Analisis Ulasan Pelanggan Pada Sewa Kamera di Jemberkamera Menggunakan Algoritme Naive Bayes

Habibi, Moh Bachtiar Rifki (2026) Analisis Ulasan Pelanggan Pada Sewa Kamera di Jemberkamera Menggunakan Algoritme Naive Bayes. Diploma thesis, Politeknik Negeri Jember.

	Text (Abstract) Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (243kB)
	Text (Bab 1 Pendahuluan) Bab 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (389kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf - Submitted Version Restricted to Registered users only Download (210kB) | Request a copy
	Text (Laporan Lengkap) Laporan Lengkap.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (2MB)

Abstract

emberkamera utilizes Google Maps for customer interaction, but the large volume of informal and subjective reviews complicates manual service evaluations. This study develops a web-based system to classify review sentiments into positive, neutral, and negative categories using the Multinomial Naive Bayes algorithm. To handle the extreme data imbalance in the negative class, the Synthetic Minority Over-sampling Technique (SMOTE) is applied. A dataset of 2,492 reviews was extracted via the Apify platform, then processed through text preprocessing and Term Frequency-Inverse Document Frequency (TF-IDF) weighting. Testing results show that a 50:50 data split scenario combined with SMOTE achieved the most optimal performance, yielding the highest accuracy of 70.47%. The integration of SMOTE effectively improved the model's sensitivity in recognizing minority negative sentiments and reduced majority class bias. The application's visual dashboard helps Jemberkamera management to evaluate business services and objectively monitor customer satisfaction in order to improve quality based on digital opinion data.

Actions (login required)

View Item