Sentiment Analysis Of Reviews Tanihub Application Using Naive Bayes Classifier Method

Wifaq, Miftahul Hafidhah (2021) Sentiment Analysis Of Reviews Tanihub Application Using Naive Bayes Classifier Method. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[img] Text
10611710000077-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 October 2023.

Download (1MB) | Request a copy

Abstract

TaniHub merupakan aplikasi e-commerce pada bidang sektor pertanian yang menyediakan berbagai produk hasil pertanian. Pada situs Google Play Store TaniHub mempunyai rating yang bagus sebesar 4,6 namun pada ulasannya masih cukup banyak pengguna yang menyatakan komplain mengenai pelayanan dan produk yang mereka tawarkan didukung oleh penelitian sebelumnya yang menyatakan 400 review yang masuk ke dalam database perusahaan, 70% pelanggan memberikan komplain bahwa pelayanan yang diberikan oleh TaniHub tidak memuaskan. Pada tahun 2020 TaniHub akan merealisasikan ekspansi ke luar Pulau Jawa dan Bali, maka dari itu pada penelitian ini akan dilakukan analisis sentimen pada ulasan aplikasi Tanihub menggunakan Naïve Bayes Classifier. Hasil penelitian ini adalah ulasan bersentimen positif adalah sebesar 77%, sedangkan ulasan yang bersentimen negatif adalah sebesar 23% yang artinya bahwa pada ulasan positif lebih banyak daripada ulasan negatif, namun 23% masih menunjukkan angka yang cukup tinggi sehingga Tanihub perlu melakukan perbaikan. Pada ketepatan klasifikasi data testing, hasil AUC sebesar 84,88% artinya adalah Good Classification. Hasil G-mean adalah sebesar 0,8486 yang artinya metode NBC dapat memisahkan kelas positif dan negatif sebesar 74,86%. ================================================================================================ TaniHub is an e-commerce application in the agricultural sector that provides a variety of agricultural products. On thesite Google Play Store, TaniHub has rating a goodof 4.6 but in the reviews there are still quite a lot of users who state complaints about the services and products they offer supported by previous research which states 400 reviews entered into thedatabase company, 70% of customers gave complained that the services provided by TaniHub were not satisfactory. In 2020 TaniHub has plans to realize expansion outside Java and Bali, therefore in this study a sentiment analysis will be carried out on the Tanihub application review using the Naïve Bayes Classifier. The results of this study are positive sentiment reviews are 77%, while negative sentiment reviews are 23%, which means that there are more positive reviews than negative reviews, but 23% still shows a high enough number so Tanihub needs to make improvements. On the accuracy of data classification testing, the AUC result of 84.88% means that it is Good Classification. The G-mean result is 0.8486, which means that the NBC method can separate the positive and negative classes by 74.86%.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: sentiment analysis, naïve bayes classifier, service and taniHub, analisis sentimen, naïve bayes classifier, Pelayanan dan TaniHub
Subjects: H Social Sciences > HA Statistics
H Social Sciences > HC Economic History and Conditions > HC108 Market surveys.
Q Science
Divisions: Faculty of Vocational > 49501-Business Statistics
Depositing User: Miftahul Hafidhah Wifaq
Date Deposited: 15 Aug 2021 09:04
Last Modified: 15 Aug 2021 09:04
URI: https://repository.its.ac.id/id/eprint/86821

Actions (login required)

View Item View Item