Sentiment analysis for patient feedback after treatment in hospital

Abstract

Developing and improving hospital services, with a focus on meeting the needs of patients, is crucial. Therefore, feedback or comments related to the hospital, both positive and negative, are particularly beneficial for de velopment and improvement. To facilitate the reading of messages by hospital staff and to quickly address negative feedback, we analyzed the sentiment of feedback or comments. The research methodology involved analyzing data using the pyThaiNLP library in Python and evaluating the results in terms of accuracy, precision, recall, and F1-score. The research results indicate that the SVM (Support Vector Machine) model outperformed Naïve Bayes in the test dataset, achieving 86% accuracy compared to 80% accuracy. Both models achieved the same accuracy, which is 76%, in the test dataset.

References

KerstinDenecke;YihanDeng,“Sentiment analysis in medical settings: New opportunities and challenges” Elevier, Germany 2015

Adam Imansyah Pandesenda; Rika Rizki Yana, “Sentiment Analysis of Service Quality of Online Healthcare Platform Using Fast Large-Margin” IEEE Jakarta, Indonesia, November 2020

Benjamin Chanakot, Charun Sanrach “THE EFFECTIVE FEATURES SELECTION THROUGH OPINION CLASSIFICATION FOR CURRICULUM ADJUSTMENT” วารสารมหาวิทยาลัยศรีนครินทรวิโรฒ (สาขาวิทยาศาสตร์ และเทคโนโลยี), July 2019

G.Saranya, G.Geetha, Chakrapani.k “Sentiment analysis of healthcare Tweets using SVM Classifier” IEEE, October 2020

พิศิษฐ์ บวรเลศิ สุธี, วรภัทร ไพรีเกรง “The Model o Sentiment Analysis for Classifying the Online Shopping Reviews” Journal of Engineering and Digital Technology (JEDT), Bangkok,Thailand, 27 June 2022

FERNANDO ARIAS, (Member, IEEE), MAYTEE ZAMBRANO NÚEEZ, (Senior Member, IEEE), ARIEL GUERRA-ADAMES “Sentiment Analysis of Public Social Media as a Tool for Health-Related Topics” Digital