Open AccessSupport Vector Machine VS Information Gain: Analisis Sentimen Cyberbullying di Twitter Indonesia
Author(s) -
Christevan Destitus,
Wella Wella,
Suryasari Suryasari
Publication year - 2020
Publication title -
ultima infosys/ultimainfosys
Language(s) - English
Resource type - Journals
eISSN - 2549-4015
pISSN - 2085-4579
DOI - 10.31937/si.v11i2.1740
Subject(s) - information gain , hyperplane , support vector machine , weighting , computer science , feature selection , entropy (arrow of time) , information gain ratio , value (mathematics) , artificial intelligence , process (computing) , data mining , machine learning , mathematics , combinatorics , physics , quantum mechanics , acoustics , operating system
This study aims to clarify tweets on twitter using the Support Vector Machine and Information Gain methods. The clarification itself aims to find a hyperplane that separates the negative and positive classes. In the research stage, there is a system process, namely text mining, text processing which has stages of tokenizing, filtering, stemming, and term weighting. After that, a feature selection is made by information gain which calculates the entropy value of each word. After that, clarify based on the features that have been selected and the output is in the form of identifying whether the tweet is bully or not. The results of this study found that the Support Vector Machine and Information Gain methods have sufficiently maximum results.