The Application of Support Vector Machine Method to Analyze the Sentiments of Netizens on Social Media Regarding the Accessibility of Disabilities in Public Spaces

Abstract

According to the Ministry of Social Affairs of the Republic of Indonesia, based on data from the Central Bureau of Statistics, there will be 22.5 million people with disabilities in Indonesia. As time goes on, it is possible that the number of people with disabilities will increase. So, facilities and infrastructure that are friendly to people with disabilities must be given great attention. Various comments from the public regarding this matter arose on social media, especially Twitter, both positive and negative. There are lot of tweet in Indonesian related to this matter, which will be classified using the Support Vector Machine algorithm with the Radial Basis Function kernel using Grid Search and cross-validation. The parameters used are in the range C, γ and produce a maximum accuracy of the parameter combination, result of this study was aligned with previous research that a good and appropriate parameter combination of C and γ in the RBF kernel SVM method will produce maximum accuracy of the classification results.