Touseef Tahir
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Touseef Tahir has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Bilal Hassan
Faculty of Engineering & Environment, Northumbria University, London Campus, London E1 7HT, UK
2 shared publications Fiza Talha
COMSATS University Islamabad
2 shared publicationsTalha Nadeem
Yuan Ze University
2 shared publications- Ali Saeed
Department of Software Engineering University of Central Punjab Lahore Pakistan ucp.edu.pk
1 shared publication - Dileep Kumar
Department of Electronic, The Islamia University Bahawalpur, Bahawalpur, Pakistan
1 shared publication Ghulam Fatima
COMSATS University Islamabad,Department of Computer Science,Lahore,Pakistan
1 shared publication
Latest Publications
- Open Access
- 21 June 2026
- Published by Wiley in Engineering Reports
- Vol. 8 (6) , e70867
Optimizing Deep Neural Models for Early Dyslexia Detection Using Novel Bilingual Handwritten Dataset
- 21 June 2026
- Published by Wiley in Engineering Reports
- Vol. 8 (6) , e70867
Open AccessOptimizing Deep Neural Models for Early Dyslexia Detection Using Novel Bilingual Handwritten Dataset
- 1 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Detecting Ambiguities in Non-Functional Requirements Using Transformer-Driven Information Extraction
In software requirements engineering, ambiguous non-functional requirements can cause design inconsistencies and poor software quality. Manual ambiguity detection is time consuming and inefficient, particularly for large-scale requirements documents. Prior studies lack in handling ambiguous non-functional requirements and often analyze simple English statements instead of discussing NFRs. In this study, we emphasize detecting anaphoric, coordination, and missing-condition ambiguity in non-functional requirements. For anaphoric ambiguity detection, we applied SpanBERT due to its contextual capturing abilities. Coordination and missing-condition ambiguities were identified using a rule-based approach, i.e., spaCy's Named Entity Ruler. We conducted experiments on a significant dataset consisting of 2400 non-functional requirements from 16 different domains. Experimental results show that the suggested approach performs better than ChatGPT in terms of accuracy and consistency across the evaluated datasets. The proposed approach can assist requirement engineers and project managers in identifying ambiguities at an early stage of development. Timely detection helps reduce rework, associated costs, schedule risks, and improves overall software quality.
- 1 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Detecting Ambiguities in Non-Functional Requirements Using Transformer-Driven Information Extraction
In software requirements engineering, ambiguous non-functional requirements can cause design inconsistencies and poor software quality. Manual ambiguity detection is time consuming and inefficient, particularly for large-scale requirements documents. Prior studies lack in handling ambiguous non-functional requirements and often analyze simple English statements instead of discussing NFRs. In this study, we emphasize detecting anaphoric, coordination, and missing-condition ambiguity in non-functional requirements. For anaphoric ambiguity detection, we applied SpanBERT due to its contextual capturing abilities. Coordination and missing-condition ambiguities were identified using a rule-based approach, i.e., spaCy's Named Entity Ruler. We conducted experiments on a significant dataset consisting of 2400 non-functional requirements from 16 different domains. Experimental results show that the suggested approach performs better than ChatGPT in terms of accuracy and consistency across the evaluated datasets. The proposed approach can assist requirement engineers and project managers in identifying ambiguities at an early stage of development. Timely detection helps reduce rework, associated costs, schedule risks, and improves overall software quality.
