HYBRID FRAMEWORK FOR SENTIMENT ANALYSIS OF PATIENT REVIEWS USING LEXICON BASED BIO-BIDIRECTIONAL ENCODER REPRESENTATIONS FROM TRANSFORMERS
DOI:
https://doi.org/10.7494/csci.2026.27.1.6461Abstract
Sentiment analysis identify and categorize the emotions expressed in reviews and written content posted on websites, utilizing text analysis technologies. Prior research has illustrated how analyzing sentiments in pharmaceutical reviews can offer valuable insights to help organizations and medical professionals assess the safety of medications post-market release. These insights protect patients and bolster their trust in healthcare providers. Currently, frameworks in the healthcare sector use either lexical techniques or machine learning models to analyze opinions. Machine learning-based approaches necessitate labeled data, while syntax-based methods are more specific to domains and have broader applications. To enhance results, this study integrates a hybrid approach that merges lexical strategies with deep learning and machine learning models. Reviews are annotated using two comprehensive emotion lexicons, SenticNet and Text Blob. Feature engineering techniques like TF and TF-IDF are utilized to extract crucial features. Lastly, classification tasks are performed using machine learning models and deep learning models tailored to biological literature. Performance metrics are utilized to evaluate the effectiveness of this combined methodology. Experimental results demonstrate that hybridization of lexicon and transformer based medical learning model produces superior outcomes compared to using each method independently. Additionally, Text Blob exhibits impressive performance, achieving 97% accuracy with hybrid of LSTM and CNN. and the another is medical transformer model is Bio Bert model on a drug review dataset, and 95% accuracy with Term Frequency, and the logistic regression model. TextBlob also attains 94% accuracy when paired with Term Frequency and LSTM model , and 97% accuracy when combined with the Bio Bert transformer based Model on a dataset sourced from tweets.
Downloads
References
[1] Aakur S.N., Sarkar S.: Leveraging symbolic knowledge bases for commonsense
natural language inference using pattern theory, IEEE Transactions on Pat-
tern Analysis and Machine Intelligence, vol. 45(11), pp. 13185–13202, 2023.
doi: 10.1109/tpami.2023.3287837.
[2] Agarwal B., Mittal N.: Prominent feature extraction for review analysis: an
empirical study, Journal of Experimental & Theoretical Artificial Intelligence,
vol. 28(3), pp. 485–498, 2016.
[3] Agarwal B., Poria S., Mittal N., Gelbukh A., Hussain A.: Concept-level sentiment
analysis with dependency-based semantic parsing: a novel approach, Cognitive
Computation, vol. 7, pp. 487–499, 2015. doi: 10.1007/s12559-014-9316-6.
[4] Alharbi N.M., Alghamdi N.S., Alkhammash E.H., Al Amri J.F.: Evaluation
of sentiment analysis via word embedding and RNN variants for Amazon on-
line reviews, Mathematical Problems in Engineering, vol. 2021(1), 5536560, 2021.
doi: 10.1155/2021/5536560.
[5] Ali T., Schramm D., Sokolova M., Inkpen D.: Can i hear you? sentiment analysis
on medical forums. In: Proceedings of the sixth international joint conference on
natural language processing, pp. 667–673, 2013.
[6] Birjali M., Kasri M., Beni-Hssane A.: A comprehensive survey on sentiment
analysis: Approaches, challenges and trends, Knowledge-Based Systems, vol. 226,
107134, 2021. doi: 10.1016/j.knosys.2021.107134.
[7] Biyani P., Caragea C., Mitra P., Zhou C., Yen J., Greer G.E., Portier K.: Co-
training over domain-independent and domain-dependent features for sentiment
analysis of an online cancer support community. In: Proceedings of the 2013
IEEE/ACM International Conference on Advances in Social Networks Analysis
and Mining, pp. 413–417, 2013. doi: 10.1145/2492517.2492606.
[8] Choudhary R.R., Jisnu K., Meena G.: Image dehazing using deep learning tech-
niques, Procedia Computer Science, vol. 167, pp. 1110–1119, 2020. doi: 10.1016/
j.procs.2020.03.413.
[9] Deng S., Sinha A.P., Zhao H.: Adapting sentiment lexicons to domain-specific so-
cial media texts, Decision Support Systems, vol. 94, pp. 65–76, 2017. doi: 10.1016/
j.dss.2016.11.001.
[10] Fern´andez-Gavilanes M., ´Alvarez-L´opez T., Juncal-Mart´ınez J., Costa-
Montenegro E., Gonz´alez-Casta˜no F.J.: Unsupervised method for sentiment anal-
ysis in online texts, Expert Systems with Applications, vol. 58, pp. 57–75, 2016.
doi: 10.1016/j.eswa.2016.03.031.
