Onaiza Maqbool
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Onaiza Maqbool has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Jaweria Kanwal
National University of Modern Languages, Islamabad, Pakistan
3 shared publications - Haroon A. Babri
Department of Electrical Engineering, University of Engineering and Technology, Lahore 54890, Pakistan
2 shared publications - Ali Daud
Faculty of Resilience, Rabdan Academy, Abu Dhabi, United Arab Emirates
1 shared publication - Arjumand Fatima
Department of Computer Science, Quaid-i-Azam University, Islamabad, Pakistan
1 shared publication - Aroosa Hameed
Computer Science, Quaid-i-Azam University, 66757 Islamabad Pakistan
1 shared publication - Farooq Zaman
Information Technology University, Lahore, Pakistan
1 shared publication
Latest Publications
- Open Access
On the Sustainability of Software Recommendations: Analyzing the Least-Answered Site on the Stack Exchange Network
As Stack Overflow considers asking for any sort of recommendation to be off-topic, Stack Exchange Network launched Software Recommendations, a particular question-answering (Q&A) community for this purpose. Out of 182 such Q&A sites, Software Recommendations has been the least-answered site for the last 5 years, with only a 57% answered rate. We analyzed the complete data dump of Software Recommendations, containing data from its inception in 2014 to October 2025, to determine what makes it the least-answered site. We observed that incorrect tagging reduces the chances of questions being discovered by experts, and for this reason, certain topics receive better answers than others. Most questions are asked by users with a reputation of less than 300, while most of the answers are provided by those having a higher reputation. In total, 78.86% of users registered on the site act as silent observers and only 21.14% are involved in Q&A activities. Although knowledge-sharing activities on the site have decreased over this period, new users keep joining, which shows the need for software recommendations despite the increasing popularity of AI tools. Although similar questions are often asked and get closed as off-topic on sister sites, a very small proportion of such questions are migrated to Software Recommendations due to the lengthy migration process and reputation reversal on that site, which holds Software Recommendations back from attracting knowledgeable users and gaining popularity. Our findings suggest that the Stack Exchange community needs to revise its incentive mechanisms and devise ways to attract knowledgeable Stack Overflow users to the Software Recommendations site.
Open AccessOn the Sustainability of Software Recommendations: Analyzing the Least-Answered Site on the Stack Exchange Network
As Stack Overflow considers asking for any sort of recommendation to be off-topic, Stack Exchange Network launched Software Recommendations, a particular question-answering (Q&A) community for this purpose. Out of 182 such Q&A sites, Software Recommendations has been the least-answered site for the last 5 years, with only a 57% answered rate. We analyzed the complete data dump of Software Recommendations, containing data from its inception in 2014 to October 2025, to determine what makes it the least-answered site. We observed that incorrect tagging reduces the chances of questions being discovered by experts, and for this reason, certain topics receive better answers than others. Most questions are asked by users with a reputation of less than 300, while most of the answers are provided by those having a higher reputation. In total, 78.86% of users registered on the site act as silent observers and only 21.14% are involved in Q&A activities. Although knowledge-sharing activities on the site have decreased over this period, new users keep joining, which shows the need for software recommendations despite the increasing popularity of AI tools. Although similar questions are often asked and get closed as off-topic on sister sites, a very small proportion of such questions are migrated to Software Recommendations due to the lengthy migration process and reputation reversal on that site, which holds Software Recommendations back from attracting knowledgeable users and gaining popularity. Our findings suggest that the Stack Exchange community needs to revise its incentive mechanisms and devise ways to attract knowledgeable Stack Overflow users to the Software Recommendations site.
- Open Access
- 15 April 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 23 (4) , 1-17
Leveraging Bidirectionl LSTM with CRFs for Pashto Tagging
Part-of-speech tagging plays a vital role in text processing and natural language understanding. Very few attempts have been made in the past for tagging Pashto Part-of-Speech. In this work, we present a Long Short-term Memory–based approach for Pashto part-of-speech tagging with special focus on ambiguity resolution. Initially, we created a corpus of Pashto sentences having words with multiple meanings and their tags. We introduce a powerful sentences representation and new architecture for Pashto text processing. The accuracy of the proposed approach is compared with state-of-the-art Hidden Markov Model. Our Model shows 87.60% accuracy for all words excluding punctuation and 95.45% for ambiguous words; however, Hidden Markov Model shows 78.37% and 44.72% accuracy, respectively. Results show that our approach outperforms Hidden Markov Model in Part-of-Speech tagging for Pashto text.
- 15 April 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Asian and Low-Resource Language Information Processing
- Vol. 23 (4) , 1-17
Open AccessLeveraging Bidirectionl LSTM with CRFs for Pashto Tagging
Part-of-speech tagging plays a vital role in text processing and natural language understanding. Very few attempts have been made in the past for tagging Pashto Part-of-Speech. In this work, we present a Long Short-term Memory–based approach for Pashto part-of-speech tagging with special focus on ambiguity resolution. Initially, we created a corpus of Pashto sentences having words with multiple meanings and their tags. We introduce a powerful sentences representation and new architecture for Pashto text processing. The accuracy of the proposed approach is compared with state-of-the-art Hidden Markov Model. Our Model shows 87.60% accuracy for all words excluding punctuation and 95.45% for ambiguous words; however, Hidden Markov Model shows 78.37% and 44.72% accuracy, respectively. Results show that our approach outperforms Hidden Markov Model in Part-of-Speech tagging for Pashto text.