- Open Access
- 1 January 2026
- Published by Wiley in Applied Computational Intelligence and Soft Computing
- Vol. 2026 (1)
Toward Intelligent Understanding of Urdu Text: A Deep Learning Perspective on Topic Classification
Urdu topic classification is an important problem in NLP; the purpose of this task is to automatically categorize Urdu texts to make them easier to organize, search, and analyze. A lot of research has been done for other languages like English, Arabic, and Chinese, but Urdu lacks comprehensive approaches. To fill this gap, this study evaluates 18 intelligent approaches using the Urdu Multi Domain Classification dataset, which comprises 34,819 Urdu sentences. Six machine learning methods—naive Bayes, SVM, random forest, KNN, decision tree, and MLP—were evaluated with bag‐of‐words, TF–IDF, and N‐grams, achieving a top accuracy of 97.08% with SVM. Four deep learning models (LSTM, BiLSTM, GRU, and SimpleRNN) with FastText embeddings were also tested, with BiLSTM reaching a top accuracy of 97.10%. Eight transformer‐based models (BERT‐mini, BERT‐base, DistilBERT‐base, BERT multilingual, XLM‐RoBERTa‐base, T5 small, multilingual T5 small, and multilingual T5 base) were explored. Multilingual T5 base achieved the highest accuracy, improving on previous results by 3.62%. Overall, the Multilingual T5‐base model achieves the highest accuracy, reaching 97.92% on the original dataset and 97.53% on the duplicate‐free dataset, outperforming the strongest baseline (max voting, 94.30%). The evaluation is carried out using four metrics: accuracy, precision, recall, and F 1 ‐score. The study shows that multilingual transformers are effective for low‐resource languages, bidirectional models capture context well, and evaluated multilingual generative approaches outperform discriminative ones.
- 1 January 2026
- Published by Wiley in Applied Computational Intelligence and Soft Computing
- Vol. 2026 (1)
Open AccessToward Intelligent Understanding of Urdu Text: A Deep Learning Perspective on Topic Classification
Urdu topic classification is an important problem in NLP; the purpose of this task is to automatically categorize Urdu texts to make them easier to organize, search, and analyze. A lot of research has been done for other languages like English, Arabic, and Chinese, but Urdu lacks comprehensive approaches. To fill this gap, this study evaluates 18 intelligent approaches using the Urdu Multi Domain Classification dataset, which comprises 34,819 Urdu sentences. Six machine learning methods—naive Bayes, SVM, random forest, KNN, decision tree, and MLP—were evaluated with bag‐of‐words, TF–IDF, and N‐grams, achieving a top accuracy of 97.08% with SVM. Four deep learning models (LSTM, BiLSTM, GRU, and SimpleRNN) with FastText embeddings were also tested, with BiLSTM reaching a top accuracy of 97.10%. Eight transformer‐based models (BERT‐mini, BERT‐base, DistilBERT‐base, BERT multilingual, XLM‐RoBERTa‐base, T5 small, multilingual T5 small, and multilingual T5 base) were explored. Multilingual T5 base achieved the highest accuracy, improving on previous results by 3.62%. Overall, the Multilingual T5‐base model achieves the highest accuracy, reaching 97.92% on the original dataset and 97.53% on the duplicate‐free dataset, outperforming the strongest baseline (max voting, 94.30%). The evaluation is carried out using four metrics: accuracy, precision, recall, and F 1 ‐score. The study shows that multilingual transformers are effective for low‐resource languages, bidirectional models capture context well, and evaluated multilingual generative approaches outperform discriminative ones.
- Open Access
- 10 August 2025
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 37 (8)
A Semiautomated Approach for Detecting Ambiguities in Software Requirements Using SpanBERT and Named Entity Recognition
Ambiguous user requirements present a challenge in software requirement engineering. A manual approach to handling ambiguity is time‐consuming. Software requirements are essential inputs to software development processes, including architecture and design, implementation, and testing. Requirement ambiguities lead to project cost overruns, delays in project delivery, and poor software product quality. Timely identification and correction of ambiguity can result in better software systems that meet product objectives and satisfy the needs of all stakeholders. This study explores various natural language processing techniques and SpanBERT (a variant of BERT). This research proposes a semiautomated approach for detecting anaphoric, coordination, and missing condition ambiguities in functional requirements. The proposed approach is validated on a new, original dataset containing 425 functional requirements from 16 domains. The ambiguities identified through our approach are compared with those detected manually and by ChatGPT. Our approach outperforms ChatGPT in detecting ambiguities. The proposed approach will aid project managers and requirement engineers in identifying ambiguities in requirement specifications, thereby helping to reduce cost overruns and delays in the software development process caused by requirement ambiguities.
