Correlation between students expectations and demographic characteristics toward features of learning analytics system in Malaysia

• Main Authors: Che Nawi, Nur Raihan, Omar, Muhd Khaizer, Sharef, Nurfadhlina Mohd, Azmi Murad, Masrah Azrifah, Mansor, Evi Indriasari, Nasharuddin, Nurul Amelina, Samian, Normalia, Arshad, Noreen Izza, Shahbodin, Faaizah, Marhaban, Mohammad Hamiruce
• Format: Article
• Language: English
• Published: Human Resource Management Academic Research Society 2023
• Online Access: http://eprints.utem.edu.my/id/eprint/27346/2/0047723122023.PDF; http://eprints.utem.edu.my/id/eprint/27346/; https://hrmars.com/papers_submitted/16961/correlation-between-students-expectations-and-demographic-characteristics-toward-features-of-learning-analytics-system-in-malaysia.pdf; http://dx.doi.org/10.6007/IJARPED/v12-i2/16961

Learning analytics is the process of assessing, evaluating, and measuring student performance and the effectiveness of the teaching and learning process. This study investigates the relationship between three dimensions of learning analytics (summative, real-time, and predictive) and learning demographic characteristics (age, gender, categories of students, current semester, field of study, credit hours are taken in the current semester and CGPA). Questionnaires were distributed to 350 students enrolled in various programs at a public university in Malaysia. The study found that demographic profiles of the respondents which include age, gender, types of students, credit hours taken, concern for achievement, learning preferences, and learning motivation significantly contributed to learning analytic features. Additionally, the study revealed a strong and positive direction of learning analytic features: summative, real-time, and predictive based on the Pearson Correlation report. To comprehensively enhance the learning experience, the study recommends an extensive study related to learner profiling that considers intrinsic and extrinsic value such as assistive technology, learning performance, and motivation. The implications for other stakeholders such as teachers, learners, curriculum developers, and policymakers can be significant, as they can use learner profiling information to develop personalized learning plans, provide targeted support, design effective learning materials, and make informed education policy and funding decisions. A comprehensive understating of learner profiling and learning analytics can have far-reaching implications for various stakeholders in the education system, potentially leading to more personalized, effective, and equitable learning experiences for all learners.