- Open Access
- 3 May 2023
- Published by Springer Nature in Research Square
Leveraging Bidirectionl LSTM with CRFs for Pashto tagging
Part-of-speech tagging plays a vital role in text processing and natural language understanding. Very few attempts have been made in the past for tagging Pashto Part-of-Speech. In this work, we present LSTM based approach for Pashto part-of-speech tagging with special focus on ambiguity resolution. Initially we created a corpus of Pashto sentences having words with multiple meanings and their tags. We introduce a powerful sentences representation and new architecture for Pashto text processing. The accuracy of the proposed approach is compared with state-of-the-art Hidden Markov Model. Our Model shows 87.60\% accuracy for all words excluding punctuations and 95.45\% for ambiguous words, on the other hand Hidden Markov Model shows 78.37\% and 44.72\% accuracy respectively. Results show that our approach outperform Hidden Markov Model in Part-of-Speech tagging for Pashto text.
- 3 May 2023
- Published by Springer Nature in Research Square
Open AccessLeveraging Bidirectionl LSTM with CRFs for Pashto tagging
Part-of-speech tagging plays a vital role in text processing and natural language understanding. Very few attempts have been made in the past for tagging Pashto Part-of-Speech. In this work, we present LSTM based approach for Pashto part-of-speech tagging with special focus on ambiguity resolution. Initially we created a corpus of Pashto sentences having words with multiple meanings and their tags. We introduce a powerful sentences representation and new architecture for Pashto text processing. The accuracy of the proposed approach is compared with state-of-the-art Hidden Markov Model. Our Model shows 87.60\% accuracy for all words excluding punctuations and 95.45\% for ambiguous words, on the other hand Hidden Markov Model shows 78.37\% and 44.72\% accuracy respectively. Results show that our approach outperform Hidden Markov Model in Part-of-Speech tagging for Pashto text.
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 56 (4) , 4457-4466
Privacy-Preserved Ranking of Industrial Sensing Services Using Topological Information
The sensing-as-a-service paradigm has realized a number of contemporary industrial Internet-of-things applications. In this article, we have considered an order-driven scenario of a smart factory, where wearable devices provide various services and communicate with the service providers. The discovery process generates numerous smart factory services. The selection of an appropriate (or a set of) service(s) remains a challenge while preserving the service data privacy. It is required to involve an anonymous communication mechanism to design a privacy-preserved ranking model. The prevalent techniques for the prioritization of semantically equivalent sensor-provided services rely on quality-of-service (QoS) information. However, the QoS information is not always readily available at the node level. Moreover, the existing topological information-based (i.e., node importance and energy) solutions do not consider imperative features, such as a degree. The objective of this study is to design a privacy-preserved ranking model based on the onion routing technique and features along with the stochastic shortest route. Onion routing enables anonymous communication and prevents unauthorized entities from accessing ranking results. The weighted valuation is then derived to compute the cost of the homogeneous and dynamic sensor-provided services. Finally, the ranking is computed based on each service cost. The proposed model is extensively evaluated in two different network configurations of varying sizes. The evaluation results show that the proposed method performs 10% better in terms of ranking quality and 32% in terms of energy efficiency across different network configurations, as compared with the existing cost-based method while offering a desired level of privacy.
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. 56 (4) , 4457-4466
Privacy-Preserved Ranking of Industrial Sensing Services Using Topological Information
The sensing-as-a-service paradigm has realized a number of contemporary industrial Internet-of-things applications. In this article, we have considered an order-driven scenario of a smart factory, where wearable devices provide various services and communicate with the service providers. The discovery process generates numerous smart factory services. The selection of an appropriate (or a set of) service(s) remains a challenge while preserving the service data privacy. It is required to involve an anonymous communication mechanism to design a privacy-preserved ranking model. The prevalent techniques for the prioritization of semantically equivalent sensor-provided services rely on quality-of-service (QoS) information. However, the QoS information is not always readily available at the node level. Moreover, the existing topological information-based (i.e., node importance and energy) solutions do not consider imperative features, such as a degree. The objective of this study is to design a privacy-preserved ranking model based on the onion routing technique and features along with the stochastic shortest route. Onion routing enables anonymous communication and prevents unauthorized entities from accessing ranking results. The weighted valuation is then derived to compute the cost of the homogeneous and dynamic sensor-provided services. Finally, the ranking is computed based on each service cost. The proposed model is extensively evaluated in two different network configurations of varying sizes. The evaluation results show that the proposed method performs 10% better in terms of ranking quality and 32% in terms of energy efficiency across different network configurations, as compared with the existing cost-based method while offering a desired level of privacy.
