Penerapan metode support vector machine dan lexicon based features dalam analisis pada tingkat kepuasan layanan ojek online pada media twitter

Syaifudin, Moh. (2023) Penerapan metode support vector machine dan lexicon based features dalam analisis pada tingkat kepuasan layanan ojek online pada media twitter. Undergraduate thesis, Politeknik Negeri Jember.

	Text (Abstract) Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (8kB)
	Text (Bab 1 Pendahuluan) Bab 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (149kB)
	Text (DaftarPustaka) Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (139kB)
	Text (FullText) FullText.pdf Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Transportation is something that is relatively close to the people, transportation has several types, namely two-wheeled and four-wheeled. One of them is the ojek online, ojek online has become one of the most popular public transportation modes today in Indonesia because they make mobility easier when there is a traffic jam in the city. The main service of ojek online is to take the passengers to their destination, but they also serve the pick-up and drop-off of goods, food ordering, shopping, tickets, and so on. Along with the rapid development of ojek online, people use social media such as Twitter to share a view and opinions about these services. Twitter can be a source of public opinion or sentiment data, which is important to accommodate every opinion and sentiment from customers and the public. Text data from tweets that contain opinions and sentiments can be collected to provide conclusions regarding the good and bad ratings of ojek online services. This study uses the Support Vector Machine and Lexicon Based Features methods to analyze public sentiment toward ojek online services. The dataset is collected via Twitter social media. The data that has been obtained will be carried out at the pre-processing stage, TF-IDF, Lexicon Based Features, Union Vector, and Classification using the Support Vector Machine method. Based on the analysis results, the accuracy value is 70%, precision is 70%, and recall is 70%.

Actions (login required)

View Item