This study investigated undergraduate students’ attitudes, perceptions, and satisfaction toward Netflix’s recommendation algorithm, focusing on students of Adeleke University, Ede, Nigeria. With algorithmic personalisation becoming a dominant feature of Over-The-Top (OTT) streaming platforms, understanding how users interact with and evaluate these systems is essential. A quantitative descriptive survey design was adopted, and data were collected from a stratified sample of 333 students using a structured questionnaire. The data collected were analysed using descriptive and inferential statistical techniques. Technology Acceptance Model (TAM) and the Uses and Gratifications Theory (UGT) were employed for this study. The results revealed a generally moderate level of satisfaction with Netflix’s recommendation system. Although 61.5% of students agreed that their viewing history influenced recommendations and 59.7% reported discovering new content through the algorithm, only 46.2% expressed overall satisfaction. Many respondents perceived the recommendations as repetitive and not reflective of their preferences. Regression analysis demonstrated a statistically significant positive relationship between user attitudes/perceptions and engagement with the Netflix algorithm (β = 0.054, t = 13.828, p < 0.001, R² = 0.366), indicating that these factors could explain 36.6% of the variance in engagement. The study shows that the majority of Adeleke University undergraduates are dissatisfied with Netflix's recommendations, finding them often irrelevant. To improve user experience, the study recommends that Netflix refine its algorithms by incorporating diverse data points and implement educational initiatives to enhance user understanding and feedback, as well as introduce customisable recommendation settings.
Vol. 4, No 2, pp. 64-70.