Main Page
Deanship
The Dean
Dean's Word
Curriculum Vitae
Contact the Dean
Vision and Mission
Organizational Structure
Vice- Deanship
Vice- Dean
KAU Graduate Studies
Research Services & Courses
Research Services Unit
Important Research for Society
Deanship's Services
FAQs
Research
Staff Directory
Files
Favorite Websites
Deanship Access Map
Graduate Studies Awards
Deanship's Staff
Staff Directory
Files
Researches
Contact us
عربي
English
About
Admission
Academic
Research and Innovations
University Life
E-Services
Search
Deanship of Graduate Studies
Document Details
Document Type
:
Thesis
Document Title
:
: Structures of Retweets Manipulation on Twitter: Case Study of Trending Topics in Saudi Arabia
أنماط التلاعب في إعادة التغريد على تويتر: دراسة حالة للمواضيع الشائعة في المملكة العربية السعودية
Subject
:
Faculty of Computing and Information Technology
Document Language
:
Arabic
Abstract
:
Online social media has become an exploited environment due to manipulation by users. Twitter network functions are especially characterized by being open, which allows anyone can follow anyone without the need to approve social connection on public Twitter. Retweeting on Twitter is a feature often exploited by groups of malicious retweeters. It has become obvious that a significant number of users take advantage by manipulating the retweeting feature in order to market their promotional content in local trending topics. This study highlights those groups to study their behavior and try to discover patterns that can reveal retweet manipulation. By applying graph theory, retweeting activity was represented as a network graph. Multiple algorithms of communities’ detection were implemented to extract these groups with high accuracy from the network. In addition, some features were extracted to identify these groups. The experiment was performed on real-life events that were reflected on Twitter. This study’s data includes retweets of 238,231 users over 46,123 tweets. 2,263 malicious retweeters were extracted from this dataset to form 254 groups. Analysis of the graph structure of these groups showed some distinctive retweeting behavior which helped in identifying those groups. A supervised model was trained to detect those groups which achieved 94% accuracy. This approach was applied on historical dataset and may be extended to cover realtime datasets to allow quicker detection of malicious retweeter groups.
Supervisor
:
Dr. Rayed Alghamdi
Thesis Type
:
Master Thesis
Publishing Year
:
1442 AH
2021 AD
Co-Supervisor
:
Dr. Nabeel Albishry
Added Date
:
Wednesday, August 18, 2021
Researchers
Researcher Name (Arabic)
Researcher Name (English)
Researcher Type
Dr Grade
Email
مروة أحمد جواس
Jawas, Marwah Ahmed
Researcher
Master
Files
File Name
Type
Description
47120.pdf
pdf
Back To Researches Page