- 10 August 2025
- Published by Wiley in Journal of Software: Evolution and Process
- Vol. 37 (8)
Open AccessA Semiautomated Approach for Detecting Ambiguities in Software Requirements Using SpanBERT and Named Entity Recognition
Ambiguous user requirements present a challenge in software requirement engineering. A manual approach to handling ambiguity is time‐consuming. Software requirements are essential inputs to software development processes, including architecture and design, implementation, and testing. Requirement ambiguities lead to project cost overruns, delays in project delivery, and poor software product quality. Timely identification and correction of ambiguity can result in better software systems that meet product objectives and satisfy the needs of all stakeholders. This study explores various natural language processing techniques and SpanBERT (a variant of BERT). This research proposes a semiautomated approach for detecting anaphoric, coordination, and missing condition ambiguities in functional requirements. The proposed approach is validated on a new, original dataset containing 425 functional requirements from 16 domains. The ambiguities identified through our approach are compared with those detected manually and by ChatGPT. Our approach outperforms ChatGPT in detecting ambiguities. The proposed approach will aid project managers and requirement engineers in identifying ambiguities in requirement specifications, thereby helping to reduce cost overruns and delays in the software development process caused by requirement ambiguities.
- Open Access
Cross-Project Multiclass Classification of EARS-Based Functional Requirements Utilizing Natural Language Processing, Machine Learning, and Deep Learning
Software requirements are primarily classified into functional and non-functional requirements. While research has explored automated multiclass classification of non-functional requirements, functional requirements remain largely unexplored. This study addressed that gap by introducing a comprehensive dataset comprising 9529 functional requirements from 315 diverse projects. The requirements are classified into five categories: ubiquitous, event-driven, state-driven, unwanted behavior, and optional capabilities. Natural Language Processing (NLP), machine learning (ML), and deep learning (DL) techniques are employed to enable automated classification. All software requirements underwent several procedures, including normalization and feature extraction techniques such as TF-IDF. A series of Machine learning (ML) and deep learning (DL) experiments were conducted to classify subcategories of functional requirements. Among the trained models, the convolutional neural network achieved the highest performance, with an accuracy of 93, followed by the long short-term memory network with an accuracy of 92, outperforming traditional decision-tree-based methods. This work offers a foundation for precise requirement classification tools by providing both the dataset and an automated classification approach.
Open AccessCross-Project Multiclass Classification of EARS-Based Functional Requirements Utilizing Natural Language Processing, Machine Learning, and Deep Learning
Software requirements are primarily classified into functional and non-functional requirements. While research has explored automated multiclass classification of non-functional requirements, functional requirements remain largely unexplored. This study addressed that gap by introducing a comprehensive dataset comprising 9529 functional requirements from 315 diverse projects. The requirements are classified into five categories: ubiquitous, event-driven, state-driven, unwanted behavior, and optional capabilities. Natural Language Processing (NLP), machine learning (ML), and deep learning (DL) techniques are employed to enable automated classification. All software requirements underwent several procedures, including normalization and feature extraction techniques such as TF-IDF. A series of Machine learning (ML) and deep learning (DL) experiments were conducted to classify subcategories of functional requirements. Among the trained models, the convolutional neural network achieved the highest performance, with an accuracy of 93, followed by the long short-term memory network with an accuracy of 92, outperforming traditional decision-tree-based methods. This work offers a foundation for precise requirement classification tools by providing both the dataset and an automated classification approach.
