Explainable AI for Issue Classification: A Multi-class Study with LIME and SHAP
Issue classification is a fundamental task in software development, enabling teams to manage issue reports. Automatic issue classification can help developers classify issue reports. However, developers should understand why each issue report is classified in such a way. A prior study has shown that explainable AI (XAI) can explain how an issue report is classified as a bug or a non-bug. However, the binary setting limits applicability to real-world issue tracking systems, where multiple categories coexist.In this paper, we replicate and extend the prior study by conducting a multi-class issue classification experiment using three categories: Bug, Enhancement, and Question. We used a fine-tuned, seBERT-based classifier and apply two widely used XAI models, LIME and SHAP, to generate explanations for issue classification. We then qualitatively investigate the results of applying LIME and SHAP to the multi-class issue classification.
Sun 16 NovDisplayed time zone: Seoul change
16:00 - 18:00 | |||
16:00 15mTalk | Fair Developer Score: Build-Adjusted Measurement of Effort and Impact Intelligent SE 2025 Xinzhou Wang Northwestern University, Jiancong Zhu Northwestern University, Jinghan Feng Northwestern University, Zixuan Zhang Northwestern University, Joshua Rauvola University of Chicago, Devon Delgado Digital Emissions, Ahmad Antar Digital Emissions, Abid Ali Northwestern University | ||
16:15 15mTalk | Optimizing LLM Code Suggestions: Feedback-Driven Timing with Lightweight State Bounds Intelligent SE 2025 Mohammad Nour Al Awad ITMO University, Sergey Ivanov ITMO University, Olga Tikhonova ITMO University | ||
16:30 15mTalk | Exploring the SECURITY.md in the Dependency Chain: Preliminary Analysis of the PyPI Ecosystem Intelligent SE 2025 Chayanid Termphaiboon Mahidol University, Raula Gaikovina Kula The University of Osaka, Youmei Fan Nara Institute of Science and Technology, Morakot Choetkiertikul Mahidol University, Thailand, Chaiyong Rakhitwetsagul Mahidol University, Thailand, Thanwadee Sunetnanta Mahidol University, Kenichi Matsumoto Nara Institute of Science and Technology | ||
16:45 15mTalk | Towards MPC-driven Software Adaptation: A Dual-Layer Approach Combining ICNN-based Modeling and Delta-based Tuning Intelligent SE 2025 Yitong Shi Institute of Science Tokyo, Chenyu Hu Institute of Science Tokyo, Mingyue Zhang Southwest University, NIANYU LI ZGC Lab, China, Jialong Li Waseda University, Japan, Kenji Tei Institute of Science Tokyo | ||
17:00 15mTalk | Explainable AI for Issue Classification: A Multi-class Study with LIME and SHAP Intelligent SE 2025 | ||