This project focuses on the classroom interaction of college English and proposes a framework for optimizing college English classroom interaction by integrating big data. Taking the behavioral analysis layer as the entry point, using PSO’s improved K-mean clustering algorithm, we focus on analyzing the specific application of data mining technology in students’ learning behavior. Then we conduct experiments on two classes of students in a university, design classroom behavioral coding to analyze classroom interaction behavior, and explore the application effect of this English classroom interaction optimization pathway. The students were divided into six categories through cluster analysis, with focused learners (22%) and continuous learners (36%) having the highest fidelity scores and the largest proportion, and the analysis of students’ learning behaviors can provide a reference for teachers’ classroom teaching. The composition of the English interaction optimization classroom changes from teacher-led to student-led in the traditional classroom, the teacher-student speech curves intersect each other and both appear four peaks, showing good classroom scope and teacher-student interaction effect, and the path of interaction optimization in the English classroom based on big data is practicable.