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Software
- Vol. 2025 (1)
Automated NLP‐Based Classification of Nonfunctional Requirements in Blockchain and Cross‐Domain Software Systems Using BERT and Machine Learning
Automated nonfunctional requirements (NFRs) classification enhances consistency and traceability by systematically labeling requirements, saving effort, supporting early architectural and testing decisions, improving stakeholder communication, and enabling quality across diverse software domains. While prior work has applied natural language processing (NLP) and machine learning (ML) to NFR classification, existing datasets are often limited in size, domain diversity, and contextual richness. This study presents a novel dataset comprising over 2400 NFRs spanning 269 software projects across 26 software application domains, including nine blockchain projects. The raw requirements are standardized using Rupp’s boilerplate to reduce vagueness and ambiguity, and the classification of NFRs types follows ISO/IEC 25,010 definitions. We employ a range of traditional ML, deep learning (DL), and a transformer‐based model (i.e., BERT‐base) for automated classification of NFRs, evaluating performance across cross‐domain and blockchain‐specific NFRs. Results highlight that domain‐aware adaptation significantly enhances classification accuracy, with traditional ML and DL models showing strong performance on blockchain requirements. This work contributes a publicly available, context‐rich dataset and provides empirical insights into the effectiveness of NLP‐based NFR classification in both general and blockchain‐specific settings.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Software
- Vol. 2025 (1)
Open AccessAutomated NLP‐Based Classification of Nonfunctional Requirements in Blockchain and Cross‐Domain Software Systems Using BERT and Machine Learning
Automated nonfunctional requirements (NFRs) classification enhances consistency and traceability by systematically labeling requirements, saving effort, supporting early architectural and testing decisions, improving stakeholder communication, and enabling quality across diverse software domains. While prior work has applied natural language processing (NLP) and machine learning (ML) to NFR classification, existing datasets are often limited in size, domain diversity, and contextual richness. This study presents a novel dataset comprising over 2400 NFRs spanning 269 software projects across 26 software application domains, including nine blockchain projects. The raw requirements are standardized using Rupp’s boilerplate to reduce vagueness and ambiguity, and the classification of NFRs types follows ISO/IEC 25,010 definitions. We employ a range of traditional ML, deep learning (DL), and a transformer‐based model (i.e., BERT‐base) for automated classification of NFRs, evaluating performance across cross‐domain and blockchain‐specific NFRs. Results highlight that domain‐aware adaptation significantly enhances classification accuracy, with traditional ML and DL models showing strong performance on blockchain requirements. This work contributes a publicly available, context‐rich dataset and provides empirical insights into the effectiveness of NLP‐based NFR classification in both general and blockchain‐specific settings.
- 9 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Exploring Data-Driven Real Estate Price Prediction in a Developing Country: The Case of Pakistan
The price prediction is critical for making better decisions when buying or selling a real estate. Currently, there is a lack of data-driven price prediction studies on Pakistani real estate market, which publicly share their datasets and the sources of data collection. In addition, mobile and webapplications of Pakistani electronic markets are also missing the data-driven real estate price prediction. This study collected data of 50 thousand real estate properties of Lahore between 2020 and 2024. The data collected from oldest and most used mobile and web-application. The regression-based machine learning (ML) and deep learning (DL) models are trained on original values of dataset and transformed values (using log and z-score) and subsets of the dataset. The ensemble ML model (i.e., Extra Trees) trained on a subset of features that are selected using mutual information performed the best with evaluation measures of R2 = 0.96, RMSE = 0.09, MAE = 0.05, and MAPE =0.008. The DL model (i.e., Bi-LSTM) trained on logged transformed complete dataset achieved best results based on evaluation measures i.e. R2 = 0.89, RMSE = 0.14, MAE=0.09, MAPE=0.01. The log transformation of feature values helped to achieve best performances of both ML and DL models.
