Improving Crisis Events Detection Using DistilBERT with Hunger Games Search Algorithm

This paper presents an alternative event detection model based on the integration between the DistilBERT and a new meta-heuristic technique named the Hunger Games Search (HGS). The DistilBERT aims to extract features from the text dataset, while a binary version of HGS is developed as a feature sele...

Full description

Bibliographic Details
Main Authors: Hadeer Adel, Abdelghani Dahou, Alhassan Mabrouk, Mohamed Abd Elaziz, Mohammed Kayed, Ibrahim Mahmoud El-Henawy, Samah Alshathri, Abdelmgeid Amin Ali
Format: Article
Language:English
Published: MDPI AG 2022-01-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/10/3/447
_version_ 1797486375243612160
author Hadeer Adel
Abdelghani Dahou
Alhassan Mabrouk
Mohamed Abd Elaziz
Mohammed Kayed
Ibrahim Mahmoud El-Henawy
Samah Alshathri
Abdelmgeid Amin Ali
author_facet Hadeer Adel
Abdelghani Dahou
Alhassan Mabrouk
Mohamed Abd Elaziz
Mohammed Kayed
Ibrahim Mahmoud El-Henawy
Samah Alshathri
Abdelmgeid Amin Ali
author_sort Hadeer Adel
collection DOAJ
description This paper presents an alternative event detection model based on the integration between the DistilBERT and a new meta-heuristic technique named the Hunger Games Search (HGS). The DistilBERT aims to extract features from the text dataset, while a binary version of HGS is developed as a feature selection (FS) approach, which aims to remove the irrelevant features from those extracted. To assess the developed model, a set of experiments are conducted using a set of real-world datasets. In addition, we compared the binary HGS with a set of well-known FS algorithms, as well as the state-of-the-art event detection models. The comparison results show that the proposed model is superior to other methods in terms of performance measures.
first_indexed 2024-03-09T23:32:16Z
format Article
id doaj.art-8b839f31a86348caa820ba9dede9bc91
institution Directory Open Access Journal
issn 2227-7390
language English
last_indexed 2024-03-09T23:32:16Z
publishDate 2022-01-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj.art-8b839f31a86348caa820ba9dede9bc912023-11-23T17:07:40ZengMDPI AGMathematics2227-73902022-01-0110344710.3390/math10030447Improving Crisis Events Detection Using DistilBERT with Hunger Games Search AlgorithmHadeer Adel0Abdelghani Dahou1Alhassan Mabrouk2Mohamed Abd Elaziz3Mohammed Kayed4Ibrahim Mahmoud El-Henawy5Samah Alshathri6Abdelmgeid Amin Ali7Department of Computer Science, Faculty of Computer Science, Nahda University, Beni Suef 62511, EgyptMathematics and Computer Science Department, University of Ahmed DRAIA, Adrar 01000, AlgeriaMathematics and Computer Science Department, Faculty of Science, Beni-Suef University, Beni Suef 62511, EgyptFaculty of Computer Science and Engineering, Galala University, Suez 435611, EgyptComputer Science Department, Faculty of Computers and Artificial Intelligence, Beni-Suef University, Beni Suef 62511, EgyptDepartment of Computer Science, Faculty of Computer Science, Zagazig University, Zagazig 44519, EgyptDepartment of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi ArabiaFaculty of Computer Science and Information, Minia University, Minia 61519, EgyptThis paper presents an alternative event detection model based on the integration between the DistilBERT and a new meta-heuristic technique named the Hunger Games Search (HGS). The DistilBERT aims to extract features from the text dataset, while a binary version of HGS is developed as a feature selection (FS) approach, which aims to remove the irrelevant features from those extracted. To assess the developed model, a set of experiments are conducted using a set of real-world datasets. In addition, we compared the binary HGS with a set of well-known FS algorithms, as well as the state-of-the-art event detection models. The comparison results show that the proposed model is superior to other methods in terms of performance measures.https://www.mdpi.com/2227-7390/10/3/447event detectiondeep learninghunger game searchDistilBERTfeature selection optimization algorithms
spellingShingle Hadeer Adel
Abdelghani Dahou
Alhassan Mabrouk
Mohamed Abd Elaziz
Mohammed Kayed
Ibrahim Mahmoud El-Henawy
Samah Alshathri
Abdelmgeid Amin Ali
Improving Crisis Events Detection Using DistilBERT with Hunger Games Search Algorithm
Mathematics
event detection
deep learning
hunger game search
DistilBERT
feature selection optimization algorithms
title Improving Crisis Events Detection Using DistilBERT with Hunger Games Search Algorithm
title_full Improving Crisis Events Detection Using DistilBERT with Hunger Games Search Algorithm
title_fullStr Improving Crisis Events Detection Using DistilBERT with Hunger Games Search Algorithm
title_full_unstemmed Improving Crisis Events Detection Using DistilBERT with Hunger Games Search Algorithm
title_short Improving Crisis Events Detection Using DistilBERT with Hunger Games Search Algorithm
title_sort improving crisis events detection using distilbert with hunger games search algorithm
topic event detection
deep learning
hunger game search
DistilBERT
feature selection optimization algorithms
url https://www.mdpi.com/2227-7390/10/3/447
work_keys_str_mv AT hadeeradel improvingcrisiseventsdetectionusingdistilbertwithhungergamessearchalgorithm
AT abdelghanidahou improvingcrisiseventsdetectionusingdistilbertwithhungergamessearchalgorithm
AT alhassanmabrouk improvingcrisiseventsdetectionusingdistilbertwithhungergamessearchalgorithm
AT mohamedabdelaziz improvingcrisiseventsdetectionusingdistilbertwithhungergamessearchalgorithm
AT mohammedkayed improvingcrisiseventsdetectionusingdistilbertwithhungergamessearchalgorithm
AT ibrahimmahmoudelhenawy improvingcrisiseventsdetectionusingdistilbertwithhungergamessearchalgorithm
AT samahalshathri improvingcrisiseventsdetectionusingdistilbertwithhungergamessearchalgorithm
AT abdelmgeidaminali improvingcrisiseventsdetectionusingdistilbertwithhungergamessearchalgorithm