A semi-supervised approach in detecting sentiment and emotion based on digital payment reviews
- PDF / 1,436,403 Bytes
- 16 Pages / 439.37 x 666.142 pts Page_size
- 1 Downloads / 153 Views
A semi‑supervised approach in detecting sentiment and emotion based on digital payment reviews Vimala Balakrishnan1 · Pik Yin Lok2 · Hajar Abdul Rahim3
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract This paper investigates the sentiment and emotion of digital payment application consumers using a hybrid approach consisting of both supervised and unsupervised machine learning techniques. Support vector machine, random forest and Naïve Bayes were modeled for sentiment and emotion analyses, whereas latent Dirichlet allocation was administered to identify top emerging topics based on English textual reviews from three digital payment applications. Random forest produced the best results for sentiment (F1 score = 73.8%; Cohen’s Kappa = 52.2%) and emotion (F1 score = 58.8%; Cohen’s Kappa = 44.7%) analyses based on a tenfold cross-validation. Latent Dirichlet allocation revealed best clusters at k = 5 and items = 25, with the top topics being App Service, Transaction, Reload Features, Connectivity and Reward. Findings are presented and discussed in general and also based on each application. Keywords Hybrid approach · Sentiment analysis · Emotion analysis · Digital payment
1 Introduction One of the revolutions of interests is the financial technologies or fintech revolution, particularly the aspiration to move toward a cashless society (i.e., a society that performs purchasing transactions using digital cards or electronic gadgets, a.k.a. digital payment) that would help improve the quality of life, improve productivity for the merchants and service providers. Unlike the Western countries,
* Vimala Balakrishnan [email protected] 1
Faculty of Computer Science and Information Technology, Universiti Malaya, 50603 Kuala Lumpur, Malaysia
2
The Nielsen Company, Kuala Lumpur, Malaysia
3
School of Humanities, Universiti Sains Malaysia, Penang, Malaysia
13
Vol.:(0123456789)
V. Balakrishnan et al.
the adoption of digital payment in Asian countries is slow in progression, with India and China being the two leading nations. For example, the e-wallet (i.e., a way of carrying digital card information on a mobile device through digital applications) industry was observed to grow in the aftermath of the demonetization policy announcement in India [1]. In China, major cities such as Beijing and Shanghai have around 45% of GDP contributed by digital economy [2], with their biggest e-commerce retailer Alibaba serving as a catalyst in the nation’s transition proven by a total of 31 billion USD spent on 2019 Singles’ Day itself [3]. With the emergence of natural language processing and artificial intelligence, the process of determining users’ perceptions from their online communications has become easy, resulting in research in the fields of sentiment and emotion analyses. Sentiment analysis is the computational task of automatically determining what feelings a writer expresses in text, usually classified as positive, neutral or negative. It allows businesses to understand the
Data Loading...
