Representation of the Student’s Controllable Performance Features Based on PS2CLH Model

Conference: The Barcelona Conference on Education (BCE2022)
Title: Representation of the Student’s Controllable Performance Features Based on PS2CLH Model
Stream: Design, Implementation & Assessment of Innovative Technologies in Education
Presentation Type: Live-Stream Presentation
Authors:
Arlindo Almada, London Metropolitan University, United Kingdom
Qicheng Yu, London Metropolitan University, United Kingdom
Preeti Patel, London Metropolitan University, United Kingdom

Abstract:

Nowadays, the number of studies measuring and representing students’ learning and performance has increased. However, there remains a lack of research that represents and measures factors or features within students’ control that impact their performances. For university managers, subject tutors and academic mentors, it is essential to represent, measure, analyse and monitor student performance alongside controllable factors affecting their academic achievement to enhance the student experience. This research evaluates the connection among students’ behaviours and lifestyles, particularly the controllable factors. Controllable factors incorporated in our PS2CLH model are the perspectives of Psychology, Self-responsibility, Sociology, Communication, Learning and Health & wellbeing. This paper proposes a controllable performance features representation in three-dimensional space based on the PS2CLH model. A cluster presentation of the features allows for targeted interventions for students who need additional support. It also indicates clearly where each student stands by using a student web profile and the necessary direction each student needs to take to get to the desired cluster. Initial data presents a clear pattern of creating a diagonal of seven clusters or students’ stages from the bottom (0, 0, 0) to the top (100, 100, 100) and leading to the use of filters or queries to represent better features such as sleep-problem, stress, practice exercises and time management. Preliminary results highlight patterns of best-performing students with specific factors/features located in the highest clusters on the rank. This insight facilitates data-driven decisions leading to effective student interventions.

---

Conference Comments & Feedback

Place a comment using your LinkedIn profile


Share this Presentation