Sentiment Analysis of Citizen on Twitter in Accessibility of Disabilities at The Public Space Using Support Vector Machine (SVM) Method with Radial Basis Function (RBF) Kernel

According to the Ministry of Social Affairs of the Republic of Indonesia, based on data from the Biro Pusat Statistik (BPS), there were $\mathbf{2 2 . 5}$ million people with disabilities in Indonesia until October 2020. As time goes on, people with disabilities may 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 from positive to negative comments. There are 1209 tweets in Indonesian related to this matter which will be classified using the Support Vector Machine (SVM) algorithm with the Radial Basis Function (RBF) kernel using GridSearch and Cross Validation. The parameters used are in the range $\mathrm{C}=[0.01$; $0.1; 1; 10; 100; 1,000; 10,000; 100,000; 1,000,000; 10,000,000]$ and $\gamma=[0.0000001; 0.000001; 0.00001; 0.0001; 0.001; 0.01; 0.1;$ $1; 10; 100]$ and produces a maximum accuracy of the parameter combination $C=1.000$ and $\gamma=0.000001(\mathrm{le}-06)$ of $83.37 \%$ which supports previous research that a good and appropriate parameter combination of C and $\gamma$ in the RBF kernel SVM method will produce maximum accuracy of the classification results.