Modelling Service Quality of Internet Service Providers during COVID-19: The Customer Perspective Based on Twitter Dataset

Abstract

Internet service providers (ISPs) conduct their business by providing Internet access features to their customers. The COVID-19 pandemic has shifted most activity being performed remotely using an Internet connection. As a result, the demand for Internet services increased by 50%. This significant rise in the appeal of Internet services needs to be overtaken by a notable increase in the service quality provided by ISPs. Service quality plays a great role for enterprises, including ISPs, in retaining consumer loyalty. Thus, modelling ISPs’ service quality is of great importance. Since a common technique to reveal service quality is a timely and costly pencil survey-based method, this work proposes a framework based on the Sentiment Analysis (SA) of the Twitter dataset to model service quality. The SA involves the majority voting of three machine learning algorithms namely Naïve Bayes, Multinomial Naïve Bayes and Bernoulli Naïve Bayes. Making use of Thaicon’s service quality metrics, this work proposes a formula to generate a rating of service quality accordingly. For the case studies, we examined two ISPs in Indonesia, i.e., By.U and MPWR. The framework successfully extracted the service quality rate of both ISPs, revealing that By.U is better in terms of service quality, as indicated by a service quality rate of 0.71. Meanwhile, MPWR outperforms By.U in terms of customer service.

Joint Distribution pada Weighted Majority Vote (WMV) untuk Peningkatan Kinerja Sentiment Analysis Tersupervisi pada Dataset Twitter

“…Metode penelitian yang digunakan meliputi beberapa tahap aktifitas machine learning yaitu grabbing, pre processing, training, testing dan evaluasi sebagaimana digambarkan dalam diagram alir pada Gambar 1. Data Twit kemudian di Pre-Process menggunakan tool NLP dari Python sastrawi yang merupakan ekstensi dari PHP Sastrawi (Rintyarna et al, 2022). Pre-process melibatkan proses-proses: (1) case folding; (2) tokenizing; (3) normalization; (4) stop word removal; dan (5) stemming.…”

“…Pre-process melibatkan proses-proses: (1) case folding; (2) tokenizing; (3) normalization; (4) stop word removal; dan (5) stemming. Sebagaimana penjelasan (Rintyarna et al, 2022), proses-proses tersebut adalah prosedur standard pada text pre processing. Fitur Bag of Word (BoW) kemudian diekstraksi dengan Python sebelum memasuki tahap Learning dan Testing pada Machine Learning.…”

“…Bagimanapun juga, optimasi paramater pada single classifier selalu menghadapi trade off berupa "error classification" sebagaimana penjelasan (Ruta and Gabrys, 2005). Pada kenyataanya sebagian besar sentiment analysis pada dataset Twitter berbahasa Indonesia lebih banyak menggunakan single classifier dibandingkan ensemble classifier (Rintyarna et al, 2022).…”

Analisis Sentimen Menggunakan Arsitektur Long Short-Term Memory (Lstm) Terhadap Fenomena Citayam Fashion Week

“…Rintyarna [5] telah melakukan analisis sentimen terhadap pandangan masyarakat Indonesia terhadap makanan organik selama pandemic COVID-19. Selama pandemic COVID-19, juga telah dilakukan analisis sentimen terhadap penyedia layanan internet [6].…”

“…Analisis sentimen dalam bahasa Indonesia sudah banyak dilakukan sebelumnya. Analisis sentimen dilakukan untuk melihat pendapat masyarakat yang disalurkan melalui media online dengan topik khusus, seperti topik bencana banjir di Jakarta, kebijakan pemerintah melakukan PSBB, pelayanan OVO, BPJS Kesehatan, makanan organik, dan pelayanan penyedia internet selama COVID-19 [1]- [6].…”