International Journal of Modern Education and Computer Science (IJMECS)
IJMECS Vol. 18, No. 5, 8 Oct. 2026
Cover page and Table of Contents: PDF (size: 1015KB)
Linguistic Encapsulation and Semantic Amalgamation based Sentiment Polarity Analysis Using Patient Reviews
PDF (1015KB), PP.118-133
Views: 0 Downloads: 0
Author(s)
Syed Zabiulla SK
1,2,*
Mausumi Goswami
3
Index Terms
GloVe, Sentiment Analysis, BERT, BiGRU, CNN.
Abstract
Sentiment analysis of medication evaluations uses Natural Language Processing (NLP) techniques to analyze users' thoughts and feelings about medications (treatments) they have received, helping evaluate the effectiveness of therapy. Machine learning aids in evaluating medication effectiveness; however, it has limitations due to the context-dependent nature of medication-related sentiment. Even though deep learning provides a better ability to capture nuances in language, deep learning models will require larger datasets and considerable computational resources. A Hybrid Bidirectional Gated Recurrent Unit-Convolutional Neural Network (Bi-GRU-CNN) is proposed for sentiment analysis of medication evaluations to address these shortcomings. The evaluation of medicines from patients involved collecting reviews and compiling them into a structured dataset as the first step. The process uses various methods to preprocess the reviews, including lowercasing, stop-word removal, and punctuation removal. SentiWordNet is used to assign sentiment polarity to reviews after they have been pre-processed, classifying them as neutral, negative, or positive. The attention-based Bidirectional Long Short-Term Memory (Bi-LSTM) model is then applied for part-of-speech tagging to extract semantic information, and a dependency tree parser that uses Global Vectors for Word Representation (GloVe) to extract syntactic information. Bidirectional Encoder Representations from Transformers (BERT) are then used to fuse the two features into a single representation. A hybrid BiGRU-CNN model is then used to classify sentiment and accurately predict the polarity of drug reviews. The CNN layer captures many local patterns, and the BiGRU layer processes sequential dependencies in both directions. The features are combined and utilized in a series of dense layers to create classifications. The proposed method achieved an overall Accuracy of 97.50%, a False Omission Rate of 4.30%, and a selectivity of 94.20% in sentiment analysis of drug reviews. The proposed method improves contextual understanding and feature extraction for a more granular understanding of sentiment.
Cite This Paper
Syed Zabiulla SK, Mausumi Goswami, "Linguistic Encapsulation and Semantic Amalgamation based Sentiment Polarity Analysis Using Patient Reviews", International Journal of Modern Education and Computer Science(IJMECS), Vol.18, No.5, pp. 118-133, 2026. DOI:10.5815/ijmecs.2026.05.07
Reference
[1]Bansal, A., & Kumar, N. (2022). Aspect-based sentiment analysis using attribute extraction of hospital reviews. New Generation Computing, 40(4), 941-960.
[2]Sharma, S. S., & Dutta, G. (2021). SentiDraw: Using star ratings of reviews to develop domain specific sentiment lexicon for polarity determination. Information Processing & Management, 58(1), 102412.
[3]Yazdani, A., Shamloo, M., Khaki, M., & Nahvijou, A. (2023). Use of sentiment analysis for capturing hospitalized cancer patients' experience from free-text comments in the Persian language. BMC Medical Informatics and Decision Making, 23(1), 275.
[4]Saad, E., Din, S., Jamil, R., Rustam, F., Mehmood, A., Ashraf, I., & Choi, G. S. (2021). Determining the efficiency of drugs under special conditions from users’ reviews on healthcare web forums. IEEE Access, 9, 85721-85737.
[5]Sweidan, A. H., El-Bendary, N., & Al-Feel, H. (2021). Sentence-level aspect-based sentiment analysis for classifying adverse drug reactions (ADRs) using hybrid ontology-XLNet transfer learning. IEEE Access, 9, 90828-90846.
[6]Durga, P., Godavarthi, D., Kant, S., & Basa, S. S. (2024). Aspect-based drug review classification through a hybrid model with ant colony optimization using deep learning. Discover Computing, 27(1), 19.
[7]Karthick, S., & Muthukumaran, N. (2024). U-Net Based Deep Regression Network Architecture for Single Image Super Resolution of License Plate Image. Lecture Notes in Networks and Systems, 946, 311-321.