- 9 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Exploring Data-Driven Real Estate Price Prediction in a Developing Country: The Case of Pakistan
The price prediction is critical for making better decisions when buying or selling a real estate. Currently, there is a lack of data-driven price prediction studies on Pakistani real estate market, which publicly share their datasets and the sources of data collection. In addition, mobile and webapplications of Pakistani electronic markets are also missing the data-driven real estate price prediction. This study collected data of 50 thousand real estate properties of Lahore between 2020 and 2024. The data collected from oldest and most used mobile and web-application. The regression-based machine learning (ML) and deep learning (DL) models are trained on original values of dataset and transformed values (using log and z-score) and subsets of the dataset. The ensemble ML model (i.e., Extra Trees) trained on a subset of features that are selected using mutual information performed the best with evaluation measures of R2 = 0.96, RMSE = 0.09, MAE = 0.05, and MAPE =0.008. The DL model (i.e., Bi-LSTM) trained on logged transformed complete dataset achieved best results based on evaluation measures i.e. R2 = 0.89, RMSE = 0.14, MAE=0.09, MAPE=0.01. The log transformation of feature values helped to achieve best performances of both ML and DL models.
- Open Access
- 27 August 2024
- Published by Wiley
A Structural Equation Modeling Based Evaluation of Relationship between Software Requirement Qualities and Project Success Factors
Context: Successful software projects control the challenges of project delays, cost overrun and delivering quality software products that satisfy customer needs. The specified software requirements are fundamental input of planning, executing, monitoring and controlling software development processes. In addition, software requirements drive software design, code, test cases, and documentation of software product. Therefore, quality of software requirements hold a critical importance for a successful software project. Objectives: This study empirically evaluates the perception of software professionals regarding relationship between qualities of software requirements and project success factors. Method: The study comprises of two steps. First we conducted a systematic mapping study and we identified 16 requirement qualities and their related 4 project success factors through analyzing 25 primary studies published between 2000 and 2024. In addition, we proposed a research model using the requirement qualities and the success factors. Second, we statistically validated the research model based on a survey among 202 software professionals. The Structural Equation Modeling (SEM) is applied on the survey responses to identify statistically significant requirement qualities and their relationship with the success factors. The SEM uses exploratory and confirmatory factor analysis and hypothesis testing. Results: The SEM confirms that survey responses of software professionals fit the research model. It confirms strong belief of software professionals that ten out of sixteen requirement qualities (RQ) are related to project success in terms of the cost containment, quality of software products, and effective software project management. The RQ include frozen system requirements, volatile requirements, requirement creep, unattainable requirements, and requirement change control, gold plating, requirements forward traceability, requirements backward traceability and verifiable requirements. Discussion: This study identified and evaluated requirement qualities related to project success factors. We recommend project managers to consider the proposed research model in better planning and executing requirements management process during software development life cycle.
- 27 August 2024
- Published by Wiley
Open AccessA Structural Equation Modeling Based Evaluation of Relationship between Software Requirement Qualities and Project Success Factors
Context: Successful software projects control the challenges of project delays, cost overrun and delivering quality software products that satisfy customer needs. The specified software requirements are fundamental input of planning, executing, monitoring and controlling software development processes. In addition, software requirements drive software design, code, test cases, and documentation of software product. Therefore, quality of software requirements hold a critical importance for a successful software project. Objectives: This study empirically evaluates the perception of software professionals regarding relationship between qualities of software requirements and project success factors. Method: The study comprises of two steps. First we conducted a systematic mapping study and we identified 16 requirement qualities and their related 4 project success factors through analyzing 25 primary studies published between 2000 and 2024. In addition, we proposed a research model using the requirement qualities and the success factors. Second, we statistically validated the research model based on a survey among 202 software professionals. The Structural Equation Modeling (SEM) is applied on the survey responses to identify statistically significant requirement qualities and their relationship with the success factors. The SEM uses exploratory and confirmatory factor analysis and hypothesis testing. Results: The SEM confirms that survey responses of software professionals fit the research model. It confirms strong belief of software professionals that ten out of sixteen requirement qualities (RQ) are related to project success in terms of the cost containment, quality of software products, and effective software project management. The RQ include frozen system requirements, volatile requirements, requirement creep, unattainable requirements, and requirement change control, gold plating, requirements forward traceability, requirements backward traceability and verifiable requirements. Discussion: This study identified and evaluated requirement qualities related to project success factors. We recommend project managers to consider the proposed research model in better planning and executing requirements management process during software development life cycle.