IRMA-International.org: Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Social Media Privacy and Security: Stacking and Boosting for Misinformation Detection

Social Media Privacy and Security: Stacking and Boosting for Misinformation Detection
View Sample PDF
Author(s): Sanaa Ashiq (National University of Modern Languages, Rawalpindi, Pakistan), Sehrish Ferdous (National University of Modern Languages, Rawalpindi, Pakistan), Muhammad Adnan (National University of Computer and Emerging Sciences (FAST), Islamabad, Pakistan), Wajahat Sultan (National University of Sciences and Technology, Pakistan), Hasan Tahir (National University of Sciences and Technology, Pakistan), Bilal Ahmed (National University of Sciences and Technology, Pakistan), Qamar Yasmeen (Niazi Medical and Dental College, Sargodha, Pakistan)and Madeeha Saqib (Imam Abdulrahman bin Faisal University, Dammam, Saudi Arabia)
Copyright: 2026
Pages: 36
Source title: User-Centric Cybersecurity Implications for Sustainable Digital Transformation
Source Author(s)/Editor(s): Saqib Saeed (Imam Abdulrahman Bin Faisal University, Saudi Arabia)and Shahzaib Tahir (National University of Sciences and Technology, Pakistan)
DOI: 10.4018/979-8-3373-3171-3.ch006

Purchase

View Social Media Privacy and Security: Stacking and Boosting for Misinformation Detection on the publisher's website for pricing and purchasing information.

Abstract

Despite being a modern means of communication, social media is one of the biggest risks to privacy and security because of the misinformation that it perpetuates. This chapter proposes a new ensemble model that uses stacking and boosting techniques for misinformation detection with identity protection. The developed framework combines machine learning and deep learning algorithms to improve detection accuracy while reducing the threat of fake news, identity fraud, and cyber terrorism. The chapter covers the implementation of natural language processing for feature extraction and model evaluation with real life datasets containing misinformation. It also addresses the policy and ethical consequences of automating misinformation detection from the perspective of safety, privacy, and freedom of speech. The resulting system encourages safety in a digital space by increasing privacy and surveillance of information among individuals and organizations, thus fostering trust in online content.

Related Content

Muhammad Naeem Shahid, Mahreen Bashir, Muhammad Umar Islam, Zahid Mahmood. © 2027. 36 pages.
KM Ashifa, B. UmaDevi, L. Anitha, Palanivel Rathinasabapathi Velmurugan, R. Vettriselvan. © 2027. 26 pages.
Mirudhula K., Karthikeyan S.. © 2027. 36 pages.
Abid Ali, Muhammad Zahid, Muhammad Naeem Shahid, Sumaira Aslam. © 2027. 24 pages.
Priyakrushna Mohanty, Rashi Modi, Aaleyah Behera. © 2027. 40 pages.
R. N. Ravikumar, S. Aarthi. © 2027. 32 pages.
V. Lava Kumar, Santhapalli Gautami, E. Gnanaprasuna, N. Sathyanarayana, D. Srikanth Reddy. © 2027. 32 pages.
Body Bottom