Akun Instagram Kementrian BUMN memiliki postingan yang dapat dikomentari dengan bebas oleh Masyarakat,Namun, kolom komentar di Instagram Kementrian BUMN sering kali menjadi tempat bagi masyarakat untuk menyampaikan komentar negatif. Khususnya pada Postingan Mengenai “Rekrutmen Bersama BUMN” (RBB). Dengan Permasalahan tersebut, penelitian ini dibuat Melakukan analisis sentimen terhadap Opini Masyarakat mengenai Program Rekrutmen Bersama BUMN (RBB) Kementrian BUMN dengan Menggunakan data yang diambil dari Instagram. Dalam penelitian ini, data dibagi dengan indeks perbandingan 80:10:10. Penelitian ini menggunakan Metode Naive Baiyes, dengan jumlah data 9448. Data tersebut terdiri dari 3.609 data positif, 6.609 data negatif, dan 291 data netral. Pembagian data dalam penelitian ini, dibagi menjadi tiga bagian yaitu, data pelatihan 80%, data pengujian 10%, dan data validasi 10%. Hasil yang didapatkan untuk positif sebesar 37,52%, kelas netral sebesar 26,47%, dan kelas negatif sebesar 36,01%. Setelah itu dilakukan proses pembobotan kata dengan total ukuran kosa kata sebanyak 7070, dan akurasi analisis sentimen komentar Instagram Kementerian BUMN menggunakan Naïve Bayes sebesar 72%.

The Ministry of BUMN's Instagram account has posts that can be commented on freely by the public. However, the comments column on the Ministry of BUMN's Instagram is often a place for the public to convey negative comments. Especially in posts regarding "Recruitment with BUMN" (RBB). With these problems, this research was carried out to carry out sentiment analysis of public opinion regarding the BUMN Joint Recruitment Program (RBB) of the Ministry of BUMN using data taken from Instagram. In this study, the data was divided by a comparison index of 80:10:10. This research uses the Naive Baiyes Method, with a total of 9448 data. The data consists of 3,609 positive data, 6,609 negative data and 291 neutral data. The data division in this research is divided into three parts, namely, 80% training data, 10% testing data, and 10% validation data. The results obtained for the positive class were 37.52%, the neutral class was 26.47%, and the negative class was 36.01%. After that, a word weighting process was carried out with a total vocabulary size of 7070, and the accuracy of the sentiment analysis of the Ministry of BUMN's Instagram comments using Naïve Bayes was 72%.