Lexicon-based sentiment analysis of medical data

Keywords: medical social media resources, sentiment analysis, lexicon-based approach, machine learning

Abstract

The article explores the possibilities of applying sentiment analysis for the use of information collected in the medical social media environment in medical decision-making. Opinions and feedbacks of medical social media subjects (physician, patient, health institution, etc.) make media resources an important source of information. The information collected in these sources can be used to improve the quality of health care and make decisions, taking into account the public opinion. Researches in this field have actualized the application of artificial intelligence methods, i.e., sentiment analysis methods. In this regard, it segments the medical social media environment in accordance with user relationships, and shows the nature of the information collected on each segment and its importance in decision-making to improve the quality of medical services. The possibilities of applying the lexicon-based sentiment analysis method for studying and classifying the collected data are explained in detail. The open database cms_hospital_satisfaction_2019 by the Kaggle company is used, and the opinions collected from patients about the services provided by a specific medical center are analyzed. This study analyzes opinions using the Valence Aware Dictionary and Sentiment Reasoner lexicon and classifies them as neutral, positive and negative and the implementation of this process is described in stages. The importance of the obtained results in decision-making regarding the better organization, evaluation and improvement of the activity of the medical institution is shown

Downloads

Download data is not yet available.

Author Biographies

Masuma Mammadova, Azerbaijan National Academy of Sciences

Corresponding Member of Azerbaijan National Academy of Sciences, Doctor of Technical Sciences, Professor

Department of Number 11

Institute of Information Technology

Zarifa Jabrayilova, Azerbaijan National Academy of Sciences

Doctor of Technical Sciences, Associate Professor

Chief Researcher

Department of Number 11

Institute of Information Technology

Nargiz Shikhaliyeva, Azerbaijan National Academy of Sciences

Engineer-Programmer

Department of Number 11

Institute of Information Technology

References

Mammadova, M., Jabrayilova, Z. (2019). Electronic medicine: formation and scientific-theoretical problems. Baku: "Information Technologies" publishing house, 319. Available at: https://ict.az/uploads/files/E-medicine-monograph-IIT-ANAS.pdf

Mammadova, M., Isayeva, A. (2018). E-health activity in social media environment. Problems of Information Society, 09 (1), 52–62. doi: https://doi.org/10.25045/jpis.v09.i1.05

Mammadovа, M., Jabrayilova, Z., Isayeva, A. (2020). Conceptual Approach to the Use of Information Acquired in Social Media for Medial Decisions. Online Journal of Communication and Media Technologies, 10 (2). doi: https://doi.org/10.29333/ojcmt/7877

Issue Brief: Social Networks in Health Care: Communication, collaboration and insights. Produced by the Deloitte Center for Health Solutions. Available at: http://healthinformationandcommunicationsystems.pbworks.com/w/file/fetch/93972338/SM%204b%20Full.pdf

Fogelson, N. S., Rubin, Z. A., Ault, K. A. (2013). Beyond likes and tweets: an in-depth look at the physician social media landscape. Clinical Obstet Gynecol, 2013, 56 (3), 495–508.

Tibb.az. Your virtual doctor. Available at: https://tibb.az/home

Aattouchi, I., Elmendili, S., Elmendili, F. (2021). Sentiment Analysis of Health Care: Review. E3S Web of Conferences, 319, 01064. doi: https://doi.org/10.1051/e3sconf/202131901064

Khan, M. T., Khalid, S. (2015). Sentiment Analysis for Health Care. International Journal of Privacy and Health Information Management, 3 (2), 78–91. doi: https://doi.org/10.4018/ijphim.2015070105

Kausar, S., Huahu, X., Ahmad, W., Shabir, M. Y., Ahmad, W. (2020). A Sentiment Polarity Categorization Technique for Online Product Reviews. IEEE Access, 8, 3594–3605. doi: https://doi.org/10.1109/access.2019.2963020

Yevseiev, S., Goloskokova, A., Shmatko, O. (2021). Researching a machine learning algorithm for a face recognition system. Technology Transfer: Fundamental Principles and Innovative Technical Solutions, 10–12. doi: https://doi.org/10.21303/2585-6847.2021.002222

Hamdan, H., Bellot, P., Bechet, F. (2015). Sentiment Lexicon-Based Features for Sentiment Analysis in Short Text. Research in Computing Science, 90 (1), 217–226. doi: https://doi.org/10.13053/rcs-90-1-17

Colab Research Google. Available at: https://colab.research.google.com/drive/17KLlgzCipalUtlID_ToGdoalKd-9A9OB#scrollTo=5N3Vro5vYyap

Ramya Sri, V. I. S., Niharika, Ch., Maneesh, K., Ismail, M. (2019). Sentiment Analysis of Patients' Opinions in Healthcare using Lexicon-based Method. International Journal of Engineering and Advanced Technology, 9 (1), 6977–6981. doi: https://doi.org/10.35940/ijeat.a2141.109119

Rokade, P. P., D, A. K. (2019). Business intelligence analytics using sentiment analysis-a survey. International Journal of Electrical and Computer Engineering (IJECE), 9 (1), 613. doi: https://doi.org/10.11591/ijece.v9i1.pp613-620

U.S. Hospital Customer Satisfaction 2016-2020. Available at: https://www.kaggle.com/datasets/abrambeyer/us-hospital-customer-satisfaction-20162020

Lexicon-based sentiment analysis of medical data

👁 83
⬇ 57
Published
2022-11-28
How to Cite
Mammadova, M., Jabrayilova, Z., & Shikhaliyeva, N. (2022). Lexicon-based sentiment analysis of medical data. Technology Transfer: Fundamental Principles and Innovative Technical Solutions, 7-10. https://doi.org/10.21303/2585-6847.2022.002671
Section
Computer Sciences