SENTIMENT ANALYSIS ON THE PERMENDIKBUD CONCERN PREVENTION AND TREATMENT OF SEXUAL VIOLENCE IN HIGHER EDUCATIONAL ENVIRONMENTS USING SUPPORT VECTOR MACHINE (SVM)

Reinhard Alfaries Saemani
Nina Setiyawati (Universitas kristen satya wacana)

JITK (Jurnal Ilmu Pengetahuan dan Komputer)
Vol 8 No 1 (2022): JITK Issue August 2022

Social media is no longer a foreign thing for people in today's technological era, one of the social media that is often used is Twitter. Twitter is used to communicate with other people and Twitter users can also give each other opinions on an issue. By involving 1252 Tweets, this study aimed to use the Support Vector Machine (SVM) algorithm on Tweet data. The processes carried out in this research are crawling, cleaning, translate, labeling, tokenizing, stop words, stemming, SVM classification. .The results showed that the accuracy level of using the SVM algorithm after the param grid was 80.3% using the parameter C = 10; gamma = 0.1; and kernel = rbf as a benchmark in the classification process. This shows that the classification process using the SVM algorithm is quite accurate.