[11] Fu X.L., Wu J., Chen J., Liu S.: Attribute-Sentiment Pair Correlation Model
Based on Online User Reviews, Journal of Sensors, vol. 2019(1), 2456752, 2019.
doi: 10.1155/2019/2456752
[12] Goeuriot L., Na J.C., Min Kyaing W.Y., Khoo C., Chang Y.K., Theng Y.L., Kim
J.J.: Sentiment lexicons for health-related opinion mining. In: Proceedings of the
2nd ACM SIGHIT International Health Informatics Symposium, pp. 219–226,
2012. doi: 10.1145/2110363.2110390.
[13] Habernal I., Pt´aˇcek T., Steinberger J.: Supervised sentiment analysis in Czech
social media, Information Processing & Management, vol. 50(5), pp. 693–707,
2014. doi: 10.1016/j.ipm.2014.05.001.
[14] Hassan M.E., Hussain M., Maab I., Habib U., Khan M.A., Masood A.: De-
tection of sarcasm in Urdu tweets using deep learning and transformer based
hybrid approaches, IEEE Access, vol. 12, pp. 61542–61555, 2024. doi: 10.1109/
access.2024.3393856.
[15] Jain P.K., Pamula R., Srivastava G.: A systematic literature review on machine
learning applications for consumer sentiment analysis using online reviews, Com-
puter science review, vol. 41, 100413, 2021. doi: 10.1016/j.cosrev.2021.100413.
[16] Lee J., Yoon W., Kim S., Kim D., Kim S., So C.H., Kang J.: BioBERT: a pre-
trained biomedical language representation model for biomedical text mining,
Bioinformatics, vol. 36(4), pp. 1234–1240, 2020.
[17] Liu S., Lee I.: Extracting features with medical sentiment lexicon and position
encoding for drug reviews, Health information science and systems, vol. 7, pp. 1–
10, 2019. doi: 10.1007/s13755-019-0072-6.
[18] Meena G., Mohbey K.K.: Sentiment analysis on images using different trans-
fer learning models, Procedia Computer Science, vol. 218, pp. 1640–1649, 2023.
doi: 10.1016/j.procs.2023.01.142.
[19] Meena G., Mohbey K.K., Acharya M., Lokesh K.: An improved convolutional
neural network-based model for detecting brain tumors from augmented MRI
images, Journal of Autonomous Intelligence, vol. 6(1), 2023. doi: 10.32629/
jai.v6i1.561.
[20] Meena G., Mohbey K.K., Indian A., Khan M.Z., Kumar S.: Identifying emotions
from facial expressions using a deep convolutional neural network-based approach,
Multimedia Tools and Applications, vol. 83(6), pp. 15711–15732, 2024.
[21] Meena G., Mohbey K.K., Kumar S.: Monkeypox recognition and prediction from
visuals using deep transfer learning-based neural networks, Multimedia Tools and
Applications, vol. 83(28), pp. 71695–71719, 2024. doi: 10.1007/s11042-024-18437-
z.
[22] Meena G., Mohbey K.K., Kumar S., Chawda R.K., Gaikwad S.V.: Image-based
sentiment analysis using InceptionV3 transfer learning approach, SN Computer
Science, vol. 4(3), 242, 2023. doi: 10.1007/s42979-023-01695-3.
[23] Molina-Gonz´alez M.D., Mart´ınez-C´amara E., Mart´ın-Valdivia M.T., Perea-
Ortega J.M.: Semantic orientation for polarity classification in Spanish reviews,
Expert systems with applications, vol. 40(18), pp. 7250–7257, 2013. doi: 10.1016/
j.eswa.2013.06.076.
[24] Montejo-R´aez A., Mart´ınez-C´amara E., Mart´ın-Valdivia M.T., Ure˜na-L´opez
L.A.: Ranked wordnet graph for sentiment polarity classification in twitter,
Computer Speech & Language, vol. 28(1), pp. 93–107, 2014. doi: 10.1016/
j.csl.2013.04.001.
[25] Mujahid M., Kanwal K., Rustam F., Aljedaani W., Ashraf I.: Arabic ChatGPT
tweets classification using RoBERTa and BERT ensemble model, ACM Transac-
tions on Asian and Low-Resource Language Information Processing, vol. 22(8),
pp. 1–23, 2023. doi: 10.1145/3605889.
[26] Mujahid M., Lee E., Rustam F., Washington P.B., Ullah S., Reshi A.A., Ashraf I.:
Sentiment analysis and topic modeling on tweets about online education during
COVID-19, Applied Sciences, vol. 11(18), 8438, 2021. doi: 10.3390/app11188438.
[27] Mujahid M., Rustam F., Shafique R., Chunduri V., Villar M.G., Ballester J.B.,
Diez I.d.l.T., Ashraf I.: Analyzing sentiments regarding ChatGPT using novel
BERT: A machine learning approach, Information, vol. 14(9), p. 474, 2023.
doi: 10.3390/info14090474.
