CHAT BASED SERVQUAL MEASUREMENT USING TEXT CLASSIFICATION (CASE STUDY: PAPERLUST)
| Main Authors: | Arya, Muhammad Apriandito; School of Business and Management, Institut Teknologi Bandung, Siallagan, Manahan; School of Business and Management, Institut Teknologi Bandung |
|---|---|
| Format: | Article info eJournal |
| Bahasa: | eng |
| Terbitan: |
The Indonesian Journal of Business Administration
, 2022
|
| Online Access: |
https://journal.sbm.itb.ac.id/index.php/IJBA/article/view/4455 |
Daftar Isi:
- E-commerce offers enormous market opportunities, this is evident from a large number of E-commerce and digital online buyers. However, not all E-commerce can be successful. Based on a survey, 90% of E-commerce failed in just 120 days due to poor service quality. Bansed on previous litarature, service quality is a crucial success factor of any business. Paperlust, a company engaged in the online design and printing industry, has not taken measurements and evaluations related to the quality of services provided, so the unsatisfying aspects of service are still unknown. Paperlust faces a decline in purchase levels throughout 2019-2020. This finding is in line with research that proves that service quality significantly influences consumer purchasing decisions. In this study we proposes a text classification approach to measure service quality based on customer chat data. Text classification with Multi-Layer Perceptron Artificial Neural network algorithm used to classify customer conversations based on sentiment classes (positive - for compliments, neutral, and negative - for complaints) on each SERVQUAL dimension where it is a typical dimension for measuring service quality. This study shows that 23% of chats received have positive sentiments, 4% have negative sentiments, and 73% have neutral sentiments. The classification results on the SERVQUAL dimension show that Empathy, Responsiveness, dan Assurance dimensions receive more compliments than complaints. Meanwhile, the Tangible and Reliability dimensions perlu get more complaints than compliments, with the proportion of complaints above 90%. Keywords: Service Quality, E-Commerce, Customer Chat, Text Mining, Text Classification, Sentiment, SERVQUAL