A real-time framework for opinion spam detection in Arabic social networks

In today’s interconnected digital landscape, social media platforms serve as the primary avenue for global conversations, encompassing various topics and opinions. Opinion spam entails spreading misleading content masked as authentic opinions. The propagation of opinion spam poses a significant chal...

Full description

Saved in:
Bibliographic Details
Main Authors: Cherry A. Ezzat, Abdullah M. Alkadri, Abeer Elkorany
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Egyptian Informatics Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1110866525000192
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849722038056386560
author Cherry A. Ezzat
Abdullah M. Alkadri
Abeer Elkorany
author_facet Cherry A. Ezzat
Abdullah M. Alkadri
Abeer Elkorany
author_sort Cherry A. Ezzat
collection DOAJ
description In today’s interconnected digital landscape, social media platforms serve as the primary avenue for global conversations, encompassing various topics and opinions. Opinion spam entails spreading misleading content masked as authentic opinions. The propagation of opinion spam poses a significant challenge, undermining the authenticity and trustworthiness of online interactions and disturbing the unrestricted exchange of ideas. One of the main challenges in spam detection is the rapid flow of spam content, which necessitates real-time detection mechanisms. Additionally, another important obstacle in detecting spam on Arabic social networks is the limited availability of labeled data. This paper proposes a framework for Real-Time Arabic Opinion Spam Detection (RTAOSD) that was developed to effectively detect opinion spam within Arabic social networks. This framework integrates advanced machine learning models, sentiment Analysis, and real-time processing techniques to achieve accurate and efficient detection of opinion spam. Furthermore, RTAOSD categorizes the non-spam content according to its relevance to topic of interest in to purify the content appear to social network users. Experimental evaluations conducted on real-world datasets demonstrate the effectiveness of RTAOSD in detecting opinion spam which leads to provide users with filtered content that match with their interest and overcome the problem of information overloading. The proposed framework achieved macro-F1 scores for spam detection ranging from 91% to 99% on different Arabic datasets surpassing previous work. While for topic relevance classification, RTAOSD achieved a macro-F1 of 86% for binary relevance and 78% for categorical relevance outperforming previous approaches used. The outcomes of this research is a real-time Arabic spam detector that accurately detects spam content and classifies non-spam text according to its relevance to topic . In addition to providing a visualization module for analyzing and reporting the characteristics of the filtered text.
format Article
id doaj-art-d7a3106b63df4a4e85a2d208f5f8b095
institution DOAJ
issn 1110-8665
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series Egyptian Informatics Journal
spelling doaj-art-d7a3106b63df4a4e85a2d208f5f8b0952025-08-20T03:11:29ZengElsevierEgyptian Informatics Journal1110-86652025-03-012910062610.1016/j.eij.2025.100626A real-time framework for opinion spam detection in Arabic social networksCherry A. Ezzat0Abdullah M. Alkadri1Abeer Elkorany2Faculty of Computers and Artificial Intelligence, Cairo University, 12613, Giza, Egypt; Corresponding author.Faculty of Computers and Artificial Intelligence, Cairo University, 12613, Giza, Egypt; Faculty of Computers and Information Technology, Hadramout University, Hadramout, YemenFaculty of Computers and Artificial Intelligence, Cairo University, 12613, Giza, EgyptIn today’s interconnected digital landscape, social media platforms serve as the primary avenue for global conversations, encompassing various topics and opinions. Opinion spam entails spreading misleading content masked as authentic opinions. The propagation of opinion spam poses a significant challenge, undermining the authenticity and trustworthiness of online interactions and disturbing the unrestricted exchange of ideas. One of the main challenges in spam detection is the rapid flow of spam content, which necessitates real-time detection mechanisms. Additionally, another important obstacle in detecting spam on Arabic social networks is the limited availability of labeled data. This paper proposes a framework for Real-Time Arabic Opinion Spam Detection (RTAOSD) that was developed to effectively detect opinion spam within Arabic social networks. This framework integrates advanced machine learning models, sentiment Analysis, and real-time processing techniques to achieve accurate and efficient detection of opinion spam. Furthermore, RTAOSD categorizes the non-spam content according to its relevance to topic of interest in to purify the content appear to social network users. Experimental evaluations conducted on real-world datasets demonstrate the effectiveness of RTAOSD in detecting opinion spam which leads to provide users with filtered content that match with their interest and overcome the problem of information overloading. The proposed framework achieved macro-F1 scores for spam detection ranging from 91% to 99% on different Arabic datasets surpassing previous work. While for topic relevance classification, RTAOSD achieved a macro-F1 of 86% for binary relevance and 78% for categorical relevance outperforming previous approaches used. The outcomes of this research is a real-time Arabic spam detector that accurately detects spam content and classifies non-spam text according to its relevance to topic . In addition to providing a visualization module for analyzing and reporting the characteristics of the filtered text.http://www.sciencedirect.com/science/article/pii/S1110866525000192Spam detectionSentiment analysisOnline Arabic social networksArabic relevance classificationData augmentationMachine learning
spellingShingle Cherry A. Ezzat
Abdullah M. Alkadri
Abeer Elkorany
A real-time framework for opinion spam detection in Arabic social networks
Egyptian Informatics Journal
Spam detection
Sentiment analysis
Online Arabic social networks
Arabic relevance classification
Data augmentation
Machine learning
title A real-time framework for opinion spam detection in Arabic social networks
title_full A real-time framework for opinion spam detection in Arabic social networks
title_fullStr A real-time framework for opinion spam detection in Arabic social networks
title_full_unstemmed A real-time framework for opinion spam detection in Arabic social networks
title_short A real-time framework for opinion spam detection in Arabic social networks
title_sort real time framework for opinion spam detection in arabic social networks
topic Spam detection
Sentiment analysis
Online Arabic social networks
Arabic relevance classification
Data augmentation
Machine learning
url http://www.sciencedirect.com/science/article/pii/S1110866525000192
work_keys_str_mv AT cherryaezzat arealtimeframeworkforopinionspamdetectioninarabicsocialnetworks
AT abdullahmalkadri arealtimeframeworkforopinionspamdetectioninarabicsocialnetworks
AT abeerelkorany arealtimeframeworkforopinionspamdetectioninarabicsocialnetworks
AT cherryaezzat realtimeframeworkforopinionspamdetectioninarabicsocialnetworks
AT abdullahmalkadri realtimeframeworkforopinionspamdetectioninarabicsocialnetworks
AT abeerelkorany realtimeframeworkforopinionspamdetectioninarabicsocialnetworks