[28] Na J.C., Kyaing W.Y.M., Khoo C.S., Foo S., Chang Y.K., Theng Y.L.: Sen-
timent classification of drug reviews using a rule-based linguistic approach. In:
The Outreach of Digital Libraries: A Globalized Resource Network: 14th In-
ternational Conference on Asia-Pacific Digital Libraries, ICADL 2012, Taipei,
Taiwan, November 12-15, 2012, Proceedings 14, pp. 189–198, Springer, 2012.
doi: 10.1007/978-3-642-34752-8 25.
[29] Nakov P., Rosenthal S., Kiritchenko S., Mohammad S.M., Kozareva Z., Ritter A.,
Stoyanov V., Zhu X.: Developing a successful SemEval task in sentiment analysis
of Twitter and other social media texts, Language Resources and Evaluation,
vol. 50, pp. 35–65, 2016. doi: 10.1007/s10579-015-9328-1.
[30] Ofek N., Caragea C., Rokach L., Biyani P., Mitra P., Yen J., Portier K., Greer G.:
Improving sentiment analysis in an online cancer survivor community using dy-
namic sentiment lexicon. In: 2013 international conference on social intelligence
and technology, pp. 109–113, IEEE, 2013. doi: 10.1109/society.2013.20.
[31] Park S., Lee W., Moon I.C.: Efficient extraction of domain specific sentiment
lexicon with active learning, Pattern Recognition Letters, vol. 56, pp. 38–44, 2015.
doi: 10.1016/j.patrec.2015.01.004.
[32] del Pilar Salas-Z´arate M., L´opez-L´opez E., Valencia-Garc´ıa R., Aussenac-Gilles
N., Almela ´A., Alor-Hern´andez G.: A study on LIWC categories for opinion
mining in Spanish reviews, Journal of Information Science, vol. 40(6), pp. 749–
760, 2014. doi: 10.1177/0165551514547842.
[33] del Pilar Salas-Z´arate M., Paredes-Valverde M.A., Limon J., Tlapa D.A., B´aez
Y.A.: Sentiment Classification of Spanish Reviews: An Approach based on Fea-
ture Selection and Machine Learning Methods., J Univers Comput Sci, vol. 22(5),
pp. 691–708, 2016.
[34] Poria S., Hazarika D., Majumder N., Mihalcea R.: Beneath the tip of the ice-
berg: Current challenges and new directions in sentiment analysis research, IEEE
transactions on affective computing, vol. 14(1), pp. 108–132, 2020. doi: 10.1109/
taffc.2020.3038167.
[35] Rahman M.A., Begum M., Mahmud T., Hossain M.S., Andersson K.: Ana-
lyzing sentiments in elearning: A comparative study of bangla and romanized
bangla text using transformers, IEEE Access, vol. 12, pp. 89144–89162, 2024.
doi: 10.1109/access.2024.3419024.
[36] Saad E., Din S., Jamil R., Rustam F., Mehmood A., Ashraf I., Choi G.S.:
Determining the efficiency of drugs under special conditions from users’ re-
views on healthcare web forums, IEEE Access, vol. 9, pp. 85721–85737, 2021.
doi: 10.1109/access.2021.3088838.
[37] Saif H., He Y., Alani H.: Alleviating data sparsity for twitter sentiment analysis.
In: Making Sense of Microposts, CEUR Workshop Proceedings (CEUR-WS. org),
2012.
[38] Saleh M.R., Mart´ın-Valdivia M.T., Montejo-R´aez A., Ure˜na-L´opez L.: Experi-
ments with SVM to classify opinions in different domains, Expert Systems with
Applications, vol. 38(12), pp. 14799–14804, 2011. doi: 10.1016/j.eswa.2011.05.070.
[39] Sharif H., Zaffar F., Abbasi A., Zimbra D.: Detecting adverse drug reactions
using a sentiment classification framework, Computer Science, Medicine, 2014.
[40] Smith P., Lee M.: Cross-discourse development of supervised sentiment analysis
in the clinical domain. In: Proceedings of the 3rd workshop in computational
approaches to subjectivity and sentiment analysis, pp. 79–83, 2012.
[41] Sudheesh R., Mujahid M., Rustam F., Mallampati B., Chunduri V., de la
Torre D´ıez I., Ashraf I.: Bidirectional encoder representations from transformers
and deep learning model for analyzing smartphone-related tweets, PeerJ Com-
puter Science, vol. 9, e1432, 2023. doi: 10.7717/peerj-cs.1432.
[42] Vijayaraghavan S., Basu D.: Sentiment analysis in drug reviews using supervised
machine learning algorithms, arXiv preprint arXiv:200311643, 2020.
[43] Wankhade M., Rao A.C.S., Kulkarni C.: A survey on sentiment analysis methods,
applications, and challenges, Artificial Intelligence Review, vol. 55(7), pp. 5731–
5780, 2022. doi: 10.1007/s10462-022-10144-1.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Computer Science
This work is licensed under a Creative Commons Attribution 4.0 International License.
