Karthik Shivashankar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Karthik Shivashankar has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
Antonio Martini
Department of Informatics, University of Oslo, Oslo, Norway
3 shared publications- Antonio Martini
Department of Informatics, University of Oslo, Oslo, Norway
3 shared publications Kristian Marison Haugerud
Department of Informatic University of Oslo Oslo Norway
2 shared publicationsMaren Maritsdatter Kruke
Visma Software International, Oslo, Norway
2 shared publicationsMili Orucevic
Visma Software International, Oslo, Norway
2 shared publications- Ghadi S. Al Hajj
Department of Informatics, University of Oslo
1 shared publication
Latest Publications
- Open Access
- 17 July 2026
- Published by Springer Nature in Software Quality Journal
- Vol. 34 (3) , 38
QualiTagger: automating software quality categorization in issue trackers
Managing software quality is crucial for maintainable software systems, yet understanding how quality attributes are discussed within the informal, noisy context of issue trackers remains a significant challenge. Current automatic approaches for categorizing quality concerns often falter, as they are typically validated on small domain-specific datasets and are ill-equipped to parse the conversational language of developer discourse. This hinders effective prioritization and technical debt management. This paper introduces QualiTagger, an automated approach for classifying seven distinct software quality attributes from issue tracker text, and QualiDataSet, a novel, curated dataset of over 700,000 labeled GitHub issues that underpins this work. We demonstrate that an ensemble of specialized binary classifiers, built upon the DistilRoBERTa architecture, significantly outperforms a single multiclass model and shows superior or comparable efficacy to a general-purpose Large Language Model (GPT-4o) for this task. The model’s real-world applicability is further validated through an industrial case study at Visma focusing on security issues) and a user study with software engineering students. Our evaluation confirms that QualiTagger achieves high classification accuracy and, crucially, generalizes effectively to previously unseen (Out-of-Distribution) projects, a key indicator of its practical utility. By providing both a robust classification tool and a large-scale public dataset, this research enables a more nuanced, data-driven understanding of how software quality is managed in practice, offering valuable insights for project management and future empirical software engineering research
- 17 July 2026
- Published by Springer Nature in Software Quality Journal
- Vol. 34 (3) , 38
Open AccessQualiTagger: automating software quality categorization in issue trackers
Managing software quality is crucial for maintainable software systems, yet understanding how quality attributes are discussed within the informal, noisy context of issue trackers remains a significant challenge. Current automatic approaches for categorizing quality concerns often falter, as they are typically validated on small domain-specific datasets and are ill-equipped to parse the conversational language of developer discourse. This hinders effective prioritization and technical debt management. This paper introduces QualiTagger, an automated approach for classifying seven distinct software quality attributes from issue tracker text, and QualiDataSet, a novel, curated dataset of over 700,000 labeled GitHub issues that underpins this work. We demonstrate that an ensemble of specialized binary classifiers, built upon the DistilRoBERTa architecture, significantly outperforms a single multiclass model and shows superior or comparable efficacy to a general-purpose Large Language Model (GPT-4o) for this task. The model’s real-world applicability is further validated through an industrial case study at Visma focusing on security issues) and a user study with software engineering students. Our evaluation confirms that QualiTagger achieves high classification accuracy and, crucially, generalizes effectively to previously unseen (Out-of-Distribution) projects, a key indicator of its practical utility. By providing both a robust classification tool and a large-scale public dataset, this research enables a more nuanced, data-driven understanding of how software quality is managed in practice, offering valuable insights for project management and future empirical software engineering research
- Open Access
- 1 April 2026
- Published by Springer Nature
- p. 137-151
TD-Suite: All Batteries Included Framework for Technical Debt Classification
In Agile software development, maintaining velocity requires the continuous management of Technical Debt (TD). However, the rapid iteration cycles inherent to Agile often obscure debt accumulation, making manual identification in issue trackers prohibitively expensive. To address this, we present TD-Suite, a comprehensive framework engineered to automate the classification of technical debt. It leverages state-of-the-art transformer models to analyze textual artifacts, such as developer discussions in issue reports, where subtle indicators of debt often lie hidden. TD-Suite provides a seamless end-to-end pipeline suitable for Agile ML Engineering, managing everything from initial data ingestion and rigorous preprocessing to model training, thorough evaluation, and final inference. It supports both binary classification (debt or no debt) and granular categorization—identifying code, architecture, design, or documentation debt—enabling Agile teams to formulate targeted refactoring strategies. To ensure robustness on real-world, imbalanced datasets, TD-Suite incorporates k-fold cross-validation, early stopping, and class weighting strategies. The framework explicitly integrates the tracking and reporting of carbon emissions associated with model training. Furthermore, it features a user-friendly Gradio web interface within a Docker container, simplifying integration into DevOps pipelines and democratizing access for practitioners without deep ML expertise.
