Νάστος Δημήτριος

PhD Candidate

Aristotle University of Thessaloniki, Department of Electrical and Computer Engineering
54124 Thessaloniki – GREECE
Email: diminast (at) ece [dot] auth [dot] gr
LinkedIn: https://www.linkedin.com/in/dimitrios-nikitas-nastos/ 

Education

11/2022-today

PhD Candidate
Electrical and Computer Engineering Department
Aristotle University of Thessaloniki, Greece
PhD Thesis: “Development of Conversational Systems with Artificial Intelligence and Natural Language Processing Techniques”

11/2020-07/2022

Master’s degree
Advanced Computing and Communication Systems,
Aristotle University of Thessaloniki, Greece
Master Thesis: “Design and Development of Greek Question Answering System”

10/2013 – 07/2020

Diploma of Electrical and Computer Engineering
Electrical and Computer Engineering Department,
Aristotle University of Thessaloniki, Greece
Diploma Thesis: “Visualization of Resources Availability on Two-Dimensional Maps”

Professional Experience

10/2022 – today Research Associate / NLP Engineer,
Electrical and Computer Engineering Department,
Aristotle University of Thessaloniki, Greece

Research interests

  • Natural Language Processing
  • Natural Language Understanding
  • Conversational AI
  • Machine Learning
  • Software Engineering

Foreign Languages

  • English: Proficient (Certificate of Proficiency in English,University of Cambridge- C2)
  • German: Intermediate (Goethe-Zertifikat B1)

Publications

2023

Conference Papers

Dimitrios-Nikitas Nastos, Themistoklis Diamantopoulos and Andreas Symeonidis
"Towards Interpretable Monitoring and Assignment of Jira Issues"
Proceedings of the 18th International Conference on Software Technologies (ICSOFT 2023), pp. 696-703, 2023 Jul

Lately, online issue tracking systems like Jira are used extensively for monitoring open-source software projects. Using these systems, different contributors can collaborate towards planning features and resolving issues that may arise during the software development process. In this context, several approaches have been proposed to extract knowledge from these systems in order to automate issue assignment. Though effective under certain scenarios, these approaches also have limitations; most of them are based mainly on textual features and they may use techniques that do not extract the underlying semantics and/or the expertise of the different contributors. Furthermore, they typically provide black-box recommendations, thus not helping the developers to interpret the issue assignments. In this work, we present an issue mining system that extracts semantic topics from issues and provides interpretable recommendations for issue assignments. Our system employs a dataset of Jira issues and extracts information not only from the textual features of issues but also from their components and their labels. These features, along with the extracted semantic topics, produce an aggregated model that outputs interpretable recommendations and useful statistics to support issue assignment. The results of our evaluation indicate that our system can be effective, leaving room for future research.

@conference{ICSOFT2023Issues,
author={Dimitrios-Nikitas Nastos and Themistoklis Diamantopoulos and Andreas Symeonidis},
title={Towards Interpretable Monitoring and Assignment of Jira Issues},
booktitle={Proceedings of the 18th International Conference on Software Technologies (ICSOFT 2023)},
pages={696-703},
year={2023},
month={07},
date={2023-07-10},
url={https://issel.ee.auth.gr/wp-content/uploads/2023/07/ICSOFT2023Issues.pdf},
doi={https://doi.org/10.5220/0012146400003538},
keywords={Task Management;Jira Issues;Topic Modeling;Project Management},
abstract={Lately, online issue tracking systems like Jira are used extensively for monitoring open-source software projects. Using these systems, different contributors can collaborate towards planning features and resolving issues that may arise during the software development process. In this context, several approaches have been proposed to extract knowledge from these systems in order to automate issue assignment. Though effective under certain scenarios, these approaches also have limitations; most of them are based mainly on textual features and they may use techniques that do not extract the underlying semantics and/or the expertise of the different contributors. Furthermore, they typically provide black-box recommendations, thus not helping the developers to interpret the issue assignments. In this work, we present an issue mining system that extracts semantic topics from issues and provides interpretable recommendations for issue assignments. Our system employs a dataset of Jira issues and extracts information not only from the textual features of issues but also from their components and their labels. These features, along with the extracted semantic topics, produce an aggregated model that outputs interpretable recommendations and useful statistics to support issue assignment. The results of our evaluation indicate that our system can be effective, leaving room for future research.}
}

Themistoklis Diamantopoulos, Dimitrios-Nikitas Nastos and Andreas Symeonidis
"Semantically-enriched Jira Issue Tracking Data"
20th International Conference on Mining Software Repositories (MSR 2023), pp. 218-222, ACM, 2023 May

Current state of practice dictates that software developers host their projects online and employ project management systems to monitor the development of product features, keep track of bugs, and prioritize task assignments. The data stored in these systems, if their semantics are extracted effectively, can be used to answer several interesting questions, such as finding who is the most suitable developer for a task, what the priority of a task should be, or even what is the actual workload of the software team. To support researchers and practitioners that work towards these directions, we have built a system that crawls data from the Jira management system, performs topic modeling on the data to extract useful semantics and stores them in a practical database schema. We have used our system to retrieve and analyze 656 projects of the Apache Software Foundation, comprising data from more than a million Jira issues.

@conference{MSR2023,
author={Themistoklis Diamantopoulos and Dimitrios-Nikitas Nastos and Andreas Symeonidis},
title={Semantically-enriched Jira Issue Tracking Data},
booktitle={20th International Conference on Mining Software Repositories (MSR 2023)},
pages={218-222},
publisher={ACM},
year={2023},
key={MSR2023},
month={05},
date={2023-05-15},
url={https://issel.ee.auth.gr/wp-content/uploads/2023/04/MSR2023JiraIssuesDataset.pdf},
doi={https://doi.org/10.1109/MSR59073.2023.00039},
keywords={mining software repositories;Task Management;Jira Issues;Topic Modeling;BERT},
abstract={Current state of practice dictates that software developers host their projects online and employ project management systems to monitor the development of product features, keep track of bugs, and prioritize task assignments. The data stored in these systems, if their semantics are extracted effectively, can be used to answer several interesting questions, such as finding who is the most suitable developer for a task, what the priority of a task should be, or even what is the actual workload of the software team. To support researchers and practitioners that work towards these directions, we have built a system that crawls data from the Jira management system, performs topic modeling on the data to extract useful semantics and stores them in a practical database schema. We have used our system to retrieve and analyze 656 projects of the Apache Software Foundation, comprising data from more than a million Jira issues.}
}