Riad Sonbol
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Riad Sonbol has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
Nada Ghneim
Department of Informatics, Higher Institute for Applied Sciences and Technology, Damascus, Syria
6 shared publicationsGhaida Rebdawi
Department of Informatics, Higher Institute for Applied Sciences and Technology, Damascus, Syria
5 shared publications- Ghaida Rebdawi
Higher Institute for Applied Sciences and Technology
2 shared publications - Albani
Safee technology LLC, Dubai, United Arab Emirates
1 shared publication - Anas Abdulaziz
Higher Institute for Applied Sciences and Technology (HIAST), Damascus, Syria
1 shared publication - Mohamad Bashar Disoki
Higher Institute for Applied Sciences and Technology (HIAST)
1 shared publication
Latest Publications
- 25 September 2026
- Published by Springer Nature
- p. 325-334
Inflated Performance in fMRI-Based ASD Diagnosis: A Reproducibility Study of Data Leakage in Feature Selection Pipelines
- 25 September 2026
- Published by Springer Nature
- p. 325-334
Inflated Performance in fMRI-Based ASD Diagnosis: A Reproducibility Study of Data Leakage in Feature Selection Pipelines
- 29 August 2026
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 29 (3) , 182
Enhancing cross-patient generalization in AI-based Parkinson’s disease detection
- 29 August 2026
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 29 (3) , 182
Enhancing cross-patient generalization in AI-based Parkinson’s disease detection
- Open Access
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 20803-20825
Automated Detection of Self-Admitted Technical Debt: A Systematic Literature Review
In modern software development, developers frequently introduce comments that describe temporary solutions, incomplete implementations, or deferred improvements. These comments, commonly referred to as Self-Admitted Technical Debt (SATD), may provide short-term flexibility but can accumulate into long-term maintenance challenges and quality degradation. This paper presents a systematic literature review of automated SATD detection research published between 2015 and 2025. Following established systematic review guidelines, we analyzed 46 primary studies selected from an initial pool of 1,537 publications. The review provides a structured synthesis of the field by: 1) identifying and categorizing the main SATD detection objectives; 2) analyzing representation techniques for textual, structural, and hybrid inputs; 3) comparing learning approaches ranging from traditional machine learning to transformer-based and large language models; and 4) summarizing evaluation practices and performance trends. Our findings reveal a clear methodological evolution from keyword-based and feature-engineered models toward context-aware and multi-modal architectures. While transformer-based approaches such as BERT and CodeBERT demonstrate strong potential, their adoption is constrained by limited benchmark datasets, inconsistent evaluation protocols, and a lack of explainability. To address these challenges, the review highlights key research gaps and outlines future directions, including standardized benchmarks, explainable SATD detection, and cross-project generalization. Overall, this study consolidates a decade of SATD research into a unified perspective and provides actionable guidance for developing more robust, interpretable, and scalable SATD detection techniques to support sustainable software maintenance.
