM, Random Forest, and XGBoost) under multiple imbalance-handling scenarios, including static and adaptive strategies.The results demonstrate that the proposed adaptive framework substantially improves minority-class vulnerability detection, achieving up to a 2.5-fold increase in F1-score and up to 83% improvement in MCC compared to the no-imbalance baseline. Importantly, these performance gains are obtained while maintaining practical training time and controlled memory growth. In particular, Logistic Regression and XGBoost exhibit the most favorable performance–efficiency trade-off, highlighting the scalability and practical applicability of H-LLM-IM for large-scale vulnerability analysis under severe class imbalance.
Fatma Altınsoy· Süleyman Demirel Üniversites...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
