• A Hybrid LLM-Driven Recommendation System for Selecting Flutter Packages Using Structured Metadata and Stack Overflow Knowledge 

  Bandara, R.M.I.M.; Chathumini, K.G.L.; Kumara, B.T.G.S. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  The rapid growth of the Flutter ecosystem has built significant challenges for the developers in choosing the right third-party packages. Existing popularity-based methods fail to capture developer intent or semantic ...
• AI-Driven Risk Prediction in Software Development Environment 

  Sanchayan, R.; Somaweera, W.T.S.; Sandaruwan, R.M.T. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Software development projects are constantly carried out in circumstances that are highly unexpected and dynamic. Unpredictability caused by frequent demand changes, shifting responsibilities, and delivery schedule ...
• AI Based Flutter Interface Generator Using Natural Language Commands with Social and Ethical Considerations 

  Andarawewa, K.M.; Chathumini, K.G.L. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  The accelerated pace of development of Artificial Intelligence (AI) and the emerging opportunities to automate the generation of user interfaces (UI) are explored in this research, especially within the context of ...
• Detecting Developer Burnout Through Sentiment Trends in Software Repositories Using DistilBERT 

  Samaraweera, S.P.I.L.D.; Adeeba, S. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Recent studies have indicated that severe chronic stress relates to burnout, and Software Engineering (SE) is no exception, having greater than 57chronic stress. Conventional methods of evaluation employ surveys and ...
• Semantic Metadata-enhanced Deep Learning Techniques for Duplicate Bug Report Detection 

  Sandunika, D.M.N.; Herath, G.A.C.A. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Duplication of bug reports poses a significant impact on software development efficiency with 12-25% of bugs report being duplicated on large projects. Manual identification techniques are both time consuming and prone ...
• Optimizing API and framework design for improved usability, maintainability, and developer productivity 

  Hashan, G.T.; Somaweera, W.T.S.; Sandaruwan, R.M.T. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  The use of APIs/ Frameworks in software development today cannot be done without and yet numerous of them still have design defects that hinder usability, maintainability and developer productivity due to lack of systematic ...
• An Empirical Evaluation of Clean Architecture: Impact on Software Quality and Developer Productivity 

  Senadheera, M.A.K.R.; Somaweera, W.T.S.; Sandaruwan, R.M.T. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Clean architecture(CA) is one of the most reliable and most productive architectures in the modern world. By organizing code into distinct layers, each with a clear responsibility, allows developers to build robust, ...
• Enhancing software quality and team productivity in agile development environments through machine learning-based sentiment analysis 

  Dayarathna, K.O.K.S.; Wasalthilaka, W.V.S.K. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Communication in Agile software development plays an important place for task coordination, clarifying requirements and sprint activities supervision. The sentiment shown in these communication messages can provide useful ...
• Analyzing developer misguidance in AI code suggestion tools: a large-scale empirical study 

  Sathursana, K.; Nirubikaa, R. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Artificial Intelligence (AI)-based code suggestion tools are widely used in current software development. These tools save time and help developers at many stages. At the same time, they produce code with some issues-the ...
• Time Series Forecasting of User Engagement in Python Software Applications Based on Usage Logs 

  Janarthan, V.; Erandi, J.D.T.; Tharaka, Y.M.S. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Understanding users’ engagement in Python-based software applications is important for improving usability, maintaining user satisfaction, and strategic future planning. Python usage logs contain important but rarely ...
• An explainable AI-based approach for Java code smell detection to improve software maintainability 

  Wedaarachchi ., R; Herath, G.A.C.A.; Wasalthilaka, W.V.S.K. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Code smells are early indicators of design flaws that compromise long term software maintainability. Traditional static analysis tools often generate false positives or fail to detect context dependent smells because ...
• Classification of Non-Functional Requirements in Software Development using Deep Learning 

  Kavindi, H.M.K.; Herath, G.A.C.A. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Non-functional requirements are the most significant quality attributes that define a software system as being reliable, secure and efficient under the real-world conditions. But, NFRs are often not taken into account ...
• Comparative Analysis of Sentiment Classification Models for Algorithmic Trading 

  Perera, R.D.M.; Ishanka, U.A.P (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Market sentiment, as driven by news and online discussion sites is increasingly impacting algorithmic trading systems. In this work, we analyze financial news headlines from Yahoo Finance, enhanced with related discussion ...
• Automated detection of developer mental health status in collaboration platforms using NLP and activity analysis 

  Abewardhana, M.R.S.C.; Ishanka, U.A.P. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Software developers experience significant mental health challenges due to workrelated stressors, making it essential for workplaces to adopt systematic and proactive strategies for identifying and supporting employees ...
• Evaluating the security of JavaScript code generated by GitHub Copilot using static analysis tools 

  Partheepan, V.; Wijerathna, R.M.K.K. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Artificial Intelligence (AI) tools are changing the way code is written in software development. According to a Sonatype (2023) report 97% of developers use Large Language Models (LLMs) for their work and improve software ...
• A Context-Aware Multi-Task Learning Framework for Developer Recommendation in GitHub Issue Triage 

  Thilakshana, I.K.A.D.; Kudagamage, U.P. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)
• A Rule-based Self-healing Baseline for Hybrid AI Repair of Common Python Syntax Errors 

  Perera, H.A.I.J.; Lekamge, L.S. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Python has become a popular language of beginners due to its simplicity. However, syntax errors remain as a hurdle to productivity and learning. Although automated program repair (APR) has improved, in the majority of ...
• Predicting Developer Burnout and Enhancing Team Performance through Multi-Modal Workload Analysis from Jira and GitHub Activity 

  Sabeeb, A.I.M.; Erandi, J.D.T.; Maduwanthi, W.V.C. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Developer burnout has become a critical challenge in agile software development, as faster delivery cycles, high task-switching demands, and sustained cognitive load affect mental wellbeing and gradually reduce productivity. ...
• Comparative evaluation of traditional and neural models for multi-class classification of GitHub commit messages 

  Tharsa, S.; Wijerathine, P.M.A.K. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Commit messages are a critical source of information within software repositories, documenting changes made to code entries. While they are important to empirical software engineering and development cycles, these messages ...
• TikTok Video Classification Based on Emotions Using Convolutional Neural Networks 

  Nagodavithana, S.D.; Rupasingha, R.A.H.M.; Kumara, B.T.G.S. (Faculty of Computing. Sabaragamuwa University of Sri Lanka., 2026-01-28)

  Emotion recognition is a product of AI and computer vision, which enables systems to decipher human emotions during a range of uses. As TikTok grows, expressions made by users in the short videos offer valuable information ...

View more