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 20803-20825
Open AccessAutomated Detection of Self-Admitted Technical Debt: A Systematic Literature Review
In modern software development, developers frequently introduce comments that describe temporary solutions, incomplete implementations, or deferred improvements. These comments, commonly referred to as Self-Admitted Technical Debt (SATD), may provide short-term flexibility but can accumulate into long-term maintenance challenges and quality degradation. This paper presents a systematic literature review of automated SATD detection research published between 2015 and 2025. Following established systematic review guidelines, we analyzed 46 primary studies selected from an initial pool of 1,537 publications. The review provides a structured synthesis of the field by: 1) identifying and categorizing the main SATD detection objectives; 2) analyzing representation techniques for textual, structural, and hybrid inputs; 3) comparing learning approaches ranging from traditional machine learning to transformer-based and large language models; and 4) summarizing evaluation practices and performance trends. Our findings reveal a clear methodological evolution from keyword-based and feature-engineered models toward context-aware and multi-modal architectures. While transformer-based approaches such as BERT and CodeBERT demonstrate strong potential, their adoption is constrained by limited benchmark datasets, inconsistent evaluation protocols, and a lack of explainability. To address these challenges, the review highlights key research gaps and outlines future directions, including standardized benchmarks, explainable SATD detection, and cross-project generalization. Overall, this study consolidates a decade of SATD research into a unified perspective and provides actionable guidance for developing more robust, interpretable, and scalable SATD detection techniques to support sustainable software maintenance.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 883-891
HIAST at QIAS 2025: Retrieval-Augmented LLMs with Top-Hit Web Evidence for Arabic Islamic Reasoning QA
Mohamed Motasim Hamed, Nada Ghneim, Riad Sonbol. Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 883-891
Open AccessHIAST at QIAS 2025: Retrieval-Augmented LLMs with Top-Hit Web Evidence for Arabic Islamic Reasoning QA
Mohamed Motasim Hamed, Nada Ghneim, Riad Sonbol. Proceedings of The Third Arabic Natural Language Processing Conference: Shared Tasks. 2025.
- 28 March 2023
- Published by Springer Nature in SN Computer Science
- Vol. 4 (3) , 1-16
A Machine Translation Like Approach to Generate Business Process Model from Textual Description
- 28 March 2023
- Published by Springer Nature in SN Computer Science
- Vol. 4 (3) , 1-16
A Machine Translation Like Approach to Generate Business Process Model from Textual Description
- Open Access
- 13 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 62811-62830
The Use of NLP-Based Text Representation Techniques to Support Requirement Engineering Tasks: A Systematic Mapping Review
Natural Language Processing (NLP) is widely used to support the automation of different Requirements Engineering (RE) tasks. Most of the proposed approaches start with various NLP steps that analyze requirements statements, extract their linguistic information, and convert them to easy-to-process representations, such as lists of features or embedding-based vector representations. These NLP-based representations are usually used at a later stage as inputs for machine learning techniques or rule-based methods. Thus, requirements representations play a major role in determining the accuracy of different approaches. In this paper, we conducted a survey in the form of a systematic literature mapping (classification) to find out (1) what are the representations used in RE tasks literature, (2) what is the main focus of these works, (3) what are the main research directions in this domain, and (4) what are the gaps and potential future directions. After compiling an initial pool of 2,227 papers, and applying a set of inclusion/exclusion criteria, we obtained a final pool containing 104 relevant papers. Our survey shows that the research direction has changed from the use of lexical and syntactic features to the use of advanced embedding techniques, especially in the last two years. Using advanced embedding representations has proved its effectiveness in most RE tasks (such as requirement analysis, extracting requirements from reviews and forums, and semantic-level quality tasks). However, representations that are based on lexical and syntactic features are still more appropriate for other RE tasks (such as modeling and syntax-level quality tasks) since they provide the required information for the rules and regular expressions used when handling these tasks. In addition, we identify four gaps in the existing literature, why they matter, and how future research can begin to address them.
- 13 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 62811-62830
Open AccessThe Use of NLP-Based Text Representation Techniques to Support Requirement Engineering Tasks: A Systematic Mapping Review
Natural Language Processing (NLP) is widely used to support the automation of different Requirements Engineering (RE) tasks. Most of the proposed approaches start with various NLP steps that analyze requirements statements, extract their linguistic information, and convert them to easy-to-process representations, such as lists of features or embedding-based vector representations. These NLP-based representations are usually used at a later stage as inputs for machine learning techniques or rule-based methods. Thus, requirements representations play a major role in determining the accuracy of different approaches. In this paper, we conducted a survey in the form of a systematic literature mapping (classification) to find out (1) what are the representations used in RE tasks literature, (2) what is the main focus of these works, (3) what are the main research directions in this domain, and (4) what are the gaps and potential future directions. After compiling an initial pool of 2,227 papers, and applying a set of inclusion/exclusion criteria, we obtained a final pool containing 104 relevant papers. Our survey shows that the research direction has changed from the use of lexical and syntactic features to the use of advanced embedding techniques, especially in the last two years. Using advanced embedding representations has proved its effectiveness in most RE tasks (such as requirement analysis, extracting requirements from reviews and forums, and semantic-level quality tasks). However, representations that are based on lexical and syntactic features are still more appropriate for other RE tasks (such as modeling and syntax-level quality tasks) since they provide the required information for the rules and regular expressions used when handling these tasks. In addition, we identify four gaps in the existing literature, why they matter, and how future research can begin to address them.
