Gamified e-learning systems aim to enhance learning outcomes and foster learner's engagement by incorporating multiple game elements. These elements have varying influence on the learner's behavior, such as encouraging focus, competition, or exploratory attitudes. However, game elements are often implemented within the learning process in a uniform way that is not adaptable, with no available metadata about them, and without the teacher's involvement or choice. However, since game elements have a behavioral effect on the learners, the selection of relevant game elements should include the teachers' objectives for effective gamification. Therefore, this paper proposes an approach to facilitate understanding and formalizing gamification concepts for enhanced understanding from the teacher's side so that they can apply it and share it. The proposed approach begins with defining gamification and its associated properties and how it can be formalized in a semantic model. This ontological model is then populated through data collection and integration processes, which is then validated by means of SPARQL queries. This approach lays the foundation for future advancements, including the potential to recommend appropriate teachers to assist another in integrating gamification into e-learning processes.

Gamification in e-learning systems implies integrating game elements in non-gaming context to attain the learner’s engagement through pre-defined engagement objectives. These objectives impact the selection of the to-be-applied game elements, which typically influences the learner’s behavior within the learning process. In turn, this behavior is expected to help the teachers in reaching their learning objectives. Therefore, involving teachers in the gamification process as they are in the learning process can ensure the coherence between the learning and engagement objectives. However, since teachers often lack familiarity with gamification, they are rarely involved with the gamification process. Accordingly, recommender systems can play a vital role in assisting teachers through gamification. Therefore, this paper investigates the existing recommender systems from teacher’s perspective to highlight the advancements proposed for assisting teachers and examines the utilization of game elements within gamified e-learning systems to identify their types and explore their practical applications. Based on our research results, this paper proposes a (1) game elements categorization based on their practical applications and (2) a layered recommendation process flow that incorporates the different game elements categories, to assist the teachers in gamifying the learning process.

Can we trust verified accounts on social media? With the recent exponential inflation of social media in every aspect, tremendous efforts have been directed to comprehend, analyze, relate, predict, secure, privacy-preserve, and validate its content. This included natural language processing, sentiment analysis, opinion mining, fake accounts/news detection, graph mining, recommendations, anonymization, …, etc. However, assessing the trust level of the disseminated content was never addressed. Social media users are left to deal with the content of the verified accounts and decide for themselves whether they are true or fake. This raises a dire concern: how can we evaluate the trust level of the content posed by the verified accounts we follow? In this paper, we investigate the challenges of zero-trust management for content in social media. We draw the community’s attention to go beyond fake accounts/content detection and explore trust assessment of content for the legitimate account, rather than solely checking whether it is verified or not. In this regard, we derive a set of open challenges with AI-based solutions for further investigation to maintain a trustworthy social media ecosystem with trusted content.

Recent advancements in single-cell transcriptomics have revolutionized data generation, resulting in the production of vast amounts of single-cell RNA sequencing (scRNA-seq) data. The intricate biology of tissues and organs may be better understood through the analysis of such data, which aims to not only identify known cell types but also uncover novel ones. In this paper, we outline the standard single-cell RNA-seq data analytic process with particular focus on the critical role of unsupervised clustering, since it has a significant influence over subsequent analyses and the resulting biological insights. However, navigating the computational landscape for clustering single-cell transcriptomic data poses significant challenges. Thus, in this article, we provide a simplified exploration of key computational challenges and considerations within the realm of scRNA-seq data clustering, emphasizing the application and relevance of selected unsupervised methods in current research, while acknowledging the potential for further investigation of the biological aspects in this field. Furthermore, we present recommendations on how such challenges may be addressed. This work not only sheds light on the complexities of scRNA-seq data cluster analysis, but also provides insights into how to effectively address and surmount these challenges.

Web services composition has drawn a great attention in computing industries to build complex and large systems. However, web services composition modeling has major challenges, including dependency determination, complexity, user requests dependency, handling cycles within a composition, service redundancy and scalability concerns. The service dependency graph (SDG) between services in a repository should be accurate to ensure the quality of composition and the associated user requests’ responses. Despite of the crucial importance of accurate dependencies for adequate web services compositions, current modeling approaches do not provide any metric to evaluate the dependency between services for quality estimation. In this paper, the Mutual Information-based Services Dependency (MISD) model is proposed as a graph-based modeling approach, independent to any given user request. It constructs services dependency graphs based on Web Services Mutual Information (WSMI), a proposed modified version of mutual information as the dependency metric, along with other criteria for an accurate, efficient dependency evaluation. It finds the optimum composition representing the structure of the web services composition in a repository rather than the path of given user requests. The experimental dependency analysis emphasizes the efficiency of the generated OC and accuracy of the constructed SDG to be 76% and 86% higher than the state-of-the-art models respectively. The time cost to build the SDG and to find the OC is reduced dramatically up to 99% for different public repositories compared to the state-of-the-art studies as the number of user requests increases.

Abstract Regression testing repeatedly executes test cases of previous builds to validate that the original features are not affected with any new changes. In recent years, regression testing has seen a remarkable progress with the increasing popularity of agile methods, which stress the central role of regression testing in maintaining software quality. The optimum case for regression testing in agile context is to run regression set at the end of each sprint and release, which requires a lot of cost and time. In this paper, we present an automated agile regression testing approach on both the sprints and release levels. The proposed approach addresses both weighted sprint test cases prioritization technique, which prioritizes test cases based on several parameters having real practical weight for testers, and Cluster‐based Release Test cases Selection technique that clusters user stories based on the similarity of covered modules to solve the scalability issue. Test cases are then selected based on issues logged for failed test cases using text mining techniques. The proposed approach achieves enhancement for both the prioritization and selection of test cases for agile regression testing. Copyright © 2016 John Wiley & Sons, Ltd.

Seamless information processing is gradually being integrated into daily human activities by creating a ubiquitous computing environment. Such information processing requires continuous access to the profiles of users so that the environment can act based on users' preferences. In this paper, we present a design of an experimental study of an agent-based approach to control resource consumption in a ubiquitous environment. A key idea is to explore whether it is feasible to use a mechanism that may help preserve inhabitants' privacy while at the same time provide a smart environment which resolves conflicts based on the preferences of the inhabitants. Experiments will be based on Bosthan, an agent-based simulator for smart spaces that is currently under development. Bosthan can simulate smart environments to investigate and evaluate different ubiquitous applications.