Copyright © 2026 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{200902,
        author = {P. Ganesh and Rithikha V and Nishanthi S and Jayapriya S},
        title = {A Time-Aware Graph-Based Approach for Software Bug Triaging},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {no},
        pages = {16-24},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200902},
        abstract = {Software bug triaging — the process of assigning incoming bug reports to the most suitable developer — is a critical yet time-consuming activity in large-scale software projects. Existing approaches predominantly rely on static graph models or text-only features, failing to capture the evolving temporal dynamics of bug-developer interaction patterns. To address these limitations, we propose a Time-Aware Graph-Based (TAGB) framework for automated software bug triaging. TAGB integrates BERT-based semantic feature extraction with a Time-Weighted Heterogeneous Graph Neural Network (TW-HGNN) that jointly encodes structural and temporal information. Bug reports are modeled as nodes in a dynamic graph, developers as labels, and temporal dependencies as time-stamped edges, enabling the model to capture how assignment patterns evolve over time. Extensive experiments on three large-scale open-source bug repositories — Eclipse, Mozilla, and GCC — collected from Bugzilla spanning 2010 to 2020 demonstrate that TAGB achieves Top-10 recommendation accuracies of 83.14%, 81.97%, and 82.43%, outperforming state-of-the-art baselines including CNND- BRT, NCGBT, ST-DGNN, and GCBT. Ablation studies confirm the critical contribution of the temporal weighting mechanism and the superiority of combined BERT-TF- IDF feature extraction. Results demonstrate that incorporating temporal awareness into graph-based bug triaging significantly improves both accuracy and generalization across projects with diverse structural characteristics.},
        keywords = {Software bug triaging, temporal graph neural networks, heterogeneous graphs, BERT, dynamic graphs, time-aware modeling, software maintenance.},
        month = {May},
        }