Enhancing University English Education with Big Data Analytics to Optimize Teaching Methods and Student Engagement

The integration of big data analytics and Artificial Intelligence (AI)-based solutions has revolutionized English learning at the university level by allowing data-driven and personalized teaching. Although its use is increasing, the current literature mostly uses disaggregated datasets and fails to capture the joint effect of behavior and perception on learning outcomes. The study will fill these gaps by offering a dual-data model which combines secondary big data comprising of the with primary survey data of 230 respondents ( 190 students and 40 teachers). The research question studied is the impact of learner factors, motivation, and interactivity of the platforms on English language proficiency in terms of vocabulary, reading, and speaking. Through descriptive and inferential statistics analysis, it is determined that students who were less proficient in the previous assessment were most improved in their entire learning, especially in reading comprehension. After intervention scores showed that the average vocabulary increase was 0.45 scored and reading improvement 0.62 scored. Survey data showed a range of satisfaction with big data-based platforms ( 2.89 to 3.07 on a 5 -point Likert scale) with mostly neutral or slightly positive comments. These findings support the utility of the proposed framework for better teaching practices and student learning, thus supplying universities with large-scale data for their decision-making regarding the improvement of teaching English to non-native speakers. Descriptive statistics were used to summarize learning patterns and platform usage, while inferential statistics such as correlation analysis, ANOVA, and regression were applied to examine relationships among variables and validate the significance of the findings.