Artificial intelligence in higher education: The interplay of competence, perception, and artificial intelligence influence on self-learning outcomes

Abstract

The quick adoption of artificial intelligence (AI) in higher education has changed how students learn and cultivate their capacity for self-directed learning. Although previous research has looked at the adoption of AI, few have investigated the ways in which perception, competency, and AI's behavioural effect, all work together to shape self-learning outcomes in emerging nations. These dynamics were examined in this study among 509 students from two of Ghana's largest universities of teacher education with distance education programmes. The study used a cross-sectional survey approach, and Partial Least Squares Structural Equation Modeling to evaluate the data. The results revealed three key insights. First, competence in using generative AI particularly skills in prompt creation, error detection, and ethical awareness were significant but modestly predicted self-learning outcomes. Second, perception of AI's usefulness and ease of use showed no significant direct effect, suggesting that positive attitudes alone were insufficient to generate academic benefits. Collectively, the model explained 57.4% of the variance in self-learning outcomes and demonstrated strong predictive relevance. Practically, the study underscored the need for higher education institutions to embed AI literacy into curricula for improved learning outcomes.