Application of Deep Learning Algorithms in Improving Teaching Quality Assessment of Applied Psychology Micro-Major Programs

Applied psychology micro-major programs, as emerging interdisciplinary education models, face challenges in teaching quality assessment including complex evaluation dimensions and heterogeneous learning behavior data. Addressing the problem that existing assessment models struggle to capture deep temporal dependencies and key influencing factors in students' learning processes, this study constructs a deep learning assessment framework integrating Bidirectional Long Short-Term Memory networks and multi-head attention mechanisms. The framework integrates multi-source data including learning behavior sequences and psychological assessment data, utilizes BiLSTM networks to extract bidirectional temporal features, and combines multi-head attention mechanisms to achieve adaptive weight allocation and feature fusion of assessment elements, establishing a high-precision teaching quality prediction model. Experimental verification based on teaching data from 180 students across two consecutive semesters in an applied psychology micro-major program at a university shows that the proposed model achieves an assessment accuracy of 97.23%, an improvement of 11.6 percentage points over traditional machine learning methods and 4.8 percentage points over single deep learning models, with an inference time of 1.8 milliseconds. The model can effectively identify core factors affecting teaching quality and provide interpretable assessment evidence, offering precise data support for applied psychology micro-major teaching reform.