Analisis opini pelanggan pada pelayanan PLN 123 di Twitter menggunakan Naive Bayes Classifier

Irfandi, Muhammad Arya (2022) Analisis opini pelanggan pada pelayanan PLN 123 di Twitter menggunakan Naive Bayes Classifier. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 10611810000032-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (1MB)

Abstract

Seiring berkembangnya teknologi, PLN berinovasi dengan mengubah layanan yang awalnya berupa layanan konvensional yang mengharuskan pelanggan datang ke kantor cabang PLN terdekat. Saat ini, PLN memiliki layanan pengaduan terkait kelistrikan melalui media sosial, salah satunya yaitu Twitter. Komentar pelanggan terhadap pelayanan yang diberikan PLN di Twitter sangat membantu pihak PLN untuk mengetahui kebutuhan serta keinginan pelanggan, termasuk berbagai kekurangan dalam pelayanan. Komentar tersebut dapat dianalisis menggunakan analisis sentimen. Pada penelitian ini akan dilakukan analisis sentimen dengan data yang diambil melalui _crawling_ Twitter menggunakan kata kunci "PLN 123" untuk mendapatkan ulasan masyarakat mengenai kinerja pelayanan PLN 123\. Penelitian ini bertujuan untuk mengetahui pendapat pelanggan terhadap pelayanan PLN 123 di Twitter. Penelitian ini dilakukan dengan metode _Naïve Bayes Classifier_ sehingga dapat memberikan informasi apabila terjadi permasalahan kelistrikan dari segi pelayanan, sehingga pihak PLN 123 dapat merespons keluhan pelanggan dengan tepat agar permasalahan yang dialami dapat teratasi dengan baik. Hasil klasifikasi menunjukkan bahwa mayoritas pelanggan memberikan opini yang bersifat negatif, yaitu sebesar 59,90%. Hasil ketepatan klasifikasi dari data opini pelanggan terhadap pelayanan PLN 123 di Twitter menggunakan _Naïve Bayes Classifier_ diperoleh berdasarkan nilai _accuracy_. Hasil ketepatan klasifikasi menunjukkan bahwa nilai _accuracy_ yang diperoleh sebesar 61,7%.
================================================================================================================================
As technology develops, PLN continues to innovate by transforming its services, which were originally conventional and required customers to visit the nearest PLN branch office. Currently, PLN provides electricity-related complaint services through social media, one of which is Twitter. Customer comments regarding the services provided by PLN on Twitter are very helpful for PLN in identifying customers’ needs and expectations, as well as the shortcomings of its services. These comments can be analyzed using sentiment analysis. In this study, sentiment analysis was conducted using data collected through Twitter crawling with the keyword “PLN 123” to obtain public reviews regarding the performance of PLN 123 services. This study aims to determine customer opinions regarding PLN 123 services on Twitter. The research was conducted using the Naïve Bayes Classifier method to provide information regarding customer opinions and service-related electricity problems, enabling PLN 123 to respond to customer complaints appropriately so that the problems experienced can be resolved effectively. The classification results show that the majority of customers expressed negative opinions, accounting for 59.90% of the data. The classification accuracy of customer opinion data regarding PLN 123 services on Twitter using the Naïve Bayes Classifier was evaluated based on the accuracy value. The results showed that the classification accuracy was 61.7%.

Item Type:	Thesis (Other)
Additional Information:	519.53 Irf a-1
Uncontrolled Keywords:	Analisis Sentimen, Naïve Bayes Classifier, PLN 123, Twitter, Sentiment Analysis, Naïve Bayes Classifier, PLN 123, Twitter
Subjects:	Q Science > QA Mathematics > QA278.55 Cluster analysis
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	magang .
Date Deposited:	05 Oct 2026 07:29
Last Modified:	05 Oct 2026 07:29
URI:	http://repository.its.ac.id/id/eprint/145270

Actions (login required)

View Item