Sentiment Analysis of Online Gojek Transportation Services on Twitter Using the Naïve Bayes Method

Abstract

Abstract— Social media is the most accessed internet content by internet users in Indonesia. This is not surprising, given the many benefits that social media provides, one of which is the benefit of self-expression. Self-expression can include many things, including emotional openness, which is the openness of a person in conveying the emotions he is feeling. Along with the development of social media, emotional disclosure is ubiquitous in social media, one of which is social media Twitter. With the development of information technology, means of transportation are also developing with the existence of online transportation services. Currently, the use of online transportation services has become a necessity, so it is necessary to conduct a sentiment analysis on online transportation services to find out how the public responds to these online transportation services. The purpose of this study is to analyze community responses by analyzing data in the form of tweets and then classifying them into positive, negative, and neutral classes using the Naïve Bayes method because the error rate obtained is lower when the dataset is large, besides that the accuracy of Naive Bayes and the speed is higher. high when applied to a larger dataset. The results of this study indicate that the neutral sentiment level of public tweets is greater than the level of positive sentiment and negative sentiment with an accuracy of 25.00%.

Enhancing Sentiment Analysis With Chatbots: A Comparative Study of Text Pre-Processing

“…This research proves that Chatbots such as Chat GPT-3.5 Open AI and Google Bard can be considered as alternative text pre-processing methods in Sentiment Analysis, offering an option alongside Python-based text pre-processing as presented in studies [5], [24]- [26], or solely relying on Rapidminer as shown in studies [3], [4], [6], [21], [22]. This research stands out as unique compared to previous studies because it combines widely used Text Pre-Processing tools like Rapidminer with Artificial Intelligence products, namely Chat GPT-3.5 Open AI and Google Bard.…”

“…Previous research has predominantly utilized Rapidminer applications, as seen in studies [3], [4], [6], [21], [22], while others have used Python, as seen in studies [5], [23]- [26]. The average accuracy value resulting from these three studies using Python is 73.33%.…”

Sentiment Analysis of Twitter Users to the PeduliLindungi Using Naïve Bayes Algorithm

“…Naïve Bayes is one of the techniques for developing a classification that combines probability and statistical methods with "naive" to manage conditions between attributes independently [16]. Naïve Bayes shown high accuracy and easy to train compared to the other machine learning algorithms with low error rate for large dataset [17]. Naïve Bayes algorithm is used to predict the likelihood of a specific word belonging to a specific class.…”

Sentiment Analysis of Society Towards the Child-free Phenomenon (Life Without Children) on Twitter Using Naïve Bayes Algorithm

“…Therefore, several methods can be employed to shorten the time of the sentiment analysis process on the tweet data. One method that can be used to analyze the sentiment of a matter is the Naïve Bayes method or algorithm [9], [10]. The Naïve Bayes algorithm is based on the Bayes principle, which explains that all events have contributions of equal importance or independence concerning selecting a particular class.…”