- 1 April 2026
- Published by Springer Nature
- p. 137-151
Open AccessTD-Suite: All Batteries Included Framework for Technical Debt Classification
In Agile software development, maintaining velocity requires the continuous management of Technical Debt (TD). However, the rapid iteration cycles inherent to Agile often obscure debt accumulation, making manual identification in issue trackers prohibitively expensive. To address this, we present TD-Suite, a comprehensive framework engineered to automate the classification of technical debt. It leverages state-of-the-art transformer models to analyze textual artifacts, such as developer discussions in issue reports, where subtle indicators of debt often lie hidden. TD-Suite provides a seamless end-to-end pipeline suitable for Agile ML Engineering, managing everything from initial data ingestion and rigorous preprocessing to model training, thorough evaluation, and final inference. It supports both binary classification (debt or no debt) and granular categorization—identifying code, architecture, design, or documentation debt—enabling Agile teams to formulate targeted refactoring strategies. To ensure robustness on real-world, imbalanced datasets, TD-Suite incorporates k-fold cross-validation, early stopping, and class weighting strategies. The framework explicitly integrates the tracking and reporting of carbon emissions associated with model training. Furthermore, it features a user-friendly Gradio web interface within a Docker container, simplifying integration into DevOps pipelines and democratizing access for practitioners without deep ML expertise.
- 30 November 2025
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 37 (12)
Enhancing Task Prioritization in Software Development Issues Tracking System
Modern software development faces a critical bottleneck in manually prioritizing the overwhelming volume of issues generated in platforms like Jira and GitHub. This labor‐intensive process leads to delays, increased costs, inconsistent handling, and developer burnout, worsened by the lack of standardized priority labels. This paper investigates the potential of automated issue priority classification using state‐of‐the‐art Transformer models to alleviate this burden. We evaluate the performance of models like BERT, DeBERTa, and ModernBERT, comparing them against general large language models (LLMs) such as GPT‐3.5, Qwen2.5‐3B and Llama‐3.2‐3B, using curated datasets derived from public Jira and GitHub repositories. Our research addresses the effectiveness of these models for their generalization capabilities on out‐of‐distribution projects, the impact of fine‐tuning, and performs a detailed performance comparison across different priority levels and model types. Results demonstrate that Transformer models, particularly ModernBERT, achieve high classification performance (e.g., accuracy > 81%), significantly outperforming the evaluated general LLMs (accuracy 75%) for this specific task. We find that binary classification is more effective than multilabel approaches, models generalize well to unseen projects, and performance is further enhanced by fine‐tuning. Key contributions include the provision of cleaned, labeled datasets and a comprehensive evaluation confirming the viability and benefits of using specialized Transformer models for automated issue priority suggestion, offering a path to improved efficiency and resource allocation in software development workflows.
- 30 November 2025
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 37 (12)
Enhancing Task Prioritization in Software Development Issues Tracking System
Modern software development faces a critical bottleneck in manually prioritizing the overwhelming volume of issues generated in platforms like Jira and GitHub. This labor‐intensive process leads to delays, increased costs, inconsistent handling, and developer burnout, worsened by the lack of standardized priority labels. This paper investigates the potential of automated issue priority classification using state‐of‐the‐art Transformer models to alleviate this burden. We evaluate the performance of models like BERT, DeBERTa, and ModernBERT, comparing them against general large language models (LLMs) such as GPT‐3.5, Qwen2.5‐3B and Llama‐3.2‐3B, using curated datasets derived from public Jira and GitHub repositories. Our research addresses the effectiveness of these models for their generalization capabilities on out‐of‐distribution projects, the impact of fine‐tuning, and performs a detailed performance comparison across different priority levels and model types. Results demonstrate that Transformer models, particularly ModernBERT, achieve high classification performance (e.g., accuracy > 81%), significantly outperforming the evaluated general LLMs (accuracy 75%) for this specific task. We find that binary classification is more effective than multilabel approaches, models generalize well to unseen projects, and performance is further enhanced by fine‐tuning. Key contributions include the provision of cleaned, labeled datasets and a comprehensive evaluation confirming the viability and benefits of using specialized Transformer models for automated issue priority suggestion, offering a path to improved efficiency and resource allocation in software development workflows.
