Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Malak Baslyman has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • mUXSmellDetection: An LLM-Assisted Framework for Automated UX Smell Detection in Mobile Apps

    by Haifa Alshammare, Mohammad Alshayeb, Malak Baslyman

    1. The rapid advancement of mobile device capabilities has accelerated the digitization of services previously delivered through traditional channels, leading to a shift toward mobile applications ...

  • Open Access

    Are We Aligned? A Preliminary Investigation of the Alignment of Responsible AI Values between LLMs and Human Judgment

    by Asma Yamani, Malak Baslyman, Moataz Ahmed

    Large Language Models (LLMs) are increasingly employed in software engineering tasks such as requirements elicitation, design, and evaluation, raising critical questions regarding their alignment with human judgments on responsible AI values. This study investigates how closely LLMs' value preferences align with those of two human groups: a US-representative sample and AI practitioners. We evaluate 23 LLMs across four tasks: (T1) selecting key responsible AI values, (T2) rating their importance in specific contexts, (T3) resolving trade-offs between competing values, and (T4) prioritizing software requirements that embody those values. The results show that LLMs generally align more closely with AI practitioners than with the US-representative sample, emphasizing fairness, privacy, transparency, safety, and accountability. However, inconsistencies appear between the values that LLMs claim to uphold (Tasks 1-3) and the way they prioritize requirements (Task 4), revealing gaps in faithfulness between stated and applied behavior. These findings highlight the practical risk of relying on LLMs in requirements engineering without human oversight and motivate the need for systematic approaches to benchmark, interpret, and monitor value alignment in AI-assisted software development.

  • Open Access

    Toward a Better Understanding of User Emotion: An Emotion-Aware Requirements Elicitation Support Tool—EmORE Tool

    by Mashail N. Alkhomsan, Malak Baslyman, Mohammad Alshayeb

    Requirements engineering plays a pivotal role in software development, but overlooks the subjective emotional perspectives of users. However, capturing user emotions effectively is essential for designing engaging systems aligned with pragmatic needs. This paper presents the EmORE tool for generating emotional journey artifacts that provide novel insights into user affect dynamics during the requirements elicitation process. The tool implements a customizable interview technique to evoke usage-specific emotional responses. Emotions are quantified using the Self-Assessment Manikin (SAM) rating technique to enable consistent measurement. Machine learning classifiers categorize expressed emotions, while clustering algorithms identify cross-user patterns to construct comprehensive emotional journey maps—the core contribution of this work. The customizable elicitation workflow and quantitative emotion capture capabilities help mitigate subjectivity, variability, and context-dependence. The tool was evaluated through case studies, interviews, and usability assessments. The accuracy analysis showed 80-96% precision in predicting users’ emotional responses across diverse touchpoints. Thematic analysis revealed positive perceptions of the tool’s potential but concerns about interpretability and adoption. The System Usability Scale (SUS) scores indicated high usability with opportunities to improve learnability. Overall, the results validate the tool’s capabilities while highlighting areas for enhancement, such as simplified onboarding and seamless integration with existing project management techniques. This research facilitates the inclusion of complex emotional perspectives in software engineering to drive user adoption and satisfaction.


  • Open Access

    Mobile, Wearable, and Contactless Approaches to Pediatric Stress Detection: A PRISMA-ScR Guided Scoping Review (Preprint)

    by Arshad Nasser, Sami Elferik, Malak Salim Omar Baslyman

    BACKGROUND Stress in childhood and adolescence can disrupt emotional, cognitive, and physiological development, with long-term health consequences. Conventional assessments (eg, cortisol sampling, retrospective questionnaires) are invasive, burdensome, and poorly suited for pediatric use. Advances in mobile health (mHealth), wearable devices, and non-contact sensing enable non-invasive, real-time monitoring of stress in children and adolescents. OBJECTIVE This scoping review synthesizes evidence on non-invasive technologies for pediatric stress detection and regulation, with particular attention to mobile, wearable, and ubiquitous health applications. It maps the technologies, protocols, and interventions reported to date and identifies gaps and future directions for research and practice. METHODS Following PRISMA-ScR guidelines, five databases (PubMed, Scopus, IEEE Xplore, ACM Digital Library, Google Scholar) were searched for peer-reviewed studies published between 2013 and June 2025. Eligible studies involved participants aged 0–18 years, used non-invasive technological methods for stress detection, monitoring, or mitigation, and reported empirical outcomes. Data were charted across seven dimensions: technology type, stress induction and validation, study context, age group, evaluation method, datasets, and intervention strategies. RESULTS Forty-nine studies were included. Most used wearable devices (84%), with limited exploration of non-contact (14%) or hybrid systems. Stress induction methods were heterogeneous, dominated by cognitive and academic tasks, with no standardized pediatric protocols. Adolescents were the most studied group, whereas children under 8 years were underrepresented. Evaluation approaches ranged from traditional statistics to supervised and deep learning models (accuracies 82%--95.6%), though reproducibility was constrained by small, homogeneous samples and a lack of open pediatric datasets. Only 9 studies integrated mitigation strategies (eg, biofeedback, serious games, caregiver-facing tools), typically in short-term deployments. Ethical and privacy considerations were acknowledged but rarely operationalized. While the review covers a broad spectrum of non-invasive approaches, the majority of included studies were delivered through mobile and wearable platforms, with fewer exploring ambient or ubiquitous sensing, aligning the field closely with mobile and ubiquitous health research. CONCLUSIONS Non-invasive mobile and wearable technologies offer strong potential for scalable pediatric stress monitoring, yet the field remains fragmented. Priorities include developing age-appropriate stress protocols, creating diverse open datasets, evaluating systems in real-world and longitudinal contexts, and embedding closed-loop interventions. Stronger ethical, privacy, and equity safeguards are critical for translation into schools, telehealth, and everyday mHealth practice. CLINICALTRIAL Not Applicable

