ANALISIS SENTIMEN UJARAN KEBENCIAN PEMILIHAN PRESIDEN 2019 MENGGUNAKAN ALGORITMA NAÏVE BAYES

MUFTIA CHALIDA, NIM. 15650016 (2019) ANALISIS SENTIMEN UJARAN KEBENCIAN PEMILIHAN PRESIDEN 2019 MENGGUNAKAN ALGORITMA NAÏVE BAYES. Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

[img]
Preview
Text (ANALISIS SENTIMEN UJARAN KEBENCIAN PEMILIHAN PRESIDEN 2019 MENGGUNAKAN ALGORITMA NAÏVE BAYES)
15650016_BAB I_BAB_TERAKHIR_DAFTAR_PUSTAKA.pdf - Published Version

Download (6MB) | Preview
[img] Text (ANALISIS SENTIMEN UJARAN KEBENCIAN PEMILIHAN PRESIDEN 2019 MENGGUNAKAN ALGORITMA NAÏVE BAYES)
15650016_BAB II_S.D._SEBELUM_BAB_TERAKHIR.pdf - Published Version
Restricted to Registered users only

Download (8MB)

Abstract

Reflecting presidential election on the 2014, the widespread spread of racial issues and hate speech are predicted to occur again in the 2019 presidential election. Based on data from Semiocast Jakarta was occupying the top city of the 20 most active cities after sorting by number of tweets or tweet as much as 1,058 billion in June, then followed Bandung city, West Java, that surprisingly was the sixth place. (Semiocast, 2012) Using a multistage random data collection method, which is based on data from semiocast sites, with sampling areas covering Jakarta, Bandung, Semarang, Surabaya, Yogyakarta. Data are tweet posts on the 2019 presidential election keyword search results. As for the results of the implementation of hate speech sentiment analysis on the test data a number of 5055 data were tweeted with hastag pilpres2019 in the cities of Jakarta, Bandung, Semarang, Surabaya, Yogyakarta by utilizing the classification model from training data using Naive Bayes Classifier and TF-IDF Weighting obtained irrelevant sentiment classification as much as 11.3% with 573 data, negative sentiments as much as 35.4% with 1786 data, neutral sentiments as much as 26.7% as many as 1350 data and positive sentiments as much as 26.6 % as much as 1343 data, with a tendency towards negative sentiments with the largest value of 35.4% in the 5 cities. While the results of the sentiment of hate speech were the biggest in each city, namely: Jakarta with a negative sentiment of 33.8%, Bandung with negative sentiment of 65.4%, Surabaya with a positive sentiment of 37.2%, Yogyakarta with a number of negative sentiments 51.8%. and Semarang with negative sentiment of 61.7%.

Item Type: Thesis (Skripsi)
Additional Information: M. Didik R. Wahyudi, M.T.
Uncontrolled Keywords: sentiment analysis, twitter, classification, naïve bayes classifier, multistage random, hate speech, 2019 presidential election
Subjects: Tehnik Informatika
Divisions: Fakultas Sains dan Teknologi > Teknik Informatika (S1)
Depositing User: Drs. Mochammad Tantowi, M.Si.
Date Deposited: 12 Apr 2019 09:02
Last Modified: 12 Apr 2019 09:02
URI: http://digilib.uin-suka.ac.id/id/eprint/34534

Share this knowledge with your friends :

Actions (login required)

View Item View Item
Chat Kak Imum