Aspect-Based Sentiment Analysis in Identifying Factors Causing Technostress in Fintech Users Using Naïve Bayes Algorithm

DOI

10.2991/978-94-6463-340-5_10How to use a DOI?

Keywords

e-wallet; technostress; TF-IDF; BoW; ABSA; LDA; Naïve Bayes

Abstract

Technology has revolutionized finance through fintech, simplifying transactions and access to financial services. In Indonesia, fintech, particularly e-wallets, has experienced rapid growth. However, these technological advancements also present challenges such as technostress, which affects user behavior. Although OVO dominated the e-wallet market in 2021, user ratings declined in 2022, possibly related to news of complaints related to OVO services on the Google Play Store. This research aims to identify key aspects through data mining, using Aspect-Based Sentiment Analysis (ABSA) using Naïve Bayes with these factors, and determine the causes of technostress among OVO users. In addition, this study also evaluated text transformation methods: TF-IDF and Bag-of-Words (BoW). LDA-based topic modeling revealed 5 clusters with 4 core topics: features, access, services, and security. In general sentiment analysis, a data sharing ratio of 70:30 yielded the highest accuracy of 94.3% for TF-IDF and 95.25% for BoW compared to 75:25 and 80:20. BoW excels in terms of accuracy and prediction quality without overfitting. However, the TF-IDF model had difficulty with the prediction of positive reviews. The causes of technostress among OVO users were related to the transfer process (feature aspect), login problems (access aspect), concerns about customer service quality (service aspect), and satisfaction with security (security aspect).

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yanuar Taruna Lutfi
AU  - Muhardi Saputra
AU  - Riska Yanu Fa’rifah
PY  - 2023
DA  - 2023/12/30
TI  - Aspect-Based Sentiment Analysis in Identifying Factors Causing Technostress in Fintech Users Using Naïve Bayes Algorithm
BT  - Proceedings of the International Conference on Enterprise and Industrial Systems (ICOEINS 2023)
PB  - Atlantis Press
SP  - 107
EP  - 117
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-340-5_10
DO  - 10.2991/978-94-6463-340-5_10
ID  - Lutfi2023
ER  -