ANALISIS SENTIMEN PADA PROGRAM MERDEKA BELAJAR KAMPUS MERDEKA MENGGUNAKAN ALGORITMA NAIVE BAYES DAN LOGISTIC REGRESSION

KAMALI, FAISHAL MAKARIM (2024) ANALISIS SENTIMEN PADA PROGRAM MERDEKA BELAJAR KAMPUS MERDEKA MENGGUNAKAN ALGORITMA NAIVE BAYES DAN LOGISTIC REGRESSION. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01 Cover.pdf Download (273kB) | Preview
Preview	Text (ABSTRAK) 02 Abstrak.pdf Download (26kB) | Preview
	Text (BAB I) 03 Bab 1.pdf Restricted to Registered users only Download (71kB)
	Text (BAB II) 04 Bab 2.pdf Restricted to Registered users only Download (220kB)
	Text (BAB III) 05 Bab 3.pdf Restricted to Registered users only Download (87kB)
	Text (BAB IV) 06 Bab 4.pdf Restricted to Repository staff only Download (335kB)
	Text (BAB V) 07 Bab 5.pdf Restricted to Registered users only Download (22kB)
	Text (DAFTAR PUSTAKA) 08 Daftar Pustaka.pdf Restricted to Registered users only Download (85kB)
	Text (LAMPIRAN) 09 Lampiran.pdf Restricted to Registered users only Download (271kB)

Abstract

The Merdeka Campus Program (MBKM) is a new policy launched by the Indonesian government. This policy is used by the government to improve the quality of students to adjust to technological, world of work, social, and cultural developments. As this program is a new innovation in the world of higher education, there are many discussions on social media. Nowadays, people widely use Twitter social media to give opinions or responses about trends and government policies. Analysis of 1034 tweet data was conducted using naive bayes classifier and logistic regression algorithms. The texts were classified into positive, negative and neutral categories. The implementation was done through several steps, such as text preprocessing, data division by TF-IDF, model calculation, and algorithm. The program was created using python programming language using Google Colab tools. This research displays the word cloud with the most words. Based on the research results, the system can classify with the naive Bayes algorithm with an average accuracy of 59%, an average precision of 62%, an average recall of 55%, and an average f1 score of 54%. In contrast, the system that uses the logistic regression algorithm produces sentiment analysis results with an average accuracy of 62%, an average precision of 63%, and an average recall of 60%. Keywords: Independent Campus, Naive Bayes, Logistic Regression. Program Kampus Merdeka (MBKM) adalah kebijakan baru yang diluncurkan oleh pemerintah Indonesia. Kebijakan ini digunakan oleh pemerintah untuk meningkatkan kualitas siswa untuk menyesuaikan diri dengan perkembangan teknologi, dunia kerja, sosial, dan budaya. Karena program ini merupakan inovasi baru di dunia perguruan tinggi, banyak diskusi di media sosial. Saat ini, masyarakat banyak menggunakan media sosial Twitter untuk memberikan pendapat atau tanggapan tentang tren dan kebijakan pemerintah. Analisis terhadap 1034 data tweet dilakukan dengan menggunakan algoritma naive bayes classifier dan logistic regression. Teks diklasifikasikan dalam kategori positif, negatif, dan netral. Pengimplementasian dilakukan melalui beberapa langkah, seperti preprocessing teks, pembagian data dengan TF-IDF, perhitungan model, dan algoritma. Program dibuat menggunakan bahasa pemrograman python menggunakan tools Google Colab. Penelitian ini menampilkan cloud kata dengan kata terbanyak. Berdasarkan hasil penelitian, sistem dapat mengklasifikasikan dengan algoritma naive Bayes dengan akurasi rata-rata 59%, presisi rata-rata 62%, recall rata-rata 55%, dan skor f1-rata 54%. Sebaliknya, sistem yang menggunakan algoritma regresi logistik menghasilkan hasil analisis sentimen dengan rata-rata akurasi rata-rata 62%, presisi rata-rata 63%, dan recall rata-rata 60%. Kata kunci: Kampus Merdeka, Naive Bayes, Regresi Logistik.

Actions (login required)

View Item