  • Open Access

    Text-to-Image Representativity Fairness Evaluation Framework

    by Asma Yamani, Malak Baslyman

    Text-to-Image generative systems are progressing rapidly to be a source of advertisement and media and could soon serve as image searches or artists. However, there is a significant concern about the representativity bias these models embody and how these biases can propagate in the social fabric after fine-tuning them. Therefore, continuously monitoring and evaluating these models for fairness is important. To address this issue, we propose Text-to-Image (TTI) Representativity Fairness Evaluation Framework. In this framework, we evaluate three aspects of a TTI system; diversity, inclusion, and quality. For each aspect, human-based and model-based approaches are proposed and evaluated for their ability to capture the bias and whether they can substitute each other. The framework starts by suggesting the prompts for generating the images for the evaluation based on the context and the sensitive attributes under study. Then the three aspects are evaluated using the proposed approaches. Based on the evaluation, a decision is made regarding the representativity bias within the TTI system. The evaluation of our framework on Stable Diffusion shows that the framework can effectively capture the bias in TTI systems. The results also confirm that our proposed model based-approaches can substitute human-based approaches in three out of four components with high correlation, which could potentially reduce costs and automate the process. The study suggests that continual learning of the model on more inclusive data across disadvantaged minorities such as Indians and Middle Easterners is essential to mitigate current stereotyping and lack of inclusiveness.


  • Open Access

    Establishing Heuristics for Improving the Usability of GUI Machine Learning Tools for Novice Users

    by Asma Z Yamani, Haifa Abdullah Al-Shammare, Malak Baslyman

    Machine learning (ML) tools with graphical user interfaces (GUI) are facing demand from novice users who do not have the background of their underlying concepts. These tools are frequently complex and pose unique challenges in terms of interaction and comprehension by novice users. There is yet to be an established set of usability heuristics to guide and assess GUI ML tool design. To address this gap, in this paper, we extend Nielsen’s heuristics for evaluating GUI ML Tools through a set of empirical evaluations. To validate the proposed heuristics, user testing was conducted by novice users on a prototype that reflects those heuristics. Based on the results of the evaluations, our new heuristics set improves upon existing heuristics in the context of ML tools. It can serve as a resource for practitioners designing and evaluating these tools.


  • Open Access

    Emotion-Driven Adaptation of Software Applications using User Requirements Notation Models

    by Mashail N. Alkhomsan, Malak Baslyman, Mohammad Alshayeb

    Software applications aim to deliver intuitive user experiences that maximize adoption and effectiveness. However, accommodating individual differences poses challenges for universally accessible interface design. This paper proposes an emotion-driven adaptation approach to develop Adaptive user interface applications (AUIs) using User Requirements Notation (URN) Models. The approach focuses on eliciting emotional requirements, designing alternative adaptation strategies, and implementing dynamic UI adaptations based on user emotions. During the requirements phase, user emotional goals are elicited to construct emotion-aware goal models using Goal-oriented Requirements Language (GRL). These models are subsequently analyzed to inform the development of adaptation strategies for the interface at runtime, which are triggered by transitions in emotional states. Specifically, User Case Maps (UCMs) capture adaptive strategies that are enacted according to users' emotions inferred through interaction monitoring. The technique provides a flexible, requirements-driven methodology applicable across domains like healthcare, education, or finance that demands accommodating diverse individual differences and delivering optimized user experiences.

  • GRLMerger: an automatic approach for integrating GRL models

    by Nadeen AlAmoudi, Jameleddine Hassine, Malak Baslyman