Culinary matter is an integral part of people’s everyday lives, especially for those who like to taste a variety of flavors and uniqueness of different food. It is easier to find information about the culinary you want to try through sites and social media. With the information, visitors can get an idea of the taste, price, and location of culinary treats. In the DKI Jakarta area, social media play an important role in providing data on people's assessments of culinary treats. Considering the use of social media platforms such as Instagram, Facebook, and Twitter, the researchers apply the methods of Naive Bayes and Support Vector Machine that later produce a result that can be used as a basis for assessing culinary treats in Jakarta. This research takes data from three sources, namely Twitter, Zomato and Quora. The data collection period for Twitter is from March 01, 2022-June 30, 2022, while for Zomato and Quora from September 2021 to June 2022, during which 2520 data are collected. The data will be then processed to draw a conclusion. The accuracy test on three sources show the accuracy score of Naïve Bayes is higher than that of the Support Vector Machine, with the accuracy of Naïve Bayes of 76.00% and that of the support vector machine of 74.00%, resulting in more positive responses than negative responses and indicating that culinary treats in Jakarta is considered good by the community.
Read full abstract