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.

A Systematic Review on Educational Data Mining

The usage of learning management systems in education has been increasing in the last few years. Students have started using mobile phones, primarily smart phones that have become a part of their daily life, to access online content. Student's online activities generate enormous amount of unused data that are wasted as traditional learning analytics are not capable of processing them. This has resulted in the penetration of Big Data technologies and tools into education, to process the large amount of data involved. This study looks into the recent applications of Big Data technologies in education and presents a review of literature available on Educational Data Mining and Learning Analytics.

Application of Big Data in Education Data Mining and Learning Analytics-A Literature Review

Educational Data Mining: A review of evaluation process in the e-learning

In recent years there has been an enormous increase in learning resources available online through massive open online courses and learning management systems. In this context, personalized resource recommendation has become an even more significant challenge, thereby increasing research in that direction. Recommender systems use ontology, artificial intelligence, among other techniques to provide personalized recommendations. Ontology is a way to model learners and learning resources, among others, which helps to retrieve details. This, in turn, generates more relevant materials to learners. Ontologies have benefits of reusability, reasoning ability, and supports inference mechanisms, which helps to provide enhanced recommendations. The comprehensive survey in this paper gives an overview of the research in progress using ontology to achieve personalization in recommender systems in the e-learning domain.

Review of ontology-based recommender systems in e-learning

An admissions system based on valid and reliable admissions criteria is very important to select candidates likely to perform well academically at institutions of higher education. This study focuses on ways to support universities in admissions decision making using data mining techniques to predict applicants’ academic performance at university. A data set of 2,039 students enrolled in a Computer Science and Information College of a Saudi public university from 2016 to 2019 was used to validate the proposed methodology. The results demonstrate that applicants’ early university performance can be predicted before admission based on certain pre-admission criteria (high school grade average, Scholastic Achievement Admission Test score, and General Aptitude Test score). The results also show that Scholastic Achievement Admission Test score is the pre-admission criterion that most accurately predicts future student performance. Therefore, this score should be assigned more weight in admissions systems. We also found that the Artificial Neural Network technique has an accuracy rate above 79%, making it superior to other classification techniques considered (Decision Trees, Support Vector Machines, and Naive Bayes).

/pdf/using-data-mining-techniques-to-predict-student-performance-2fsvft1tkp.pdf

Using Data Mining Techniques to Predict Student Performance to Support Decision Making in University Admission Systems

Educational data mining: A review

The usage of technology within the educational department has become more vital by each year passing. One of the most popular technological approaches used is the e-learning environment. The usage of e-learning environment in education involves a wide range of types of students, and this includes the hearing impaired ones. Some adjustment or enhancement needs to be implemented within the e-learning environment, based on the needs or the adaptability of the hearing impaired students accordingly. This paper reviews some of the past researches on the usage of the e-learning environment for hearing impaired students for the past decade or so. INTRODUCTION There are a lot of disabled individuals who have the right to get the best education as they can get, just like their normal peers. Hearing impaired (HI) individuals are among those of people with disabilities that deserve the same rights. Hearing impaired individuals, particularly hearing impaired students, usually acquire the same level of mental capability as the normal hearing students in terms of studying. The term ‘deaf and dumb’ is not practically to be used since the hearing impaired students are only lacking of their hearing capability not their intelligence level (Schwartz, 2002). Therefore, they will be undertaking the same subjects or courses in any education departments or institutions as those taught to the normal hearing students of the same age. However, a problem could occur for the hearing impaired students if the technique used by the teachers or instructors in teaching them is as the same used for normal hearing students. Thus, the usage of technology is vital in preparing the HI students with appropriate learning environment, since by using technology, the HI students could access sound in their own suitable way (Berndsen & Luckner, 2010). E-learning environment is one of the most used techniques for educational purpose and this includes the education for HI students. However, most e-learning environment available does not particularly can be useful to those students due to its feature which is lacking in terms of adaptability. They often encounter problem in accessing the information available in terms of understanding it and using it in a proper manner (Fichten, Ferraro, Asuncion, Chwojka, Nguyen, Klomp & Wolforth, 2009). Therefore, in order to assist these HI students in accessing the information adequately, the e-learning environment needs to be developed and designed according to the needs of the HI students by adding or enhancing some features within the e-learning environment. DISCUSSION ON SELECTED PAPERS In this section, we present the review of past researches on the usage of the e-learning environment for hearing impaired students starting from the year 2005 until the year of 2012. Table 1 below shows the list of the studies related to the issue concerned. We begin the review with the brief explanation on the each study, followed by the approaches, limitations and also some valuable directions for future studies. Table 1: List of studies on the hearing impaired e-learning environment Author(s) Year Participants

/pdf/e-learning-environment-for-hearing-impaired-students-2p6txj661k.pdf

E-Learning Environment for Hearing Impaired Students.