- Open Access
The Use of NLP-Based Text Representation Techniques to Support Requirement Engineering Tasks: A Systematic Mapping Review
Natural Language Processing (NLP) is widely used to support the automation of different Requirements Engineering (RE) tasks. Most of the proposed approaches start with various NLP steps that analyze requirements statements, extract their linguistic information, and convert them to easy-to-process representations, such as lists of features or embedding-based vector representations. These NLP-based representations are usually used at a later stage as inputs for machine learning techniques or rule-based methods. Thus, requirements representations play a major role in determining the accuracy of different approaches. In this paper, we conducted a survey in the form of a systematic literature mapping (classification) to find out (1) what are the representations used in RE tasks literature, (2) what is the main focus of these works, (3) what are the main research directions in this domain, and (4) what are the gaps and potential future directions. After compiling an initial pool of 2,227 papers, and applying a set of inclusion/exclusion criteria, we obtained a final pool containing 104 relevant papers. Our survey shows that the research direction has changed from the use of lexical and syntactic features to the use of advanced embedding techniques, especially in the last two years. Using advanced embedding representations has proved its effectiveness in most RE tasks (such as requirement analysis, extracting requirements from reviews and forums, and semantic-level quality tasks). However, representations that are based on lexical and syntactic features are still more appropriate for other RE tasks (such as modeling and syntax-level quality tasks) since they provide the required information for the rules and regular expressions used when handling these tasks. In addition, we identify four gaps in the existing literature, why they matter, and how future research can begin to address them.
Open AccessThe Use of NLP-Based Text Representation Techniques to Support Requirement Engineering Tasks: A Systematic Mapping Review
Natural Language Processing (NLP) is widely used to support the automation of different Requirements Engineering (RE) tasks. Most of the proposed approaches start with various NLP steps that analyze requirements statements, extract their linguistic information, and convert them to easy-to-process representations, such as lists of features or embedding-based vector representations. These NLP-based representations are usually used at a later stage as inputs for machine learning techniques or rule-based methods. Thus, requirements representations play a major role in determining the accuracy of different approaches. In this paper, we conducted a survey in the form of a systematic literature mapping (classification) to find out (1) what are the representations used in RE tasks literature, (2) what is the main focus of these works, (3) what are the main research directions in this domain, and (4) what are the gaps and potential future directions. After compiling an initial pool of 2,227 papers, and applying a set of inclusion/exclusion criteria, we obtained a final pool containing 104 relevant papers. Our survey shows that the research direction has changed from the use of lexical and syntactic features to the use of advanced embedding techniques, especially in the last two years. Using advanced embedding representations has proved its effectiveness in most RE tasks (such as requirement analysis, extracting requirements from reviews and forums, and semantic-level quality tasks). However, representations that are based on lexical and syntactic features are still more appropriate for other RE tasks (such as modeling and syntax-level quality tasks) since they provide the required information for the rules and regular expressions used when handling these tasks. In addition, we identify four gaps in the existing literature, why they matter, and how future research can begin to address them.
