Media of University of Babylon | A Detailed Seminar by PhD Candidate Iman Qais Abdul-Jalil in the Software Department, College of Information Technology

Media of University of Babylon - كلية الطب

A Detailed Seminar by PhD Candidate Iman Qais Abdul-Jalil in the Software Department, College of Information Technology – University of Babylon

by : Duhaa Fadill Abbas

Date : 18/5/2025 07:05:09 PM

Veiw : 35

A Detailed Seminar by PhD Candidate Iman Qais Abdul-Jalil in the Software Department, College of Information Technology – University of Babylon

Duhaa Fadill Abbas
As part of the ongoing academic activities for postgraduate students, the Software Department at the College of Information Technology – University of Babylon held a comprehensive seminar for PhD candidate Iman Qais Abdul-Jalil, to discuss the scientific aspects of her dissertation entitled:

"Detecting Fake News on Social Networks Based on Textual and Visual Sources Using the Deep Learning Attention Mechanism"

The seminar was conducted under the supervision of Prof. Dr. Israa Hadi Ali, and attended by the scientific committee composed of:

- Prof. Dr. Huda Naji Nawaf – Chair
- Prof. Dr. Iman Salih Sakban – Member
- Prof. Dr. Asaad Sabah Hadi – Member
- Asst. Prof. Dr. Ahmed Khalaf Obeid – Member
- Asst. Prof. Dr. Ahmed Habeeb Saeed – Member
- Prof. Dr. Israa Hadi Ali – Member and Supervisor

With the growing popularity of social media platforms, the dissemination of misinformation and fake news has become a pressing issue, resulting in widespread public mistrust and significant challenges in manual detection due to the speed and volume of content. In response, the academic community has made considerable efforts to develop automated algorithms for fake news detection.

However, many of the existing detection systems focus primarily on the textual content of the news article, overlooking the substantial influence of accompanying visual elements, which often serve as a primary motivator for initial engagement and further sharing. This over-reliance on textual analysis alone limits the accuracy of fake news detection—particularly for visually-rich content—highlighting the necessity for a more robust and multimodal approach.

The core objective of this research is to develop an advanced multimodal framework for detecting fake news by integrating both textual and visual data sources. The proposed model leverages deep learning and attention mechanisms to enhance prediction accuracy, demonstrating the capacity to effectively analyze and identify deceptive content within a curated news dataset.