SENTIMENT EXTRACTION FROM PATIENT FEEDBACK AND HEALTH RECORDS USING DEEP LEARNING

Abstract

The rapid growth of patient-generated drug reviews has introduced a valuable resource for understanding real-world treatment outcomes and user experiences. This thesis ex- plores deep learning approaches for extracting sentiment from such unstructured feedback, focusing on two architectures: Bidirectional Long Short-Term Memory (Bi-LSTM) and a hybrid Convolutional Neural Network with Bi-LSTM (CNN-BiLSTM). Unlike many existing studies that depend on static pre-trained embeddings, both mod- els are trained from scratch using task-specific word representations. This enhances their adaptability to domain-specific terminology and nuanced sentiment expressions commonly found in medical reviews. The experiments are conducted on the publicly available Drug Review Dataset from the UCI Machine Learning Repository, hosted on Kaggle. Reviews are preprocessed and labeled as positive, negative, or neutral based on user-provided ratings. The models are evaluated using standard metrics including accuracy, precision, recall, F1-score, and Cohen’s Kappa. The results indicate that the CNN-BiLSTM model outperforms the standalone Bi- LSTM across all metrics. Its combined ability to extract local features and capture bidi- rectional context leads to more robust sentiment prediction. This research demonstrates the feasibility of building end-to-end sentiment classifiers tailored to healthcare narratives and lays the groundwork for future extensions such as multilingual analysis, aspect-based sentiment classification, and interpretable AI models.