Comparison of SVM Naïve Bayes Algorithm for Sentiment Analysis Toward West Java Governor Candidate Period 2018-2023 Based on Public Opinion on Twitter

摘要

Opinion is a statement conveyed by a person or group of people in addressing a problem by providing predictions or expectations about the event. No guarantee that an opinion automatically will be true because it is not reinforced by the facts, it is subjective, and there is a different opinion about an event. Everyone has different views and same rights to express opinions or give opinions toward particular event. Public opinion is view of someone for certain problem comes out due to prior conversation with another person who may have an effect on the opinion given. Public opinion comes from a discussion process in addressing the problem then lead to a conclusion as a joint decision and a shared opinion. One of the media to convey public opinion is through social media like twitter. Public opinion about the election of West Java governor candidate period 2018-2023 on twitter was increasingly widespread. There are several sentiments emerged for four candidates elected on twitter accounts such as Ridwan Kamil-Uu Ruzhanul Ulum, Tubagus Hasanuddin-Anton Charliyan, Sudrajat-Ahmad Syaikhu, and Deddy Mizwar-Dedi Mulyadi. Therefore, it is necessary to classify the sentiments to the existing opinion so that it can be predicted in advance which of the governor candidate pair of West Java who has more positive and predictable sentiments will be elected as governor period 2018-2023. The data used by the researchers is tweet in Indonesian Language with keywords Rindu, Hasanah, Asyik, 2DM with datasets number is 800 tweets. There are many classification techniques commonly used for opinion sentiment analysis. This study compares two classification techniques namely Support Vector Machine Algorithm (SVM) and Naïve Bayes Classifier (NBC). The results show that the Algorithm of Naïve Bayes Classifier (NBC) has a higher accuracy level of Support Vector Machine (SVM), up to 94% for Deddy Mizwar-Dedi Mulyadi.