A Deep Learning Model for Student Sentiment Analysis on Course Reviews

The learning status of students directly influences their learning outcomes. Course evaluations by students offer valuable insights into the effectiveness of teaching methodologies and students' own perceptions of their learning environments. These evaluations encapsulate a spectrum of emotions, ranging from satisfaction to frustration, and provide a holistic view of the educational experience. Analyzing course evaluations plays a crucial role in deciphering students' learning outcomes. By extracting sentiments from these evaluations, educators can gain a deeper understanding of students' experiences, identifying areas of improvement and tailoring teaching strategies to better meet students' needs. Sentiment analysis of course evaluations falls under text sentiment analysis. In this study, we leverage advanced deep learning techniques to extract sentiment from course evaluations. Specifically, we capitalize on the capabilities of BERT (Bidirectional Encoder Representations from Transformers), a state-of-the-art language model known for its proficiency in understanding context and semantic meaning. By harnessing BERT's bidirectional encoding and feature extraction capabilities, coupled with the bidirectional influence of BiLSTM (Bidirectional Long Short-Term Memory) models, we aim to capture nuanced relationships within the text data. Moreover, we incorporate the attention mechanism into our model architecture to assign varying weights to different parts of the input sequence, enabling the model to focus on relevant information effectively. The proposed BERT-BiLSTM-ATTENTION (BBA) model represents an innovative approach that capitalizes on the synergy between these advanced techniques. Our experimental results, based on real-world data extracted from online comments on Massive Open Online Courses (MOOCs), demonstrate the superior performance of the BBA model compared to existing approaches. By thoroughly exploring bidirectional semantics and accounting for both preceding and subsequent influences, our model offers enhanced predictive capabilities and deeper insights into students' learning experiences. This has significant implications for enhancing students' learning outcomes and improving teaching methods.