Hospital Facebook Reviews Analysis Using a Machine Learning Sentiment Analyzer and Quality Classifier.

Afiq Izzudin A Rahim,Sook-Ling Chua,Mohd Ismail Ibrahim,Kamarul Imran Musa

doi:10.3390/healthcare9121679

Afiq Izzudin A Rahim, Sook-Ling Chua + Show 2 more

Open Access

https://doi.org/10.3390/healthcare9121679

Copy DOI

Abstract

While experts have recognised the significance and necessity of social media integration in healthcare, no systematic method has been devised in Malaysia or Southeast Asia to include social media input into the hospital quality improvement process. The goal of this work is to explain how to develop a machine learning system for classifying Facebook reviews of public hospitals in Malaysia by using service quality (SERVQUAL) dimensions and sentiment analysis. We developed a Machine Learning Quality Classifier (MLQC) based on the SERVQUAL model and a Machine Learning Sentiment Analyzer (MLSA) by manually annotated multiple batches of randomly chosen reviews. Logistic regression (LR), naive Bayes (NB), support vector machine (SVM), and other methods were used to train the classifiers. The performance of each classifier was tested using 5-fold cross validation. For topic classification, the average F1-score was between 0.687 and 0.757 for all models. In a 5-fold cross validation of each SERVQUAL dimension and in sentiment analysis, SVM consistently outperformed other methods. The study demonstrates how to use supervised learning to automatically identify SERVQUAL domains and sentiments from patient experiences on a hospital’s Facebook page. Malaysian healthcare providers can gather and assess data on patient care via the use of these content analysis technology to improve hospital quality of care.

Highlights

Public health professionals need accurate and up-to-date data from a range of sociodemographic categories to develop effective quality management systems for healthcare services and policy activities
The internet and social media have been recommended as potential substitutes for assessing patient satisfaction and evaluating the quality of healthcare services [15,16]
The findings indicate that support vector machine (SVM) and naive Bayes (NB) may be used interchangeably as preferable classifiers in a supervised setting since they outperformed other classifiers in sentiment analysis and text classification

Summary

Introduction

Public health professionals need accurate and up-to-date data from a range of sociodemographic categories to develop effective quality management systems for healthcare services and policy activities. To assess patient satisfaction with various aspects of service quality, patient satisfaction surveys such as the Hospital Consumer Assessment of Healthcare Providers and Systems (HCAHPS) and service quality (SERVQUAL) questionnaires are frequently used [5,6,7,8]. These surveys are the product of years of assessment, are methodical in their administration and review, and may gather many patients’ replies per institution [9,10,11]. The internet and social media have been recommended as potential substitutes for assessing patient satisfaction and evaluating the quality of healthcare services [15,16]

Objectives

Methods

Results

Discussion

Conclusion