Abstract
We may see competition among mobile providers to acquire new customers through campaign and advertisement war, especially on social media. The problem arises on how to measure the brand reputation of these providers based on people response on their services quality. This paper addresses this issue by measuring brand reputation based on customer satisfaction through customer's sentiment analysis from Twitter data. Sample model is built and extracted from 10.000 raw Twitter messages data from January to March 2015 of top three mobile providers in Indonesia. We compared several features extractions, algorithms, and the classification schemes. After data cleaning and data balancing, the sentiments are classified and compared using three different algorithms: Naïve Bayes, Support Vector Machine, and Decision Tree classifier method. We measure customer satisfaction on five products: 3G, 4G, Short Messaging, Voice and Internet services. This paper also discusses some correlated business insights in a telecommunication services industry. Based on the overall comparison of these five products, the NBR scores for PT XL Axiata Tbk, PT Telkomsel Tbk, and PT Indosat Tbk are 32.3%, 19.0%, and 10.9% respectively.
Original language | English |
---|---|
Pages (from-to) | 519-526 |
Number of pages | 8 |
Journal | Procedia Computer Science |
Volume | 72 |
DOIs | |
Publication status | Published - 2015 |
Event | 3rd Information Systems International Conference, 2015 - Shenzhen, China Duration: 16 Apr 2015 → 18 Apr 2015 |
Keywords
- Indonesia
- Naïve Bayes
- brand reputation
- decision tree
- sentiment analysis
- support vector machine