Search results

The purpose of this paper is to propose a process mining approach to help in making early predictions to improve students’ learning experience in massive open online courses (MOOCs). It investigates the impact of various machine learning techniques in combination with process mining features to measure effectiveness of these techniques.

Student’s data (e.g. assessment grades, demographic information) and weekly interaction data based on event logs (e.g. video lecture interaction, solution submission time, time spent weekly) have guided this design. This study evaluates four machine learning classification techniques used in the literature (logistic regression (LR), Naïve Bayes (NB), random forest (RF) and K-nearest neighbor) to monitor weekly progression of students’ performance and to predict their overall performance outcome. Two data sets – one, with traditional features and second, with features obtained from process conformance testing – have been used.

The results show that techniques used in the study are able to make predictions on the performance of students. Overall accuracy (F1-score, area under curve) of machine learning techniques can be improved by integrating process mining features with standard features. Specifically, the use of LR and NB classifiers outperforms other techniques in a statistical significant way.

Although MOOCs provide a platform for learning in highly scalable and flexible manner, they are prone to early dropout and low completion rate. This study outlines a data-driven approach to improve students’ learning experience and decrease the dropout rate.

Early predictions based on individual’s participation can help educators provide support to students who are struggling in the course.

This study outlines the innovative use of process mining techniques in education data mining to help educators gather data-driven insight on student performances in the enrolled courses.

This chapter focusses on the ethical issues raised by different types of surveillance and the varied ways in which surveillance can be covert. Three case studies are presented which highlight different types of surveillance and different ethical concerns. The first case concerns the use of undercover police to infiltrate political activist groups over a 40-year period in the UK. The second case study examines a joint operation by US and Australian law enforcement agencies: the FBI’s operation Trojan Shield and the AFP’s Operation Ironside. This involved distributing encrypted phone handsets to serious criminal organisations which included a ‘backdoor’ secretly sending encrypted copies of all messages to law enforcement. The third case study analyses the use of emotional artificial intelligence systems in educational digital learning platforms for children where technology companies collect, store and use intrusive personal data in an opaque manner. The authors discuss similarities and differences in the ethical questions raised by these cases, for example, the involvement of the state versus private corporations, the kinds of information gathered and how it is used.

Document management system is an essential approach that should be managed well to ensure an effective and faster overall working process in an organization. Hardcopy documents has been one of the items that most organizations need to manage in a safe and secure manner due to the high dependency on most of their working procedure especially in government organizations. Hence, we proposed a new framework to improve the weaknesses of the existing document management procedures in government organizations. Our proposed framework integrates the implementation of an NFC system in this research due to its secure short - range communication, and the peer-to-peer communication capability in most mobile devices. Besides that, most existing government organizations within Malaysia could easily implement such technology for their internal usage as this technology is cost effective due to its availability on existing mobile devices on most Android based devices.

Self-regulation is the level of learning where the learner becomes an active agent in their learning process in terms of activity and aspects of motivation and metacognition. The current paper mostly deals with the metacognitive aspect. The purpose of this study is to gain insight into self-regulation of learning in the context of modern technology in higher education. This study also aims to highlight the direction, tendencies and trends toward which self-regulation of learning is moving in relation to modern technologies.

The review study was compiled via searches in three databases: Scopus, Web of Science and ERIC. A filter was used to search for empirical studies solely in English, published over the past decade on the topics of self-regulation of learning and technology in higher education.

The findings clearly show a correlation between self-regulation of learning and modern technology, especially after a significant event such as the Covid-19 pandemic. However, in the wake of this change, the field of education has seen the emergence of methods and new platforms that can provide support for the development of self-regulated learning strategies.

The originality of the study lies in the fact that it focuses on the link between self-regulation of learning and modern technologies in higher education, including some predictions of the future direction of self-regulation of learning in this context.

The objective of this study is to propose a model for the implementation of a technological platform for participants to develop solutions to problems related to the Fourth Industrial Revolution (4IR) megatrends, and taking advantage of artificial intelligence (AI) to develop their complex thinking through co-creation work.

The development of the model is based on a combination of participatory action research and user-centered design (UCD) methodologies, seeking to ensure that the platform is user-oriented and based on the experiences of the authors. The model itself is structured around the active and transformational learning (ATL) framework.

