The Right Sentiment Analysis Method of Indonesian Tourism in Social Media Twitter Case Study: The City of Bali

Steven, Cristian and Wella, Wella (2020) The Right Sentiment Analysis Method of Indonesian Tourism in Social Media Twitter Case Study: The City of Bali. IJNMT (International Journal of New Media Technology), 7 (2). ISSN 2355-0082

Full text not available from this repository.

Abstract

The growth of social media is changing the way humans communicate with each other, many people use social media such as Twitter to express opinions, experiences and other things that concern them, where things like this are often referred to as sentiments. The concept of social media is now the focus of business people to find out people's sentiments about a product or place that will become a business. Sentiment Analysis or often also called opinion mining is a computational study of people's opinions, appraisal, and emotions through entities, events and attributes owned. Sentiment analysis itself has recently become a popular topic for research because sentiment analysis can be applied in many industrial sectors, one of which is the tourism industry in Indonesia. To be able to do a sentiment analysis requires mastery of several techniques such as techniques for doing text mining, machine learning and natural language processing (NLP) to be able to process large and unstructured data coming from social media. Some methods that are often used include Naive Bayes, Neural Networks, K-Nearest Neighbor, Support Vector Machines, and Decision Tree. Because of this, this research will compare these four algorithms so that an algorithm can be used to analyze people's sentiments towards the city of Bali.

Item Type: Article
Subjects: 000 Computer Science, Information and General Works > 000 Computer Science, Knowledge and Systems > 005 Computer Programming
Divisions: Faculty of Engineering & Informatics > Information System
Depositing User: mr admin umn
Date Deposited: 17 Dec 2021 04:03
Last Modified: 17 Dec 2021 04:03
URI: https://kc.umn.ac.id/id/eprint/19733

Actions (login required)

View Item View Item