- Open Access
- 12 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (12) , 1-36
Maintainability and Scalability in Machine Learning: Challenges and Solutions
Rapid advancements in Machine Learning (ML) introduce unique maintainability and scalability challenges. Our research addresses the evolving challenges and identifies ML maintainability and scalability solutions by conducting a thorough literature review of over 17,000 papers, ultimately refining our focus to 124 relevant sources that meet our stringent selection criteria. We present a catalogue of 41 Maintainability and 13 Scalability challenges and solutions across Data, Model Engineering and the overall development of ML applications and systems. This study equips practitioners with insights on building robust ML applications, laying the groundwork for future research on improving ML system robustness at different workflow stages.
- 12 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (12) , 1-36
Open AccessMaintainability and Scalability in Machine Learning: Challenges and Solutions
Rapid advancements in Machine Learning (ML) introduce unique maintainability and scalability challenges. Our research addresses the evolving challenges and identifies ML maintainability and scalability solutions by conducting a thorough literature review of over 17,000 papers, ultimately refining our focus to 124 relevant sources that meet our stringent selection criteria. We present a catalogue of 41 Maintainability and 13 Scalability challenges and solutions across Data, Model Engineering and the overall development of ML applications and systems. This study equips practitioners with insights on building robust ML applications, laying the groundwork for future research on improving ML system robustness at different workflow stages.
- Open Access
- 28 May 2025
- Published by Wiley
Enhancing Task Prioritization in Software Development Issues Tracking system
Modern software development faces a critical bottleneck in manually prioritizing the overwhelming volume of issues generated in platforms like Jira and GitHub. This labor-intensive process leads to delays, increased costs, inconsistent handling, and developer burnout, worsened by the common lack of standardized priority labels. This paper investigates the potential of automated issue priority classification using state-of-the-art Transformer models to alleviate this burden. We evaluate the performance of models like BERT, DeBERTa, and ModernBERT, comparing them against general Large Language Models (LLMs) such as Qwen2.5-3B and Llama-3.2-3B, using curated datasets derived from public Jira and GitHub repositories. Our research addresses the effectiveness of these models for in-distribution classification, their generalization capabilities on out-of-distribution projects, the impact of fine-tuning, and performs a detailed performance comparison across different priority levels and model types. Results demonstrate that Transformer models, particularly ModernBERT, achieve high classification performance (e.g., accuracy > 81%), significantly outperforming the evaluated general LLMs (accuracy 75%) for this specific task. We find that binary classification is more effective than multilabel approaches, models generalize well to unseen projects, and performance is further enhanced by fine-tuning. Key contributions include the provision of cleaned, labeled datasets and a comprehensive evaluation confirming the viability and benefits of using specialized Transformer models for automated issue priority suggestion, offering a path to improved efficiency and resource allocation in software development workflows.
- 28 May 2025
- Published by Wiley
Open AccessEnhancing Task Prioritization in Software Development Issues Tracking system
Modern software development faces a critical bottleneck in manually prioritizing the overwhelming volume of issues generated in platforms like Jira and GitHub. This labor-intensive process leads to delays, increased costs, inconsistent handling, and developer burnout, worsened by the common lack of standardized priority labels. This paper investigates the potential of automated issue priority classification using state-of-the-art Transformer models to alleviate this burden. We evaluate the performance of models like BERT, DeBERTa, and ModernBERT, comparing them against general Large Language Models (LLMs) such as Qwen2.5-3B and Llama-3.2-3B, using curated datasets derived from public Jira and GitHub repositories. Our research addresses the effectiveness of these models for in-distribution classification, their generalization capabilities on out-of-distribution projects, the impact of fine-tuning, and performs a detailed performance comparison across different priority levels and model types. Results demonstrate that Transformer models, particularly ModernBERT, achieve high classification performance (e.g., accuracy > 81%), significantly outperforming the evaluated general LLMs (accuracy 75%) for this specific task. We find that binary classification is more effective than multilabel approaches, models generalize well to unseen projects, and performance is further enhanced by fine-tuning. Key contributions include the provision of cleaned, labeled datasets and a comprehensive evaluation confirming the viability and benefits of using specialized Transformer models for automated issue priority suggestion, offering a path to improved efficiency and resource allocation in software development workflows.
- Open Access
- 18 March 2025
- Published by Elsevier in Journal of Systems and Software
- Vol. 226
BEACon-TD: Classifying Technical Debt and its types across diverse software projects issues using transformers
- 18 March 2025
- Published by Elsevier in Journal of Systems and Software
- Vol. 226
Open AccessBEACon-TD: Classifying Technical Debt and its types across diverse software projects issues using transformers