期刊名称：International Journal of Emerging Technologies in Learning (iJET)
印刷版ISSN：1863-0383
出版年度：2022
卷号：17
期号：16
DOI：10.3991/ijet.v17i16.31945
语种：English
出版社：Kassel University Press
摘要：Big data learning analytics is still in its infancy and has been developed on several campuses worldwide. Ideally, all students' profiles should be described and embraced to optimize the development of any proposed system related to big data learning analytics. This paper aims to extract information related to factors contributing to students’ academic achievement using quantitative and qualitative approach, in which co-occurrence analysis were applied for quantitative approach and facet analysis for the qualitative approach. For data collection, Kitchenham’s technique were used to select and filter the literature, at the first iteration, 1,167 papers were found. After applying inclusion and exclusion criteria, 101 articles were processed for text mining. Titles and abstracts were analyzed using a text-mining tool, and then resulted clusters of words. Afterwards, clusters of words were labeled using facet analysis. This study results in eight interrelated clusters of academic achievement factors: demography, internal consistency, technology, student course engagement, activity in a classroom, educational system, socio-culture, and personality. Several insights into each cluster will be described and might be beneficial for researchers in learning analytics.
