Students feedback analysis model using deep learning-based method and linguistic knowledge for intelligent educational systems

Student feedback analysis is time-consuming and laborious work if it is handled manually. This study explores the use of a new deep learning-based method to design a more accurate automated system for analysing students' feedback (called DTLP: deep learning and teaching process). The DTLP employs convolutional neural networks (CNNs), bidirectional LSTM (BiLSTM), and attention mechanism. To the best of our knowledge, a deep learning-based method using a unified feature set, which is representative of word embedding, sentiment knowledge, sentiment shifter rules, linguistic and statistical knowledge, has not been thoroughly studied with regard to sentiment analysis of student feedback. Furthermore, DTLP uses multiple strategies to overcome the following drawbacks: contextual polarity; sentence types; words with similar semantic context but opposite sentiment polarity; word coverage limit of an individual lexicon; and word sense variations. To evaluate the DTLP, we conducted an experiment on a large volume of students' feedback. The results showed (i) DTLP outperforms the existing systems in the field, (ii) DTLP that learns from this unified feature set can acquire significantly higher performance than one that learns from a feature subset, (iii) the ensemble of sentiment shifter rules, word embedding, statistical, linguistic, and sentiment knowledge allows DTLP to obtain significant performance, and (iv) an attention mechanism into CNN-BiLSTM improves the performance of DTLP. In addition, the deployed method looks for potential causes behind student feedback.