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.

Analysis of The Influence of Customer Perceived Benefit, Ease of Use and Sales Promotion on The Decision to Use Digital Wallets for Shopeepay Customers

“…Assuming all other factors are equal, usefulness is influenced by convenience, but the more user-friendly a system is, the more valuable it is. According to findings from earlier studies, users' happiness with the Go-Jek application and the Go-Pay function is positively and significantly impacted by convenience and usefulness at the same time [11]. Sales promotions are aimed at stimulating consumer needs and urging customers to immediately buy certain products or services.…”

Analysis of E-Commerce User Acceptance of Technology-Based Loan Application Features Using The UTAUT Model

“…With the level of usage growing and the problems that occur as obstacles to pay-later success that can affect user satisfaction, it is necessary to carry out analysis and evaluation related to measuring the level of user satisfaction. In addition to an analysis of competitors' payment offerings, it may be worth a complementary analysis [22] [23]. The required input variable from the equation pay-later concludes that performance expectancy has a significant positive relationship to behavioral intention; the better the pay-later performance, the better the effect on e-commerce users [24] [25].…”

The Role of E-Customer Satisfaction as Intervening Variable in Relationship Between E-Service Quality, E-Recovery and E-Customer Loyalty of Indonesian Railroad Access Customers

“…The community in Indonesia is happy that there is rail service serving a number of routes to various destinations. This is demonstrated by the significant number of railway passengers in 2019, one of whom was traveling to the Java area [5]. According to research by the Central Statistics Agency (BPS), there were 336,799 Indonesian railway passengers in Jabodetabek in 2018, 336,045 in 2019, and just 154,591 did so in 2020.…”