- 4 May 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 248
Learning software requirements syntax: An unsupervised approach to recognize templates
- 4 May 2022
- Published by Elsevier in Knowledge-Based Systems
- Vol. 248
Learning software requirements syntax: An unsupervised approach to recognize templates
- Open Access
- 9 February 2022
- Published by Springer Nature in Research Square
A Machine Translation Like Approach to Generate Business Process Model From Textual Description
Modeling is one of the core tasks in Business Process Management (BPM). It represents the most critical step in the BPM life cycle and is considered as a time consuming and costly task. These challenges raised the question of how researchers can save this cost by building tools that could support modeling experts in their work to reduce the manual workload. In this paper, we propose a Machine Translation (MT) like approach to deal with the problem of generating a business process model based on a textual description. We chose to follow a semantic transfer-based MT approach. Our approach consists of two main phases: The natural Language Analysis phase and BPMN diagram generation. Natural Language Analysis phase aims to analyze the text and extract the required knowledge. One of the main outputs for this phase is a Concept Map which summarizes the concepts of the related domain and the relationships between these concepts. This map represents a background for our processing in the second phase where we try to generate the "translation", which is the BPMN diagram in our case. We achieve our goal in the second phase via a set of semantic, syntactic, and morphological manipulations. The approach has been implemented and evaluated using a similarity metric based on the Graph Edit Distance. The results show that the proposed approach was able to generate models that are more than 81% similar to those created manually by a human, outperforming the state of the art in this topic.
- 9 February 2022
- Published by Springer Nature in Research Square
Open AccessA Machine Translation Like Approach to Generate Business Process Model From Textual Description
Modeling is one of the core tasks in Business Process Management (BPM). It represents the most critical step in the BPM life cycle and is considered as a time consuming and costly task. These challenges raised the question of how researchers can save this cost by building tools that could support modeling experts in their work to reduce the manual workload. In this paper, we propose a Machine Translation (MT) like approach to deal with the problem of generating a business process model based on a textual description. We chose to follow a semantic transfer-based MT approach. Our approach consists of two main phases: The natural Language Analysis phase and BPMN diagram generation. Natural Language Analysis phase aims to analyze the text and extract the required knowledge. One of the main outputs for this phase is a Concept Map which summarizes the concepts of the related domain and the relationships between these concepts. This map represents a background for our processing in the second phase where we try to generate the "translation", which is the BPMN diagram in our case. We achieve our goal in the second phase via a set of semantic, syntactic, and morphological manipulations. The approach has been implemented and evaluated using a similarity metric based on the Graph Edit Distance. The results show that the proposed approach was able to generate models that are more than 81% similar to those created manually by a human, outperforming the state of the art in this topic.
- Open Access
- 1 June 2018
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 8 (3) , 1766-1773
Anaphora Resolution in Business Process Requirement Engineering
Anaphora resolution (AR) is one of the most important tasks in natural language processing which focuses on the problem of resolving what a pronoun, or a noun phrase refers to. Moreover, AR plays an essential role when dealing with business process textual description, either when trying to discover the process model from the text, or when validating an existing model. It helps these systems in discovering the core components in any process model (actors and objects).In this paper, we propose a domain specific AR system. The approach starts by automatically generating the concept map of the text, then the system uses this map to resolve references using the syntactic and semantic relations in the concept map. The approach outperforms the state-of-the art performance in the domain of business process texts with more than 73% accuracy. In addition, this approach could be easily adopted to resolve references in other domains.
- 1 June 2018
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 8 (3) , 1766-1773
Open AccessAnaphora Resolution in Business Process Requirement Engineering
Anaphora resolution (AR) is one of the most important tasks in natural language processing which focuses on the problem of resolving what a pronoun, or a noun phrase refers to. Moreover, AR plays an essential role when dealing with business process textual description, either when trying to discover the process model from the text, or when validating an existing model. It helps these systems in discovering the core components in any process model (actors and objects).In this paper, we propose a domain specific AR system. The approach starts by automatically generating the concept map of the text, then the system uses this map to resolve references using the syntactic and semantic relations in the concept map. The approach outperforms the state-of-the art performance in the domain of business process texts with more than 73% accuracy. In addition, this approach could be easily adopted to resolve references in other domains.