Adoption of ChatGPT by university students for academic purposes: Partial least square, artificial neural network, deep neural network and classification algorithms approach

Abstract

Given the limited extent of study conducted on the application of ChatGPT in the realm of education, this domain still needs to be explored. Consequently, the primary objective of this study is to evaluate the impact of factors within the extended value-based adoption model (VAM) and to delineate the individual contributions of these factors toward shaping the attitudes of university students regarding the utilization of ChatGPT for instructional purposes. This investigation incorporates dimensions such as social influence, self-efficacy, and personal innovativeness to augment the VAM. This augmentation aims to identify components where a hybrid approach, integrating partial least squares (PLS), artificial neural networks (ANN), deep neural networks (DNN), and classification algorithms, is employed to accurately discern both linear and nonlinear correlations. The data for this study were obtained through an online survey administered to university students, and a purposive sample technique was employed to select 369 valid responses. Following the initial data preparation, the assessment process comprised three successive stages: PLS, ANN, DNN and classification algorithms analysis. Intention is influenced by attitude, which is predicted by perceived usefulness, perceived enjoyment, social influence, self-efficacy, and personal innovativeness. Moreover, personal innovativeness has the maximum contribution to attitude followed by self-efficacy, enjoyment, usefulness, social influence, technicality, and cost. These findings will support the creation and prioritization of student-centered educational services. Additionally, this study can contribute to creating an efficient learning management system to enhance students' academic performance and professional efficiency.