This research study aims to identify student's perceptions regarding the use of blogging, the pattern of reflection involved in learning Authoring System through blogging and student's performance in tests based on the reflection's pattern. Sixteen students who registered for the Authoring System subject participated in this study. It was conducted using quantitative approaches, through survey and pre-experimental design of one group post-test type. The instruments used were questionnaire, performance test and blog contents, where tutors and students posted messages and comments on the blog during the course. The results showed that the students' overall perception regarding the educational benefits of writing a blog and reading other students' blogs and comments was positive. Students also moderately agreed that they had difficulties in engaging in the reflection through blogging. It was also found that blogging indirectly improved the students' performance in the test. Through blog content analysis, the dominant type of reflection was monologue. However, the results from the data mining analysis showed that the students used reflective conversation and monologue type of reflection to achieve Grade A in learning Authoring System. It shows that students require deep and critical reflection to perform better in the subject.

Pattern of reflection in learning Authoring System through blogging

Some complex problems in the computational area are learning programming and algorithms. Authoring system is a subject that can be considered as complex as it integrates the use of scripting language like Action Script in Flash, Active Server Pages (ASP) and Hypertext Preprocessor (PHP). The normal problem that resides when it comes to programming is handling error as it is not an easy task and for those who are new, might find this very troublesome. Handling the error requires proper planning and skills in analyzing problem which students usually lack at. Reflection in learning is really helpful in helping students learn the Authoring System subject effectively as they are encourage to share ideas, experiences and perspective actively on the emerging issues of Action Script topic especially in discussing the concepts and errors. With the need for reflection in developing the required skills in learning Authoring System, how then do we ensure and measure the quality in student reflection journals and its contact in assessing the subject content and students' performance in learning? Quality is defined as "processes or outcomes" [1]. In the context of this research study, quality is determined by assessing the progression of reflective processes based on the interventions given. As an educator, we need to be aware on how new technologies act as the engagers and facilitators in the reflection purposes. Blog is one of the emerging technologies that can offer such pedagogical benefits as reflective tools and social affordances across disciplines provided that one can read and make comments that lead to meaningful discussion for common interests and individual differences [2]. Although blogging enable deep reflection in each individual blogs, somehow it failed to encourage peer feedback to each other blogs and collaboration among students to support reflective thinking as expected [3]. This problem exists probably due to the minimum used of blog technical features and also the absence of activities and guidelines to elevate collaborative reflection process to take place [4]. Students' familiarity with the blog technology cannot guarantee them with the skills to use it efficiently in educational setting. They still need further expose and training on how technologies can be used beyond the technological sake [4]. Besides the use of blogs, the design of the activities should not simply indicate the progress towards the solution of the problem if to allow reflective thinking to occur. The use of case-based learning can support reflective thinking among students in learning computer-based subject. However, the implementation of case-based learning requires the presence of an instructor to guide students to solve the subject matter at hand. Instructors are therefore encouraged to regulate students thinking by integrating the metacognitive strategies in learning necessary for academic success and students should also be granted with the opportunity in using this strategy to boost the likely for students to reflect on their task and therefore contributed to their experience as a community of learners. Unfortunately, many students failed to directly engage in metacognitive thinking unless they are shown ways to do so through prudently designed instructional activities. Thus, it is vital to embed metacognitive support in the design of learning environment especially when dealing with computer education subject which involves lots of technical aspects. This study believes that the integrations of several approaches as mentioned above can granted a green light in nurturing and achieving good quality in students' reflection. In this study, the quality is heavily relied on the use of feedback either from the instructors to students or among students themselves. Most of studies regarding the reflection done before only focusing on rating students' reflection journals all alone without considering other factors that may impacting certain levels of reflection. Therefore, this study is intended to identify the impact of provision of feedback in determining the quality of students' reflection and predicting the students' performance in learning Authoring System subject. This study will employ a quantitative research design which involves the use of pre-experimental design of one group pretest-posttest type. It will be conducted in one whole semester and will involve postgraduate students who registered for Authoring System subject. Three research instruments will be used in this study: questionnaires, performance test, and student's reflection in blogs. 1. Questionnaire: -There will be two questionnaires administered in this research study. The first questionnaire is about students' perceptions regarding the educational benefits of reflection through blogging while the second questionnaire is about the students' perceptions regarding the provision of feedback both from the peers and instructors. Both questionnaires are self-developed by the researchers and will be analyzed using the Rasch Model analysis technique which is run using Win steps software. By using Rasch Model, the findings will be more interesting and meaningful as from the students' psychometrics, researchers are able to dig into detail about the real relations between students and the measureable items. 2. Performance test: -The performance test is consists of several questions on Authoring System which cover the topic on Flash and Dreamweaver. It will be administered at the last session of the semester and is graded based on the answer scheme. The performance score will later be used in data mining analysis technique through Weka software in order to predict student's performance based on the pattern of reflection among students in learning the aforementioned subject. 3. Observations and analysis of students' reflections in blogs: -Throughout the semester, student's blogs will be monitored in order to observe their activities and to encourage them to do the reflection critically. Apart from the weekly reflections, several minicases activities will be posted in the instructor's blog and students are required to make critical reflections on each mini case. The minicase is designed to help students to apply concepts and suitable for practical in lab settings [5]. The cases will be created based on real-life practices and also from the problems encountered by the students while completing the class activities. Students' postings in the blogs will be analyzed via content analysis technique. The qualitative postings from the blogs which originally in the form of text will be coded using the four levels of reflective thinking framework by [6] and this action will transformed the qualitative data into quantitative data in terms of the frequency of occurrence. In order to measure the quality of reflection, the following analyses will be taken into account [7]: 1. Overall frequency of posting given by instructors and students. 2. Nature of posting by instructors and students (answers, questions, or mix of both). 3. Timing of the posting (during or end of forum). 4. How the postings style evolve from one level of reflective thinking to another as a result of provision of feedback by instructors and students. The general outcome of doing reflection is learning. However, this study is expected to achieve more than that. The upshot of this study will determine the quality in students' reflection and also the dominant level of reflective thinking. The outcome will further validate similar studies which previously conducted concerning the reflective thinking skills with the integration of technology, pedagogical aspects of learning for active involvement and how the students' psychometrics from the developed questionnaires can addressed the crucial information about the way students gain information and learning.