- 5 September 2017
- Published by Emerald Publishing in Program: electronic library and information systems
- Vol. 51 (3) , 218-234
MFS-LDA: a multi-feature space tag recommendation model for cold start problem
Purpose: Tags are used to annotate resources on social media platforms. Most tag recommendation methods use popular tags, but in the case of new resources that are as yet untagged (the cold start problem), popularity-based tag recommendation methods fail to work. The purpose of this paper is to propose a novel model for tag recommendation called multi-feature space latent Dirichlet allocation (MFS-LDA) for cold start problem. Design/methodology/approach: MFS-LDA is a novel latent Dirichlet allocation (LDA)-based model which exploits multiple feature spaces (title, contents, and tags) for recommending tags. Exploiting multiple feature spaces allows MFS-LDA to recommend tags even if data from a feature space is missing (the cold start problem). Findings: Evaluation of a publicly available data set consisting of around 20,000 Wikipedia articles that are tagged on a social bookmarking website shows a significant improvement over existing LDA-based tag recommendation methods. Originality/value: The originality of MFS-LDA lies in segregation of features for removing bias toward dominant features and in synchronization of multiple feature space for tag recommendation.
- 5 September 2017
- Published by Emerald Publishing in Program: electronic library and information systems
- Vol. 51 (3) , 218-234
MFS-LDA: a multi-feature space tag recommendation model for cold start problem
Purpose: Tags are used to annotate resources on social media platforms. Most tag recommendation methods use popular tags, but in the case of new resources that are as yet untagged (the cold start problem), popularity-based tag recommendation methods fail to work. The purpose of this paper is to propose a novel model for tag recommendation called multi-feature space latent Dirichlet allocation (MFS-LDA) for cold start problem. Design/methodology/approach: MFS-LDA is a novel latent Dirichlet allocation (LDA)-based model which exploits multiple feature spaces (title, contents, and tags) for recommending tags. Exploiting multiple feature spaces allows MFS-LDA to recommend tags even if data from a feature space is missing (the cold start problem). Findings: Evaluation of a publicly available data set consisting of around 20,000 Wikipedia articles that are tagged on a social bookmarking website shows a significant improvement over existing LDA-based tag recommendation methods. Originality/value: The originality of MFS-LDA lies in segregation of features for removing bias toward dominant features and in synchronization of multiple feature space for tag recommendation.
- 5 March 2012
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 27 (2) , 397-412
Bug Prioritization to Facilitate Bug Report Triage
- 5 March 2012
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 27 (2) , 397-412
Bug Prioritization to Facilitate Bug Report Triage
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Bayesian Learning for Software Architecture Recovery
Understanding a software system at the architectural level is especially important when the system is to be adapted to meet changing requirements. However, architectural documentation is often unavailable or out-of-date. In this paper, we explore the use of Bayesian learning methods for automatic recovery of a software system's architecture, given incomplete or out-of-date documentation. We employ software modules with known classifications to train the Naive Bayes Classifier. We then use the classifier to place new instances, i.e. new software modules, into appropriate sub-systems. We evaluate the performance of the classifier by conducting experiments on a software system, and compare the results obtained with a manually prepared architecture. We present an analysis of the results, and also discuss the assumptions under which the results are expected to be meaningful.
- 1 April 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Bayesian Learning for Software Architecture Recovery
Understanding a software system at the architectural level is especially important when the system is to be adapted to meet changing requirements. However, architectural documentation is often unavailable or out-of-date. In this paper, we explore the use of Bayesian learning methods for automatic recovery of a software system's architecture, given incomplete or out-of-date documentation. We employ software modules with known classifications to train the Naive Bayes Classifier. We then use the classifier to place new instances, i.e. new software modules, into appropriate sub-systems. We evaluate the performance of the classifier by conducting experiments on a software system, and compare the results obtained with a manually prepared architecture. We present an analysis of the results, and also discuss the assumptions under which the results are expected to be meaningful.
- 1 December 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 314-319
A Stability Analysis of Clustering Algorithms
The use of clustering for developing a description of a software system's architecture is fairly recent. Thus there is a need to evaluate various clustering algorithms and identify the ones which are expected to give good results for software. A criterion that can be used for evaluation is stability. A clustering algorithm is said to be stable if its output i.e. the clusters it produces, do not change drastically when small changes are made to the input data. The notion of stability is especially important when a software clustering algorithm is used to build a high level description of a software system that is currently under development. In this paper, we compare the stability of six hierarchical clustering algorithms by carrying out experiments on three open-source software systems. We also present an analysis of the results, which provides insight into the clustering process of the various algorithms
- 1 December 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 314-319
A Stability Analysis of Clustering Algorithms
The use of clustering for developing a description of a software system's architecture is fairly recent. Thus there is a need to evaluate various clustering algorithms and identify the ones which are expected to give good results for software. A criterion that can be used for evaluation is stability. A clustering algorithm is said to be stable if its output i.e. the clusters it produces, do not change drastically when small changes are made to the input data. The notion of stability is especially important when a software clustering algorithm is used to build a high level description of a software system that is currently under development. In this paper, we compare the stability of six hierarchical clustering algorithms by carrying out experiments on three open-source software systems. We also present an analysis of the results, which provides insight into the clustering process of the various algorithms