Do eReferral, eWOM, Familiarity, and Cultural Distance Predict Enrollment Intention among Educational Tourists? Application of Artificial Intelligence Technique

The extant literature has demonstrated the benefits of electronic word-of-mouth (eWOM), electronic referral (eReferral), familiarity, and cultural distance on behavioral outcomes separately. Research efforts have overlooked their collective effects from educational tourism perspective. This dissertation fecundates the concept of eWOM, eReferral, familiarity, and cultural distance with social network theory to explore their influence on enrollment intention. Cross-sectional data garnered from educational tourists based on a judgmental sampling technique were subjected to linear modeling and artificial neural network modeling in training and testing phases. Empirical analysis based on a single-sourced data of n=931 educational tourists confirmed the influence of eReferral, eWOM, familiarity, and cultural distance on enrollment intentions symmetrically (linear modeling) and asymmetrically (artificial neural network). The artificial neural network technique exerted higher predictive relevance and validity. This dissertation provides meaningful theoretical, practical, and methodological insights into the collective and contributive effects of eReferral, eWOM, familiarity, and cultural distance on ed-tourist enrollment intentions. Practically, implications for university administrators and marketers are prescribed. Methodologically, the research provides incremental insights from orthodox (i.e., linear) and contemporary analytical (i.e., artificial neural network) techniques, which are relevant to the wider management and tourism literature. The results suggest that eReferral, eWOM, familiarity and cultural distance can predict intention to enroll in both symmetrically (linear modelling) and asymmetrically (Artificial Neural Network) manner. The asymmetric modeling possesses greater predictive validity and relevance. This study contributes theoretically and methodologically to the management literature by validating the proposed relationships and deploying contemporary method such as Artificial Neural Network.