A. Predicting Student Online Performance Patterns

This study aimed to investigate the differences in students’ behaviors and progress during an online training program designed to enhance their STEM skills. Latent profile analysis (LPA) identified four distinct profiles of students, each with different learning behaviors and degrees of improvement. The results suggest that not all students behaved similarly or benefitted equally from the online training. The findings provide insights into individual differences in online learning behaviors and have implications for designing personalized online learning environments.

Gao, F. (manuscript in preparation). Investigating students’ online learning patterns and its relationship with basic psychological needs satisfaction.

Gao, F. & Mandell, E. (submitted). Examining the relationship between students’ online behaviors and their basic psychological needs satisfaction. Paper to be presented at the 2023 Association for Educational Communications and Technology (AECT) International Convention.

Gao, F. Mandell, E., & Li, L. (accepted, 2023). Revealing patterns of student online learning behaviors through latent profile analysis. Proceedings of the 15th Annual International Conference on Education and New Learning Technologies. The International Academy of Technology, Education and Development (IATED).

B. Learning Analytics Dashboards (LADs)

In this project, a LAD is designed and integrated into an existing intelligent tutoring system. Research on LADs is still at its early stage (Schwendimann et al., 2017), and little research has been conducted on LADs and student autonomy support. More specifically, researchers have found that (a) although LADs were designed help learners better monitor their learning activities, limited attention was given to support such important phases of learning as planning and control (Valle et al., 2021); and (b) variables such as acceptance structures, learner performance, and usability are most commonly examined, while variables more related to autonomy support including metacognitive strategies, learning strategy, and decision-making are among the least examined variables in LADs research (Sahin & Ifenthaler, 2021). Our research directly addresses the research gap by designing a student-facing LAD that offers students’ autonomy support and guides students to make well-informed learning choices on their own.

Study 1

In this paper, we reported the initial process of designing a student-facing LAD that offers students’ autonomy support by providing necessary information for students to set their own goals and choose learning activities that are aligned with their goals. The LAD will be added to an existing online STEM learning system and will be evaluated by a group of students.

Lower, V. & Gao, F. (in preparation). An user-experience approach to the design of student-facing learning analytics dashboard.

Gao, F., Lower, V., Abouheaf, M., Krishnankuttyrema, R., & Sarder, M. (2023). Designing a student-facing learning analytics dashboard to support online STEM practices. Companion Proceedings of the 13th International Learning Analytics and Knowledge Conference (pp. 65-67). New York, NY: ACM.