Sentiment Analysis for e-Payment Service Providers Using Evolutionary eXtreme Gradient Boosting

Dana A Al-Qudah,Ala' M Al-Zoubi,Pedro A Castillo-Valdivieso,Hossam Faris

doi:10.1109/access.2020.3032216

Dana A Al-Qudah, Ala' M Al-Zoubi + Show 2 more

Open Access

https://doi.org/10.1109/access.2020.3032216

Copy DOI

Abstract

Online services depend primarily on customer feedback and communications. When this kind of input is lacking, the overall approach of the service provider can shift in unintended ways. These services rely on feedback to maintain consumer satisfaction. Online social networks are a rich source of consumer data related to services and products. Well developed methods like sentiment analysis can offer insightful analyses and aid service providers in predicting outcomes based on their reviews-which, in turn, enables decision-makers to develop effective strategic plans. However, gathering this data is more challenging on Arabic online social networks, due to the complexity of the Arabic language and its dialects. In this study, we propose an approach to sentiment analysis that combines a neutrality detector model with eXtreme Gradient Boosting and a genetic algorithm to effectively predict and analyze customers' opinions of an e-Payment service through an Arabic social network. The proposed approach yields excellent results compared to other approaches. Feature analysis is also conducted on consumer reviews to identify influencing keywords.

Highlights

With the evolution of the internet and the increasing number of users that access it, the competition to create online services has grown
We propose a sentiment analysis approach for online e-services in the Arabic context — one that addresses the complexities of neutrality detection and boosts predictive power using a hybrid of XGBoost and a genetic algorithm (GA)
EXPERIMENT AND RESULTS After extracting the data from both online social networks (OSNs) for 2017 and 2019, we split each set into two types: the first, with three classes — including positive, negative, and neutral — and the second, which was the filtered data

Summary

Introduction

With the evolution of the internet and the increasing number of users that access it, the competition to create online services has grown. Web 2.0 innovation has enabled the development of these services through websites that emphasize user-generated content, participatory culture, ease of use, and interoperability. What was once just a vision is a reality [1]. The governmental sector and private companies have come to recognize the importance of entering this competition, which will eventually be one of the success factors of increased income. During the COVID-19 pandemic in Jordan, e-government services have been enhanced in various ways to include everything from purchasing services to online. The changes implemented have not been to the users’ satisfaction, and the provision of services is not on the same level as that of many advanced countries. A lack of communication between providers and clients is at least partly to blame [2]

Objectives

Methods

Results

Conclusion