The diagnosis of self-efficacy using mouse and keyboard input
Year: 2013
Type: dissertation
Abstract: Self-efficacy is a student’s belief in his or her own capabilities regarding the completion of a specific task. Students with high levels of self-efficacy are proven to be more effective learners. If serious games, intelligent tutoring systems and computer enhanced learning in general can diagnose self-efficacy, it could lead to improved tutoring strategies, consequently improving the learning experience and process of the student. This research investigated the diagnosis of self-efficacy levels at runtime using mouse and keyboard input, the default communication channels of computer enhanced learning. In an empirical experiment, small to medium significant correlations were found between mouse movement and self-efficacy levels for the variables Distance difference, Number of pauses, Time difference, Pause time and Question time. Linear multiple regression revealed that mouse movement variables were able to predict 17% of the levels of self-efficacy, in which the Time difference was the largest and only significant contributor. This means that Time difference can be used to partially diagnose self-efficacy levels. In contrast, no correlations were found between typing performance and self-efficacy levels.
Author: M.S.R. Dijkstra
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: green
OpenAlex ID: W33566940
