Trends of learning analytics in STE(A)M education: a review of case studies

This paper aims to present a review of case studies on the use of learning analytics in Science, Technology, Engineering, (Arts), and Mathematics (or STE[A]M) education. It covers the features and trends of learning analytics practices as revealed in case studies.,A total of 34 case studies published from 2013 to 2018 reporting relevant learning analytics practices were collected from Scopus and Google Scholar for analysis. The features and trends of practices were identified through a comparison of the first (2013–2015) and the second period (2016–2018).,The results showed an increasing adoption of learning analytics in STE(A)M education, particularly in the USA and European countries and at the tertiary level. More specific types of data have been collected for the learning analytics practices, and the data related to students’ learning processes has also been more frequently used. The types of STE(A)M learning practices have become more diversified, with technology enhancement features increasingly introduced. The outcomes of the case studies reflect the overall benefits of learning analytics and address the specific needs of STE(A)M education. There have also been fewer types of limitations encountered in the learning analytics practices over the years, with unknown correlation among variables, small sample size and limited data being the major types.,This study reveals the implementation of learning analytics in relation to the contexts and needs of STE(A)M education. The findings also suggest future work for examining the adoption of learning analytics to cope with the development of STE(A)M and, in particular, how the successful experience of learning analytics in other disciplines could be transferred to STE(A)M.

[1]  John A. Bielec,et al.  Alternative IT Sourcing Strategies: Six Views. , 2011 .

[2]  Leyla Zhuhadar,et al.  Using survival analysis to discovering pathways to success in mathematics , 2019, Comput. Hum. Behav..

[3]  Janice D. Gobert,et al.  From Log Files to Assessment Metrics: Measuring Students' Science Inquiry Skills Using Educational Data Mining , 2013, Journal of the Learning Sciences.

[4]  Demetrios G. Sampson,et al.  Towards a Teaching Analytics Tool for Supporting Reflective Educational (re) Design in Inquiry-Based STEM Education , 2016, 2016 IEEE 16th International Conference on Advanced Learning Technologies (ICALT).

[5]  Kelly C. Margot,et al.  Teachers’ perception of STEM integration and education: a systematic literature review , 2019, International Journal of STEM Education.

[6]  Wim Dehaene,et al.  Integrated STEM Education: A Systematic Review of Instructional Practices in Secondary Education , 2018 .

[7]  Jen Katz-Buonincontro,et al.  STEAM in practice and research: An integrative literature review , 2019, Thinking Skills and Creativity.

[8]  Dragan Gasevic,et al.  Learning analytics should not promote one size fits all: The effects of instructional conditions in predicting academic success , 2016, Internet High. Educ..

[9]  Rianne Conijn,et al.  Predicting student performance in a blended MOOC , 2018, J. Comput. Assist. Learn..

[10]  Christine Liao,et al.  From Interdisciplinary to Transdisciplinary: An Arts-Integrated Approach to STEAM Education , 2016 .

[11]  Pablo A. Haya,et al.  A Novel Group Engagement Score for Virtual Learning Environments , 2017, IEEE Transactions on Learning Technologies.

[12]  J. M. Vílchez-González,et al.  What are we talking about when we talk about STEM education? A review of literature , 2019, Science Education.

[13]  Kam Cheong Li,et al.  Trends in learning analytics practices: a review of higher education institutions , 2018, Interact. Technol. Smart Educ..

[14]  Billy Tak-Ming Wong,et al.  Learning analytics in higher education: an analysis of case studies , 2017 .

[15]  Gayathri Vaidyanathan,et al.  Science in Africa: The view from the front line , 2011, Nature.

[16]  Anastasios A. Economides,et al.  Learning Analytics and Educational Data Mining in Practice: A Systematic Literature Review of Empirical Evidence , 2014, J. Educ. Technol. Soc..

[17]  Paulo Blikstein,et al.  Design Guidelines and Empirical Case Study for Scaling Authentic Inquiry-based Science Learning via Open Online Courses and Interactive Biology Cloud Labs , 2018, International Journal of Artificial Intelligence in Education.

[18]  Xianglei Chen.  STEM Attrition: College Students' Paths into and out of STEM Fields. Statistical Analysis Report. NCES 2014-001. , 2013 .

[19]  Billy Tak-Ming Wong,et al.  A review of learning analytics intervention in higher education (2011–2018) , 2019, Journal of Computers in Education.

[20]  Richard A. Levine,et al.  Predictive Analytics Machinery for STEM Student Success Studies , 2018, Appl. Artif. Intell..

[21]  Katja Derr,et al.  Identifying Consistent Variables in a Heterogeneous Data Set: Evaluation of a Web-Based Pre-Course in Mathematics. , 2017 .

[22]  B. Wong,et al.  The use of student response systems with learning analytics: a review of case studies (2008-2017) , 2020, Int. J. Mob. Learn. Organisation.