Sentimen analisis tweet pornografi kaum homoseksual menggunakan perbandingan algoritma support vector machine dan naïve bayes

Fitri, Merisa (2020) Sentimen analisis tweet pornografi kaum homoseksual menggunakan perbandingan algoritma support vector machine dan naïve bayes. Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

Preview	Text ABSTRACT.pdf - Accepted Version Download (8kB) | Preview
Preview	Text ABSTRAK.pdf - Accepted Version Download (107kB) | Preview
	Text Cover.pdf - Accepted Version Download (646kB)
Preview	Text BAB I.pdf - Accepted Version Download (900kB) | Preview
Preview	Text BAB II.pdf - Accepted Version Download (1MB) | Preview
Preview	Text BAB III.pdf - Accepted Version Download (1MB) | Preview
	Text BAB IV.pdf - Accepted Version Restricted to Registered users only Download (1MB)
Preview	Text BAB V.pdf - Accepted Version Download (125kB) | Preview
Preview	Text DAFTAR PUSTAKA.pdf - Accepted Version Download (300kB) | Preview

Abstract

Currently, Twitter is not only used as a place to communicate with each other and talk only opinions. Twitter is also often used by people who are not responsible for pornographic content. This is also done by the experimentalists. Homosexuality is a meeting with same-sex interests. This is of course considered taboo for Indonesian people who can only accept the heterosexual agreement of the section. Thus the minority began to explore the world of social media to get a partner. But intellectuals also use Twitter social media to transfer pornographic content. Therefore the data used in this study is pornographic tweet data and not pornography from advocates. The data used in this study consisted of 1000 data tweets. The classification algorithm used in this study is the Support Vector Machine (SVM) and Naïve Bayes algorithm, while SVM is an algorithm that embraces the concept to find the best hyperplane and Naïve Bayes is an algorithm that embraces the concepts of policy and statistics. The final result of this study is a comparison of the two algorithms, after discussing the pre-processing and TF-IDF stages related to the value obtained by the SVM algorithm by 86% while for the Naïve Bayes algorithm by 82%. After measuring the performance of the model for the two algorithms obtained precision and remember the SVM algorithm and Naïve Bayes. SVM Precision Algorithm is 97% with 74% recall. Naïve Bayes Precision Algorithm is 77% and 93% recall. This proves that the SVM algorithm is able to provide better values compared to the Naïve Bayes algorithm. Keywords: Accuracy, Classification, Homosexual, Naïve Bayes, Pornography, SVM

Actions (login required)

View Item