Presently, educational institutions compile and store huge volumes of data, such as student enrolment and attendance records, as well as their examination results. Mining such data yields stimulating ...information that serves its handlers well. Rapid growth in educational data points to the fact that distilling massive amounts of data requires a more sophisticated set of algorithms. This issue led to the emergence of the field of educational data mining (EDM). Traditional data mining algorithms cannot be directly applied to educational problems, as they may have a specific objective and function. This implies that a preprocessing algorithm has to be enforced first and only then some specific data mining methods can be applied to the problems. One such preprocessing algorithm in EDM is clustering. Many studies on EDM have focused on the application of various data mining algorithms to educational attributes. Therefore, this paper provides over three decades long (1983-2016) systematic literature review on clustering algorithm and its applicability and usability in the context of EDM. Future insights are outlined based on the literature reviewed, and avenues for further research are identified.
Research paper recommenders emerged over the last decade to ease finding publications relating to researchers' area of interest. The challenge was not just to provide researchers with very rich ...publications at any time, any place and in any form but to also offer the right publication to the right researcher in the right way. Several approaches exist in handling paper recommender systems. However, these approaches assumed the availability of the whole contents of the recommending papers to be freely accessible, which is not always true due to factors such as copyright restrictions. This paper presents a collaborative approach for research paper recommender system. By leveraging the advantages of collaborative filtering approach, we utilize the publicly available contextual metadata to infer the hidden associations that exist between research papers in order to personalize recommendations. The novelty of our proposed approach is that it provides personalized recommendations regardless of the research field and regardless of the user's expertise. Using a publicly available dataset, our proposed approach has recorded a significant improvement over other baseline methods in measuring both the overall performance and the ability to return relevant and useful publications at the top of the recommendation list.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Background Mobile health (mHealth) applications (apps) show promise in supporting epilepsy self-management (eSM). To delve deeper into this potential, we conducted a systematic review of epilepsy ...mHealth apps available on both iOS and Android platforms, examining articles related to eSM. This review allowed us to identify important domains related to eSM. Furthermore, based on the findings, we developed an epilepsy mHealth app framework that aims to improve self-management for the local population. This study aims to assess the practicality and usability of the proposed mHealth app framework designed to improve eSM. We will conduct an expert panel review to evaluate the effectiveness and feasibility of the framework. Material and methods Content validity was assessed by an expert panel comprising epileptologists and pharmacists. The validation process involved scoring the items within each domain of the framework to evaluate their practicality and usability (quantitative component). In addition, a panel discussion was conducted to further explore and discuss the qualitative aspects of the items. Results A total of 4 domains with 15 items were highly rated for their practicality and usefulness in eSM. Conclusions The locally validated framework will be useful for developing eSM mobile apps. Seizure Tracking, Medication Adherence, Treatment Management, and Healthcare Communication emerged as the most crucial domains for enhancing eSM.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
The ever-evolving nature of research works creates the cacophony of new topics incessantly resulting in an unstable state in every field of research. Researchers are disseminating their works ...producing a huge volume of articles. In fact, the spectacular growth in scholarly literature is widening the choice sets overwhelmingly for researchers. Consequently, they face difficulties in identifying a suitable topic of current importance from a plethora of research topics. This remains an ill-defined problem for researchers due to the overload of choices. The problem is even more severe for new researchers due to the lack of experience. Hence, there is a definite need for a system that would help researchers make decisions on appropriate topics. Recommender systems are good options for performing this very task. They have been proven to be useful for researchers to keep pace with research dynamics and at the same time to overcome the information overload problem by retrieving useful information from the large information space of scholarly literature. In this article, we present RTRS, a knowledge-based Research Topics Recommender System to assist both novice and experienced researchers in selecting research topics in their chosen field. The core of this system hinges upon bibliometric information of the literature. The system identifies active research topics in a particular area and recommends top
N
topics to the target users. The results obtained have proven useful to academic researchers, particularly novices, in making an early decision on research topics.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OBVAL, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
One of the challenges of emotion classification is the existence of low annotated datasets, that makes the task more complex. Certain existing datasets often suffer from imbalanced data for the ...emotion classes. Several data augmentation approaches can help to overcome the challenges regarding imbalanced datasets. However, the existing data augmentation techniques in emotion classification lack consideration for the contextual nuances of emotions and this area is still relatively underexplored. In this work, we study the impact of data augmentation on classification performance of three machine learning models including Logistic Regression, BiLSTM and BERT and compare frequently used methods to address the issue. Specifically, we assessed Easy Data Augmentation (EDA) and contextual Embedding-based data augmentation (BERT) on two datasets. Based on the experimental results, we combined two BERT-based augmentation techniques including insert and substitute, to generate data for minority emotion classes. Furthermore, we proposed a data augmentation method using ChatGPT. Compared to the baseline models, incorporating the BERT augmentation techniques with BERT model resulted in improvements of +4.34% and +5.56% in Macro F1 score on the SemEval-2018 and GoEmotions datasets, respectively. Moreover, the proposed augmentation technique utilizing ChatGPT yielded improvements of +3.55% and +4.83% on the same datasets.
