Arabic Tweets Spam Detection Based on Various Supervised Machine Learning and Deep Learning Classifiers
Hassan, S., Elrefaei, L., Andraws, M. (2023). Arabic Tweets Spam Detection Based on Various Supervised Machine Learning and Deep Learning Classifiers. EKB Journal Management System, 2(2), 1099-1119. doi: 10.21608/msaeng.2023.291931
Shimaa I. Hassan; Lamiaa Elrefaei; Mina Shoukrey Andraws. "Arabic Tweets Spam Detection Based on Various Supervised Machine Learning and Deep Learning Classifiers". EKB Journal Management System, 2, 2, 2023, 1099-1119. doi: 10.21608/msaeng.2023.291931
Hassan, S., Elrefaei, L., Andraws, M. (2023). 'Arabic Tweets Spam Detection Based on Various Supervised Machine Learning and Deep Learning Classifiers', EKB Journal Management System, 2(2), pp. 1099-1119. doi: 10.21608/msaeng.2023.291931
Hassan, S., Elrefaei, L., Andraws, M. Arabic Tweets Spam Detection Based on Various Supervised Machine Learning and Deep Learning Classifiers. EKB Journal Management System, 2023; 2(2): 1099-1119. doi: 10.21608/msaeng.2023.291931

Arabic Tweets Spam Detection Based on Various Supervised Machine Learning and Deep Learning Classifiers

MSA Engineering Journal
Volume 2, Issue 2 - Serial Number 6, March 2023, Page 1099-1119  XML PDF (634.03 K)
Document Type: Original Article
DOI: 10.21608/msaeng.2023.291931
View on SCiNiTO View on SCiNiTO
Authors
Shimaa I. Hassan1; Lamiaa Elrefaei1; Mina Shoukrey Andraws2
1Electrical Engineering Department, Faculty of Engineering at Shoubra, Benha University, Cairo, Egypt
2Engineering Department, Nuclear Research Centre, Egyptian Atomic Energy Authority, Cairo, Egypt
Abstract
 In this paper, different machine learning algorithms, ensemble algorithms,
and deep learning algorithms are applied to Arabic tweets to detect whether it
human-generated or not. The tweets are used twice as preprocessed and nonpreprocessed to measure the effectiveness of Arabic preprocessing in the
classification process. The data is also tokenized with various methods like unigram,
trigram, and Term Frequency–Inverse Document Frequency. The experiments
show that the support vector machine with the non-preprocessed tweets and
unigram tokenization has the best performance of 83.11% and a precision of 0.9516
while it predicts the spam or not in a relatively small time.
Keywords
Machine Learning; Ensemble; Deep Learning; Arabic Tweets; Twitter spam
Statistics
Article View: 190
PDF Download: 637