Research Article
AFine-TunedBERT-BasedTransferLearningApproachfor
TextClassification
RukhmaQasim,
1
WaqasHaiderBangyal ,
1
MohammedA.Alqarni,
2
andAbdulwahabAliAlmazroi
3
1
Dept. of Computer Science, University of Gujrat, Pakistan
2
University of Jeddah, College of Computer Science and Engineering, Department of Software Engineering, Jeddah, Saudi Arabia
3
University of Jeddah, College of Computing and Information Technology at Khulais, Department of Information Technology,
Jeddah, Saudi Arabia
Correspondence should be addressed to Waqas Haider Bangyal; waqas.haider@uog.edu.pk
Received 14 September 2021; Revised 25 November 2021; Accepted 3 December 2021; Published 7 January 2022
Academic Editor: Redha Taiar
Copyright © 2022 Rukhma Qasim et al. is is an open access article distributed under the Creative Commons Attribution
License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is
properly cited.
Text Classification problem has been thoroughly studied in information retrieval problems and data mining tasks. It is beneficial in
multiple tasks including medical diagnose health and care department, targeted marketing, entertainment industry, and group
filtering processes. A recent innovation in both data mining and natural language processing gained the attention of researchers from
all over the world to develop automated systems for text classification. NLP allows categorizing documents containing different texts.
A huge amount of data is generated on social media sites through social media users. ree datasets have been used for experimental
purposes including the COVID-19 fake news dataset, COVID-19 English tweet dataset, and extremist-non-extremist dataset which
contain news blogs, posts, and tweets related to coronavirus and hate speech. Transfer learning approaches do not experiment on
COVID-19 fake news and extremist-non-extremist datasets. erefore, the proposed work applied transfer learning classification
models on both these datasets to check the performance of transfer learning models. Models are trained and evaluated on the
accuracy, precision, recall, and F1-score. Heat maps are also generated for every model. In the end, future directions are proposed.
1.Introduction
Natural language processing is a scientific process to train a
computer to understand and process human language. NLP
gained a lot of importance in recent years because of the
researchers and processing powers of machines. Researchers
are doing their best to generate interesting facts and figures
from human language and implement those results in every
field of life from educations to hospitals, industry to
shopping malls, etc. In past, NLP problems were solved
using rule-based systems. However, due to the different
nature of text in the world, machine learning is applied to
NLPandithasgainedastronggroundusingSVMandNa¨ ıve
Bayes. Natural language processing and text mining refer to
the process of human-generated text that came from mul-
tiple social media networks using different algorithms,
programs, and techniques. It is an important field of AI.
With continued research on text mining and NLP using data
mining algorithms, machine learning, and deep learning,
data mining techniques have gained the best results in the
fields of automatic question answering machines, anaphora
resolution, automatic abstraction, bioinformatics, and web
relation network analysis [1]. Researches show that NLP,
data mining, and text classification can be very helpful in
every prospect of life. ere are also many other researchers
who have used NLP in hate speech, sentiment analysis [2],
detection of controversial Urdu speeches [3], movie reviews
[4], stock market [5], online reviews [6], and restaurant
reviews [7].
In recent decades, social media has gained huge im-
portance because of its usage for different purposes. If people
use social media often, then it is obvious they will generate a
Hindawi
Journal of Healthcare Engineering
Volume 2022, Article ID 3498123, 17 pages
https://doi.org/10.1155/2022/3498123