ANALISIS SENTIMEN RANCANGAN UNDANG-UNDANG TINDAK PIDANA KEKERASAN SEKSUAL/UNDANG-UNDANG TINDAK PIDANA KEKERASAN SEKSUAL PENGGUNA TWITTER MENGGUNAKAN ALGORITMA NAÏVE BAYES CLASSIFIER

ADAM PANCA PUTRA PINARIA, . (2023) ANALISIS SENTIMEN RANCANGAN UNDANG-UNDANG TINDAK PIDANA KEKERASAN SEKSUAL/UNDANG-UNDANG TINDAK PIDANA KEKERASAN SEKSUAL PENGGUNA TWITTER MENGGUNAKAN ALGORITMA NAÏVE BAYES CLASSIFIER. Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

	Text COVER.pdf Download (1MB)
	Text BAB 1.pdf Download (435kB)
	Text BAB 2.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text BAB 3.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text BAB 4.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text BAB 5.pdf Restricted to Registered users only Download (94kB) | Request a copy
	Text DAFTAR PUSTAKA.pdf Download (260kB)
	Text LAMPIRAN.pdf Restricted to Registered users only Download (2MB) | Request a copy

Abstract

Penelitian ini bertujuan untuk melakukan analisis sentimen Rancangan Undang-Undang Tindak Pidana Kekerasan Seksual/Undang-Undang Tindak Pidana Kekerasan Seksual pengguna Twitter menggunakan metode Naïve Bayes Classifier dan mengevaluasi kinerja klasifikasinya. Analisis sentimen pada penelitian ini menggunakan metode Naïve Bayes Classifier dengan pembobotan Term Frequency-Inverse Document Frequency. Proses pengumpulan data dilakukan menggunakan pustaka Snscrape Python. Data pakai yang digunakan untuk dibersihkan hanya yang bersentimen positif dan negatif. Proses pembersihan data melalui tahapan preproses teks yaitu Case Folding, Cleansing, Tokenizing, Stopword Removal, Stemming dan Normalization. Analisis sentimen yang dihasilkan berupa 12.807 data, dengan sentimen negatif sebanyak 10.263 data (80,1%) dan sentimen positif sebanyak 2.544 data (19,9%). Sentimen pengguna twitter Indonesia mengarah pada sentimen negatif. Pengujian kinerja model klasifikasi metode analisis sentimen penelitian ini menggunakan teknik Confusion Matrix pada hasil klasifikasi data uji dengan nilai Accuracy klasifikasi algoritma sebesar 93%, nilai Precision klasifikasi sebesar 99%, nilai Recall klasifikasi sebesar 87% dan F- Measure sebesar 93%. Dari nilai pengujian yang dihasilkan dapat disimpulkan model klasifikasi dengan metode algoritma Naive Bayes Classifier memiliki kinerja yang sangat baik. This study aims to analyze the sentiment of the Draft Law on Sexual Violence Crimes / Law on Sexual Violence Crimes on Twitter users using the Naïve Bayes Classifier method and evaluate its classification performance. Sentiment analysis in this study uses the Naïve Bayes Classifier method with Term Frequency-Inverse Document Frequency weighted. The data collection process was carried out using the Snscrape Python library. The usage data that is used for cleaning is only positive and negative sentiment. The process of cleaning the data through the stages of text preprocessing, namely Case Folding, Cleansing, Tokenizing, Stopword Removal, Stemming and Normalization. The resulting sentiment analysis is 12,807 data, with negative sentiment as much as 10,263 data (80.1%) and positive sentiment as much as 2,544 data (19.9%). The sentiment of Indonesian Twitter users is towards negative sentiment. Testing the performance of the classification model for the sentiment analysis method of this study uses the Confusion Matrix technique on the results of the classification of test data with an algorithm classification Accuracy value of 93%, a classification Precision value of 99%, a classification Recall value of 87% and an F-Measure of 93%. From the resulting test values, it can be concluded that the classification model with the Naive Bayes Classifier algorithm method has very good performance.

Item Type:	Thesis (Sarjana)
Additional Information:	1.) Dr. Widodo, M.Kom. 2.) Murien Nugraheni, S.T., M.Cs.
Subjects:	Teknologi dan Ilmu Terapan > Teknik Komputer
Divisions:	FT > S1 Pendidikan Teknik Informatika Komputer
Depositing User:	Users 16772 not found.
Date Deposited:	13 Feb 2023 06:17
Last Modified:	13 Feb 2023 06:17
URI:	http://repository.unj.ac.id/id/eprint/36783

Actions (login required)

View Item