[8]Kumar, J. A., Trueman, T. E., & Cambria, E. (2022). Gender-based multi-aspect sentiment detection using multilabel learning. Information Sciences, 606, 453-468.
[9]N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A simple way to prevent neural networks from overfitting,” Journal of Machine Learning Research, vol. 15, pp. 1929–1958, 2014.
[10]Mudigonda, A., Yalavarthi, U. D., Satyanarayana, P., Alkhayyat, A., Arularasan, A. N., Ganesh, S. S., & Kumar, C. M. S. (2024). IDEAL: an inventive optimized deep ensemble augmented learning framework for opinion mining and sentiment analysis. Social Network Analysis and Mining, 14(1), 89.
[11]Grissette, H., & Nfaoui, E. H. (2022). Affective concept-based encoding of patient narratives via sentic computing and neural networks. Cognitive Computation, 14(1), 274-299.
[12]Grissette, H., & Nfaoui, E. H. (2023). Deep associative learning approach for bio-medical sentiment analysis utilizing unsupervised representation from large-scale patients’ narratives. Personal and Ubiquitous Computing, 27(6), 2055-2069.
[13]Han, Y., Liu, M., & Jing, W. (2020). Aspect-level drug reviews sentiment analysis based on double BiGRU and knowledge transfer. IEEE Access, 8, 21314-21325.
[14]Ahmed, I., Ahmad, M., Chehri, A., & Jeon, G. (2023). A heterogeneous network embedded medicine recommendation system based on LSTM. Future Generation Computer Systems, 149, 1-11.
[15]Nayak, S. K., Garanayak, M., Swain, S. K., Panda, S. K., & Godavarthi, D. (2023). An intelligent disease prediction and drug recommendation prototype by using multiple approaches of machine learning algorithms. IEEE Access, 11, 99304-99318.
[16]Es-Sabery, F., Es-Sabery, K., Qadir, J., Sainz-De-Abajo, B., Hair, A., Garcia-Zapirain, B., & De La Torre-Díez, I. (2021). A MapReduce opinion mining for COVID-19-related tweets classification using enhanced ID3 decision tree classifier. IEEE Access, 9, 58706-58739.
[17]Mahalakshmi, V., Shenbagavalli, P., Raguvaran, S., Rajakumareswaran, V., & Sivaraman, E. (2024). Twitter sentiment analysis using conditional generative adversarial network. International Journal of Cognitive Computing in Engineering, 5, 161-169.
[18]Mathebula, M., Modupe, A., & Marivate, V. (2024). ChatGPT as a text annotation tool to evaluate sentiment analysis on south African financial institutions. IEEE Access, 12, 144017-144043.
[19]Le-Hong, P., & Cambria, E. (2024). Integrating graph embedding and neural models for improving transition-based dependency parsing. Neural Computing and Applications, 36(6), 2999-3016.
[20]Ellaky, Z., Benabbou, F., Matrane, Y., & Qaqa, S. (2024). A hybrid deep learning architecture for social media bots detection based on BiGRU-LSTM and GloVe word embedding. IEEE Access, 12, 100278-100294.
[21]Murat, A., & Ali, S. (2024). Low-resource POS tagging with deep affix representation and multi-head attention. IEEE Access, 12, 66495-66504.
[22]Wang, A., Qi, Y., & Baiyila, D. (2025). C-BERT: A Mongolian reverse dictionary based on fused lexical semantic clustering and BERT. Alexandria Engineering Journal, 111, 385-395.
[23]Lu, Y., Wu, X., Liu, P., Li, H., & Liu, W. (2023). Rice disease identification method based on improved CNN-BiGRU. Artificial Intelligence in Agriculture, 9, 100-109.
[24]Xia, K., Huang, J., & Wang, H. (2020). LSTM-CNN architecture for human activity recognition. Ieee Access, 8, 56855-56866.
[25]Dataset 1: Harsh Jain (2020) kaggle: [https://www.kaggle.com/code/harshjain123/drugs-review-sentiment/input].
[26]Kokab, S. T., Asghar, S., & Naz, S. (2022). Transformer-based deep learning models for the sentiment analysis of social media data. Array, 14, 100157.