Abstract
Sentiment analysis has become a critical area of research in Natural Language Processing (NLP), enabling insights from unstructured text. Within this field, Aspect-Based Sentiment Analysis (ABSA) plays a practical role in domains such as healthcare, where patients drug reviews often contain diverse opinions across multiple aspects, including overall comments, perceived benefits, and side effects. However, aspect-level classification remains challenging due to class imbalance, subtle sentiment expression, and the limitations of traditional models. This research investigates the performance of three modeling paradigms: traditional machine learning (SVM, SVC, and XGBoost), deep learning (CNN-BiLSTM), and transformer-based approaches (DistilBERT sentence-pair classification). Using the UCI Drug Review dataset, the study implements evaluation through stratified train/test splits, nested cross-validation, and multiple metrics including precision, recall, F1-score, and confusion matrices, to ensure robust comparison. Results demonstrate that traditional models such as SVM and XGBoost offer interpretability and strong precision but struggle with recall on minority classes. The CNN-BiLSTM model improved contextual understanding but displayed weakness in neutral sentiment detection. DistilBERT, achieved the best overall performance, demonstrating higher F1-score and stronger balance across all aspects, effectively handling subtle sentiment distinctions. This research provides a comprehensive multi-model comparison for ABSA in healthcare, highlighting trade-offs between efficiency, interpretability, and accuracy. It underscores the strength of transformer-based models for nuanced sentiment tasks while affirming the continued relevance of traditional approaches in practical applications.
Advisor
Rushit Dave
Committee Member
Rajeev Bukralia
Committee Member
Mansi Bhavsar
Date of Degree
2025
Language
english
Document Type
Thesis
Degree
Master of Science (MS)
Program of Study
Data Science
Department
Computer Information Science
College
Science, Engineering and Technology
Recommended Citation
Park, E. S. (2025). Evaluating aspect-based sentiment analysis in healthcare drug reviews across machine learning, deep neural networks, and transformer models [Master’s thesis, Minnesota State University, Mankato]. Cornerstone: A Collection of Scholarly and Creative Works for Minnesota State University, Mankato. https://cornerstone.lib.mnsu.edu/etds/1567/
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Rights Statement