Pattern of Reflection in Learning for Predicting Students' Performance





Purpose: This study examines the effect of two main factors, that is, lack of knowledge of ICT, and the availability of ICT facilities such as hardware, software, and internet access, which identified to be the common barriers towards practicing online formative assessment.
 
Theoretical framework:  Many educational institutions have been urged to adopt online learning due to the development of communications and digital device technology as well as the COVID-19 pandemic that ravaged the world in the previous two years. The shift from offline to online mode affects how formative assessment should be conducted during teaching and learning. The lack of knowledge of information and communication technology (ICT) and ICT facilities are prevalent in Nigeria.
 
Design/methodology/approach: This study employed a survey design to examine online assessment feedback practice as well as factors contributing to the practices among 256 academics in one tertiary education in Sokoto. Descriptive and inferential statistical analyses were used.
 
Findings: Online formative assessment feedback practice is at low level due to lack of knowledge of software applications and facilities.
 
Research, Practical & Social implications: Government needs to invest more on educational technology by providing adequate ICT facilities in tertiary institutions in Sokoto, as well as offering suitable trainings on ICT literacy for academics.
 
Originality/value: Online formative assessment contributes to enhancement in educational attainment and efficiency in learning and teaching.





/pdf/online-formative-assessment-practices-among-academics-of-2c1gdaxx.pdf

Siti Khadijah Mohamad

Papers

Educational data mining: A review

E-Learning Environment for Hearing Impaired Students.

Pattern of reflection in learning Authoring System through blogging

Pattern of Reflection in Learning for Predicting Students' Performance

Online Formative Assessment Practices Among Academics of Tertiary Education in Sokoto State, Nigeria