Sentiment Analysis of Telemedicine Applications on Twitter Using Lexicon-Based and Naive Bayes Classifier Methods

Abstract

Since the onset of the COVID-19 pandemic in Indonesia, many people have turned to telemedicine programs as an alternative to minimize social interactions, opting for consultations from the safety of their homes using smartphones and internet connectivity. Given the necessity for physical distancing and avoiding crowded places, these applications have become indispensable substitutes for in-person medical consultations. Numerous apps facilitating access to healthcare services have been introduced in Indonesia, ranging from business startups to initiatives by the Ministry of Health. Telemedicine can potentially revolutionize healthcare in Indonesia, addressing critical health challenges. A significant issue within Indonesia's healthcare system is the scarcity of doctors and their uneven distribution. With only four doctors per 10,000 people, this figure falls far below the WHO guideline of 10 doctors per 1,000. Sentiment analysis of these applications was conducted to evaluate how telemedicine applications meet public needs and offer an alternative solution. Lexicon-based and naive Bayes methods were employed to classify tweet data into positive, neutral, and negative sentiments. The results revealed 908 positive tweets, 172 negative tweets, and 168 neutral tweets, indicating predominantly positive public perceptions of telemedicine applications. The naive Bayes classifier exhibited a 74% accuracy rate, with a precision of 98% and a recall of 86%. These findings underscore the positive impact and acceptance of telemedicine applications among the Indonesian populace, emphasizing their significance in augmenting the nation's healthcare landscape.