<![CDATA[Comments from social media can be analyzed further. Social media is used to interact from one person to another, as well as with the government. This Issue Was Raised Because Of Debate And Public Opinion From The Community, Institutions And Ngos Regarding Ministerial Regulation No. 30 Of 2021 Concerning Prevention And Handling Of Sexual Violence. In The Higher Education Environment, Therefore In This Research We Want To Examine What Is The Main Root Of The Problem Using A Methodical Approach Using Natural Language Processing. The pre-processing applied is case folding, tokenization, elimination of stop words, stemming using literature. The model implementing PSO failed to improve accuracy on all kernels. Best performance before applying PSO to twitter dataset using linear kernel. This study conducted sentiment analysis regarding the issuance of ministerial regulation no. 30 of 2021. The data obtained was then preprocessed. The performance measured is accuracy and f1-macro in the model without PSO and accuracy in the model using accuracy. The model to be formed uses linear kernels, RBF and polynomials of order 1 and order 2. Sentence analysis is a field that analyzes sentiment, attitudes and emotions of entities and their attributes in text form. The aim of this research is to compare the performance of the Support Vector Machine classification algorithm without Particle Swarm Optimization feature selection and the performance of the Support Vector Machine classification algorithm using Particle Swarm Optimization feature selection. The data obtained is then pre-processed. The data set was automatically labeled using VADER (Valence Dictionary for Sentiment Reasoning). The kernels that succeeded in increasing accuracy were the RBF kernel and polynomials on the Twitter dataset. Keywords: SVM, Vader, PSO, Sentiment Analysis, Government Policy]]>
Copyrights © 2024
