Visual versus Contextual Instructional Guidance in a Computer Vision-Based Learning Environment: Effects on Educational Technology Students’ Visual Data Interpretation and Intelligent Educational Interaction Design

Abstract

This study investigated the effect of visual versus contextual instructional guidance in a computer vision-based learning environment on educational technology students’ visual data interpretation skills and intelligent educational interaction design. The study responds to a growing need to prepare students not only to use artificial intelligence and computer vision tools, but also to understand their visual outputs, interpret their pedagogical meaning, recognize their limitations, and translate them into informed design decisions. A quasi-experimental pretest–posttest design with two experimental groups was employed. The participants were 100 second-level students from the Department of Educational Technology, Faculty of Specific Education, Alexandria University, equally assigned to a visual guidance group and a contextual guidance group. Both groups studied the same content, completed the same tasks, and used the same computer vision-based learning environment; the only difference was the type of instructional guidance provided. Data were collected using a Visual Data Interpretation Skills Test, a Visual Data Interpretation Performance Rubric, an Intelligent Educational Interaction Design Cognitive Test, an Intelligent Educational Interaction Design Product Rubric, a Learning Environment Interaction Log, and an Environment Usability Scale. The results showed statistically significant differences in favor of the contextual guidance group in visual data interpretation, practical performance, cognitive understanding of intelligent educational interaction design, and the quality of the final design product. Interaction log indicators also showed that contextual guidance was associated with higher learning pathway quality, more frequent post-support revisions, and more purposeful use of feedback. No statistically significant difference was found between the two groups in overall environment usability. These findings suggest that contextual guidance was more effective in helping students move beyond noticing visual elements toward interpreting their meaning and using them in design decisions, whereas visual guidance primarily supported attention and element location. The study recommends that computer vision-based learning environments should combine visual clarity with contextual explanation so that students can interpret visual outputs critically and transform them into responsible, interpretable, and pedagogically meaningful intelligent educational interactions.