An Improved Quantum Software Challenges Classification Approach using Transfer Learning and Explainable AI

Abstract

Quantum Software Engineering (QSE) has emerged as a research direction practiced by tech joints. Quantum developers face challenges in optimizing quantum computing and QSE concepts. Developers use Stack Overflow to discuss quantum challenges using specialized tags to label posts. These tags often refer to technical quantum aspects. Categorizing quantum practitioners’ questions by concept can help identify common QSE challenges. We conducted studies to classify quantum developers’ questions into various challenges. We extracted 2829 developers questions from Q&A platforms using quantum-related tags. The posts were analyzed to identify frequent quantum-related challenges anddevelop a novel grounded theory. The challenges identified include Tooling, Theoretical, Learning, Conceptual, Errors, and API Usage. Through content analysis and grounded theory, the developers’ discussions were annotated with commonly reported quantum challenges to develop a ground truth dataset. ChatGPT was used to validate human annotations and resolve disagreements. Various fine-tuned transformer algorithms, including BERT, DistilBERT, and RoBERTa, were used to classify developer discussions into commonly reported quantum challenges. We achieved an average accuracy of 95% with BERT DistilBERT algorithms, compared to fine-tuned Deep and Machine Learning (D&ML) classifiers, including Feedforward Neural Networks (FNN), Convolutional Neural Networks (CNN), and Long Short-Term Memory networks (LSTM), which achieved accuracies of 89%, 86%, and 84%, respectively. The proposed Transformer-based approach outper-forms the previous D&ML-based approach with a 6% increase in accuracy by processing actual developer discussions, i.e., without data augmentation. Furthermore, we applied SHAP (SHapley Additive exPlanations) to provide model interpretability, revealing how specific linguistic features drive predictions and enhancing transparency in the classification process. These improved research findings can help quantum vendors and developers’ discussion forums to better organize developers’ discussions for improved access and readability.

Keywords

Quantum Software Engineering / Repository mining / developer forums / Stack overflow / Transfer Learning / Natural language processing

RIGHTS & PERMISSIONS

Higher Education Press 2026

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.