Vol.:(0123456789) 1 3
Mobile Networks and Applications
https://doi.org/10.1007/s11036-023-02246-z
RESEARCH
Users Sentiment Analysis Using Artifcial Intelligence‑Based FinTech
Data Fusion in Financial Organizations
Sulaiman Khan
1
· Habib Ullah Khan
1
· Shah Nazir
2
· Bayan Albahooth
3
· Mohammad Arif
4
Accepted: 4 September 2023
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023
Abstract
Innovative applications surprised the research communities in the 21st by presenting in diverse domains. Financial technology
(FinTech) is an example of these innovative applications. Financial technology applications have renovated traditional banking
systems into improved smart business models. Financial technology applications enable the customers with minimum risk or
other possible attacks and can make transactions through credit cards and mobile applications from anywhere and anytime.
However still the customer doesn’t fully trusted and preferred the uncertain behavior about FinTech-driven applications. To
precisely solve this uncertain behavior of customer sentiments, this paper identifes and encourage them towards the use of
FinTech-assisted applications. This paper proposed a pipelined model to evaluate user sentiments for their uncertain behaviors
towards these FinTech-assisted applications. The proposed model consists of a convolutional neural network (CNN) and
support vector machine (SVM), where the CNN is used for classifying the sentiments of diferent behaviors while SVM is
used for statistical information to measure to what extent the users refect negative behavior. The simulation results are based
on the sentiments of users against the OVO application and Mint application on Google Play Store. An overall accuracy rate
of 91.7% is recorded for the OVO application. This high accuracy rate refects the satisfaction of the users with the OVO
application and Mint application. Furthermore, this automatic analysis of negative reviews can be used as evidence for future
contributions in the revised versions of these applications to secure a safer and more competitive position in the market.
Keywords Financial technology applications · User sentiment analysis · Data fusion · Pipelined model · Deep learning
1 Introduction
In this modern technological age, the relentless revolution in
diferent fnancial and non-fnancial organizations has given
birth to many state-of-the-art applications, including crowd-
funding platforms, mobile payments, FinTech, RegTech, and
many others. Furthermore, these applications, especially
FinTech, represent disruptive technologies in various fnan-
cial and banking sectors. Nowadays, FinTech is a buzzword
that appears on the top page of newspapers, press, and other
social media applications. According to Citi Group in 2016,
the total investment in FinTech-driven applications increased
from $1.8 billion to $19 billion during the period ranging
from 2010 to [1], but from 2015 to 2019, it abruptly raised
to $248 billion [2]. Globally, the number of active FinTech
frms was about 20,000 at the end of 2020. Venture capital-
ists are key players who invest in the FinTech-driven applica-
tions market [3]. The main objective of FinTech-regulated
fnancial companies is to assist their customers at their door-
step without their physical presence at the organizations [4].
* Mohammad Arif
mohammadarif911@gachon.ac.kr
Sulaiman Khan
engr.sulaiman88@gmail.com
Habib Ullah Khan
habib.khan@qu.edu.qa
Shah Nazir
shahnazir@uoswabi.edu.pk
Bayan Albahooth
ba.albahooth@qu.edu.sa
1
Department of Accounting and Information Systems,
College of Business and Economics, Qatar University, Doha,
Qatar
2
Department of Computer Science, University of Swabi,
Swabi, Pakistan
3
Department of Economics and Finance, College of Business
and Economics, Qassim University, 52571 Buraydah,
Saudi Arabia
4
Department of Computer Engineering, Gachon University,
Seongnam-si 13120, South Korea