This study highlights the importance of addressing 4IR megatrends in education to prepare students for a technology-driven world. The proposed model, based on ATL and supported by AI, integrates essential competencies for tackling challenges and generating innovative solutions. The integration of AI into the platform fosters personalized learning, collaboration and reflection and enhances creativity by offering new insights and tools, whereas UCD ensures alignment with user needs and expectations.

This research presents an innovative educational model that combines ATL with AI to foster complex thinking and co-creation of solutions to problems related to 4IR megatrends. Integrating ATL ensures engagement with real-world problems and critical thinking while AI provides personalized content, tutoring, data analysis and creative support. The collaborative platform encourages diverse perspectives and collective intelligence, benefiting other researchers to better conceive learner-centered platforms promoting 21st-century skills and co-creation.

Process mining provides a generic collection of techniques to turn event data into valuable insights, improvement ideas, predictions, and recommendations. This paper uses spreadsheets as a metaphor to introduce process mining as an essential tool for data scientists and business analysts. The purpose of this paper is to illustrate that process mining can do with events what spreadsheets can do with numbers.

The paper discusses the main concepts in both spreadsheets and process mining. Using a concrete data set as a running example, the different types of process mining are explained. Where spreadsheets work with numbers, process mining starts from event data with the aim to analyze processes.

Differences and commonalities between spreadsheets and process mining are described. Unlike process mining tools like ProM, spreadsheets programs cannot be used to discover processes, check compliance, analyze bottlenecks, animate event data, and provide operational process support. Pointers to existing process mining tools and their functionality are given.

Event logs and operational processes can be found everywhere and process mining techniques are not limited to specific application domains. Comparable to spreadsheet software widely used in finance, production, sales, education, and sports, process mining software can be used in a broad range of organizations.

The paper provides an original view on process mining by relating it to the spreadsheets. The value of spreadsheet-like technology tailored toward the analysis of behavior rather than numbers is illustrated by the over 20 commercial process mining tools available today and the growing adoption in a variety of application domains.

This study aims to promote the need for advanced skills acquisition within the LIS and academic libraries. This study focuses on the importance of library management systems and the need for the graduates to be equipped with analytics skills. Combined with basic data, text mining and analytics, knowledge classification and information audit skills would benefit libraries and improve resource allocation. Agile institutional libraries in this big data era success hinge on the ability to perform depth analytics of both data and text to generate useful insight for information literacy training and information governance.

This paper adopted a living-lab methodology to use existing technology to conduct system analysis and LMS audit of an academic library of one of the highly ranked universities in the world. One of the benefits of this approach is the ability to apply technological innovation and tools to carry out research that is relevant to the context of LIS or other research fields such as management, education, humanities and social sciences. The techniques allow us to gain access to publicly available information because of system audits that were performed. The level of responsiveness of the online library was accessed, and basic information audits were conducted.

This study indicated skill gaps in the LIS training and the academic libraries in response to the fourth industrial technologies. This study argued that the role of skill acquisition and how it can foster data-driven library management operations. Hence, data mining, text mining and analytics are needed to probe into such massive, big data housed in the various libraries’ repositories. This study, however, indicated that without retraining of librarians or including this analytics programming in the LIS curriculum, the libraries would not be able to reap the benefits these techniques provided.

This paper covered research within the general and academic libraries and the broader LIS fields. The same principle and concept is very important for both public and private libraries with substantial usage and patrons.

This paper indicated that librarianship training must fill the gaps within the LIS training. This can be done by including data mining, data analytics, text mining and processing in the curriculum. This skill will enable the news graduates to have skills to assist the library managers in making informed decisions based on user-generated content (UGC), LMS system audits and information audits. Thus, this paper provided practical insights and suggested solutions for academic libraries to improve the agility of information services.

The academic librarian can improve institutional and LMS management through insights that are generated from the user. This study indicated that libraries' UGC could serve as robust insights into library management.

This paper argued that the librarian expertise transcends information literacy and knowledge classification and debated the interwoven of LMS and data analytics, text mining and analysis as a solution to improve efficient resources and training.