Sentic-Emotion Classifier on eWallet Reviews

Sentic-Emotion Classifier on eWallet Reviews

Tong Ming Lim, Yuen Kei Khor, Chi Wee Tan
Copyright: © 2023 |Pages: 29
DOI: 10.4018/IJBAN.329928
Article PDF Download
Open access articles are freely available for download

Abstract

Emotion classification using hybrid framework using lexicon and machine learning algorithms have been proven to be more accurate. This research analyses emotions from reviews of a popular eWallet mobile application in Malaysia. The proposed Sentic-Emotion Classifier is evaluated on its performance as it analyses the code-switched reviews crawled that contain formal and informal or out-of-vocab words. The code-switched reviews are mainly made up of words and expressions in English and Malay language models. This research designs, implements, and investigates several novel techniques that have been shown to have reliable and consistent predictive outcomes, and these outcomes are validated with manually annotated reviews so that the proposed classifier can be evaluated objectively. The novel contributions of the Sentic-Emotion Classifier consist of 2-tier sentiment classification, extended emolex framework, and multi-layer discrete emotion hierarchical classes which is hypothesized to be able to yield better accuracy for emotion and intensity prediction for the proposed framework.
Article Preview
Top

Introduction

In recent years, the increase of cashless transactions in many countries such as China, Singapore, and Malaysia, are largely due to the rapid development of financial technology and higher consumer confidence on secured money-over-web activities. The adoption rate of fintech products such as eWallet by 21st century young consumers from cash-based to cashless has shifted rather quickly. These young consumers have always been regarded as tech-savvy users of the smartphone era. In Malaysia, 42 eWallet service providers have received official licenses from BNM (Bank Negara Malaysia) and six (6) of them are more popular and widely adopted. They are AEON Wallet, Boost, BigPay, GrabPay, WeChat pay, and Touch‘n Go eWallet (Aji et al., 2020; Karim et al., 2020; Ray, 2017; Upadhayaya, 2012).

The number of digital payment providers increased by leaps and bounds during the COVID-19 pandemic period, as people tried to reduce physical contact with other people. Hence, understanding customers’ needs are extremely important in order to drive business growth, provide better customer services, as well as deeply understanding the strengths and weaknesses of their products. The tech savvy generation, young and old, prefer to express their feelings and opinions on the software or services that they experience on the social media sites. In order to understand the perceptions of digital payment users, sentiment and emotion analysis can be analysed based on users’ reviews, which can be collected from online app stores, such as Playstore or Appstore, social media sites, such as Facebook and Instagram, or product review platforms.

Medhat et al. (2014, p. 1094) defined sentiment analysis as a study of people’s opinions, emotions, and attitudes toward an entity such as individuals, events, and topics. It evaluates the perception of humans towards entities and enables business organizations to employ effective decision-making. Sentiment analysis classifies the sentiment of a text document into three categories, which are: positive, negative, and neutral. For example, “The customer service is so poor! No one replies to me!” is a negative sentiment, and it is important to understand the customers’ reaction towards the products and services they consumed. As a business grows, customer insight is vital, as it provides valuable information to the organization to improve the quality of services and products. In addition, emotion analysis is another dimension of affective analysis that can be conducted to further understand how customers feel based on the reviews collected. Emotion analysis is similar to sentiment analysis, but it is more specific because it classifies the reviews into one or more emotion categories, such as angry and/or happy. There are two emotion models, which are widely used in emotion analysis. Ekman’s six basic emotions (Mohammad & Turney, 2013) contain anger, disgust, fear, happiness, sadness, and surprise emotions. On the other hand, Plutchik’s wheel of emotion (Plutchik, 2003) defines a set of eight emotions, six of the emotion categories were adopted from Ekman, with two additional emotions added: trust and anticipation.

Complete Article List

Search this Journal:
Reset
Volume 11: 1 Issue (2024)
Volume 10: 1 Issue (2023)
Volume 9: 6 Issues (2022): 4 Released, 2 Forthcoming
Volume 8: 4 Issues (2021)
Volume 7: 4 Issues (2020)
Volume 6: 4 Issues (2019)
Volume 5: 4 Issues (2018)
Volume 4: 4 Issues (2017)
Volume 3: 4 Issues (2016)
Volume 2: 4 Issues (2015)
Volume 1: 4 Issues (2014)
View Complete Journal Contents Listing