Reflection is an important practice for students because it helps identifying knowledge gaps, developing improvement strategies, and enhancing academic performance. However, existing digital solutions often do not support sustained reflection or provide instructional feedback. MindMirror, an online reflective tool is proposed to integrate self-regulated learning (SRL) and metacognitive strategies through well-defined question categories, i.e., Topic Assessment, Learning Insight, and Classroom Feedback. The tool includes features for group creation, response submission, analysis tools, and artificial intelligence-generated feedback to support student reflection and teaching effectiveness. By fostering meaningful reflection and actionable insights, MindMirror aims to create a continuous, student-lecturer feedback loop that improves learning outcomes.

In the big-data era, massive Open Educational Resources (OERs) can be obtained from the Internet regardless of location or time constraints. Researchers have discussed microlearning as a service to improve learning effectiveness. However, the emergence of OERs leads to the challenge of searching for appropriate and relevant microlearning resources. In this paper, an automated video classification approach named “MVR-CLS” is proposed to organize and classify microlearning resources, so that the learners can browse for learning resources in a manageable way. Speech-To-Text data mining technique is applied to transcribe a learning video and to further analyze the video content. A 3-tier learning category structure is proposed to organize a collection of microlearning videos into appropriate learning categories. “MVR-CLS” has shown the capability to classify the microlearning videos into a finer-grained learning category as compared to the existing work. To evaluate the accuracy of the proposed approach, the classification result is validated against to the metadata of the OERs. The classification result can promote better fit of learners’ interests for content recommendations and thus enhancing the recommendation accuracy in future work.

Educational games are games explicitly designed with educational purposes and aims to balance learning and playing. These educational games help people to learn and improve as they play. However, there is a lack of gameplay monitoring process whereby the real-time information of game progress is not being reflected. Most of the existing educational games do not consolidate with learning analytics dashboards which leads to no visualization of gameplay information and inadequate gameplay analysis. When players have information on how to improve their performance, they will be encouraged to revisit the game. Hence, an educational game with learning analytics dashboard, ChemistLab, is developed for learners to learn chemistry. The dashboard will visualize the performance and skills changes overtime which reflect the players’ learning patterns and strategies used to improve their performance for better learning. The learning content of the game is extracted from the Malaysia Upper Secondary Education (Form 4) Chemistry syllabus. The expected output of the game is to allow users to observe their gameplay performance through the dashboard and gaining new knowledge through the game with the achievement of learning objectives.

In coping with the increasing on-demand movies services provided through the Internet or Cloud platform, on-demand movies providers are competing intensively in providing more varieties and choices of programs. To retain and attract more users, service providers are moving towards recommending more personalized programs to satisfy users’ needs and preferences. While the number of users and items are increasing, the effectiveness and efficiency of the recommendation become the main factors to address. This paper proposes to integrate ontological profiles with contextual elements based on hybrid recommendation approach. In this proposed system, namely HyOC-RS, ontological profile is incorporated with contextual elements to improve the recommendation mechanism. A semantically and hierarchically-linked data model represented the proposed ontological user profile. Performance of HyOC-RS is evaluated in terms of time and space complexity. HyOC-RS with small error measures has proven to be more efficient and accurate as compared to traditional recommendation systems. Additionally, experimental results have shown that HyOC-RS could resolve the problems inherent in many of the traditional content-based and collaborative filtering recommendation systems such as over specialization, data sparsity, new user, and new item problems.

Building requirements specification document in semi-formal notation and natural language needs great effort from users and developers. However, the current approach to the requirements engineering process is still lacking in auto-generating model and documentation. Most approaches only focusing in building UML use cases and a brief version of Software Requirements Specification (SRS), which are not enough as a basis for the code development process. A Rule-based Ontology Framework (ROF) for AutoGenerating Requirements Specification is proposed. It is used for auto-generating requirements specifications that consist of semi-formal modeling in Business Process Model Notation (BPMN) and natural language of Software Requirements Specification (SRS) in IEEE template. This paper discusses the implementation of ROF in a requirement engineering process in a University located in Indonesia. It is applied in Lecturer Workload Management (LWM) Application, an application that summarizes lecturer workload and calculates the scores as basis for generating salary. This application was developed by the Department of Information Systems (ISD). Existing requirements engineering process mostly depend on users’ perspective which causes building the requirements documentation require much effort and do not represent the real needs of users. Thus, the requirements documents do not support the development process which causes project delay. Using ROF, the requirements engineering process becomes more effective by specifying functional requirements that represent user’s needs and produce document that is feasible to be used as a reference for the development process

Since many service providers are providing similar web services, finding an accurate web service based on user preferences is becoming a challenging task. Therefore, enhancing web service discovery (WSD) method will improve the searching performance. In this paper, we firstly discuss and review some existing web service discovery approaches and identify their limitations. Subsequently, we propose a web service discovery method for cloud-based mobile application by using multi-level clustering technique to improve performance by reducing the searching scope. Our web service discovery architecture is able to increase the discoverability of more accurate web services based on user's preferences. Meanwhile, user preference Quality of Services (QoS) attributes are also used for ranking procedure to allow user to decide the quality of the mobile application. The experimental results show that our approach is able to increase the searching performance and provide a reliable list of selection for users.

Virtual Learning Environment (VLE) plays an important role as the online platform for education in recent years. However, there's a lack of learning interest and effectiveness using the VLE due to the limitation of real time communication and information sharing among the users. In this paper, we propose to integrate Social Network Services (SNS) into VLE to address the limitations of the current existing VLEs which include lack of personalization, interaction, discussion, collaboration and communication. We have developed a VLE with Web 2.0 approach in the university domain which includes the integration of few core SNS. We aim to provide real time interaction, encourage group learning, improve resource sharing capability and inspire students in learning.

Virtual Learning Environment (VLE) plays an important role as the online platform for education in recent years. Due to the significant increase of the shift of focus in utilizing VLE in comparing to the traditional learning environment, modularity and reusability of the services need to be increased as well. Most of the current existing VLEs are being developed using the system-based approach whereby if an education institute needs a VLE, they need to purchase the whole complete system and install it at their IT server. This limits the personalization of their VLEs in terms of user interface design and functionalities for both students and teachers (e.g. learning and coaching services). In considering the reusability, interoperability and integration of the services, Web 2.0 is adopted to improve the accessibility and flexibility of the web services. In this paper, we propose to develop VLE 2.0 using web services approach whereby the services implemented can be easily invoked, composed and reused according to the service consumer's requirements. Using VLE 2.0, education institutes can build their very own VLEs by consuming the developed VLE web services.

The visualization of Web service execution process is an emerging research in service-oriented computing (SOC) area. This paper presents a practical visualization framework in putting service discovery and selection process based on quality of service (QoS) attributes into a visual context. The proposed practical architecture serves as a foundation for designing the novel GUIs for different users. By considering the preferences and priorities for service consumers and service providers, we adopt different application UI design criteria and design patterns which tailored to service-based visualization design. Based on that, evaluation is carried out to test the usability, effectiveness and acceptability of the proposed visualization framework.