This systematic literature review focuses on the research area of process audits and explores the potential of process mining techniques for their enhancement. Traditional process audits, being ...manual and sample-based, heavily rely on auditors' expertise and preferences. With the emergence of process mining (PM), there exists an opportunity to improve traditional process audits. However, prior to initiating a PM project specifically for audits, it is crucial to understand the benefits and challenges associated with the implementation. Through a systematic analysis of research articles from six reputable scholarly literature indexing databases, this review reveals how integrating PM into the auditing landscape introduces automation, transparency, and efficiency in addition to overcoming the limitations of traditional process audits. The findings of this review provide valuable insights to identify the benefits of PM-based audits and comprehend the challenges that must be addressed to fully realize the potential of PM techniques in process audits.
Computer programming is a part of the curriculum in computer science education, and high drop rates for this subject are a universal problem. Development of metacognitive skills, including the ...conceptual framework provided by socio-cognitive theories that afford reflective thinking, such as actively monitoring, evaluating, and modifying one's thinking, has been identified as important for novice programmers. Studies have shown that metacognitive skills can be nurtured through the use of technology blended into educational activities. Designing metacognitive-related activities that focus on both social and cognitive development is both theoretically and practically challenging, especially in supporting the teaching and learning of computer programming. This paper describes six commonly-used strategies, viz., metacognitive scaffolding, reflective prompts, self-assessment, self-questioning, self-directed learning and graphic organizers, identified as important features that can be incorporated into computer-assisted learning tools in supporting computer programming learning. An experimental study was conducted to determine the effectiveness of these strategies. The results show that they helped learners by improving their performance in learning computer programming.
Full text
Available for:
BFBNIB, DOBA, IZUM, KILJ, NMLJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
In recent years, different types of review systems have been developed with the recommender system (RS). RSs are developed based on user textual reviews, ratings, and comparative opinions. RSs for ...social media resources, such as blogs, forums, social network websites, social bookmarking websites, video portals, and chat portals help users to collaborate effectively. Social media resources are used in the RS for recommending contents, articles, news, e-commerce products, and users. Although research on social media in RSs has increased annually, comprehensive literature review and classification of these RS studies are limited and must, therefore, be improved. This paper aims to provide a comprehensive review of the social media RS on research articles published from 2011 to 2015 by exploiting a methodological decision analysis in six aspects, including recommendation approaches, research domains, and data sets used in each domain, data mining techniques, recommendation type, and the use of performance measures. A total of 61 articles are reviewed among the initial 434 articles on RS research published in Web of Science and Scopus between 2011 and 2015. To accomplish the aim of this paper, a comprehensive review and analysis was performed on extracted articles to explore various recommendation approaches which are used in the RS. In addition, various social media domains are identified, where RSs have been employed. In each identified domain, publicly available data sets are also reported. Furthermore, various data mining techniques, recommendation types, and performance measures are also analyzed and reviewed in technical aspects. Finally, potential open research directions are also presented for future researchers intended to work in social media RS domain.
The soft set theory is a mathematical tool that deals with uncertainty, imprecise, and vagueness in decision systems. It has been widely used to identify irrelevant parameters and make reduction set ...of parameters for decision making in order to bring out the optimal choices of the decision systems. Many normal parameter reduction algorithms exist to handle parameter reduction and maintain consistency of decision choices. However, they require much time to repeatedly run the algorithm to reduce unnecessary parameters using either parameter important degree or oriented parameter sum. In this paper, we propose an alternative algorithm for parameter reduction and decision making based on soft set theory. We show that the proposed algorithm can reduce the computational complexity and run time compared with baseline algorithms. To evaluate the proposed algorithm, we perform thorough experiments on a binary-valued data set. The experimental result shows that the proposed algorithm is feasible and has relatively reduced the computational complexity and running time. In addition, the algorithm is relatively easy to understand compared with the state of the art of normal parameter reduction algorithm. The proposed algorithm is able to avoid the use of parameter important degree, decision partition, and finding the multiple of the universe within the sets.
Question answering (QA) systems answer the queries of users efficiently in the least amount of time. A researcher has to decide which among various methods and techniques available will be used to ...retrieve accurate answers when developing a QA system. This step creates an overhead before making a selection. The study highlights the methods and techniques that perform well in terms of the accuracy of answers provided. Nine Web-based question answering systems were consulted, and the applied methods and techniques evaluated on the basis of the percentage of questions correctly answered and the mean reciprocal rank evaluation measures. Results were discussed using three key stages involved in a QA system: answer extraction, scoring of answers, and answer aggregation. Results show some techniques have higher accuracy of answers than others. Not all methods in QA systems can improve the accuracy of answers individually, but the methods used in combination obtain greater effect. The results can be used to select methods and techniques optimal for producing highly accurate scores without spending time on benchmarking.