Fake News Detection using Optimized Deep Learning
Join Dr. Mayank Kumar in exploring AI-driven solutions for combating misinformation and supporting UN Sustainable Development Goals through advanced deep learning research.
About This Webinar
Explore cutting-edge deep learning approaches for fake news detection, featuring the Hybrid CNN-BiLSTM model with Harris Hawks Optimization as presented in the recent Springer publication.
Advanced AI Architecture
Hybrid CNN-BiLSTM model with Harris Hawks Optimization for superior fake news detection accuracy up to 98.89%
Optimized Feature Selection
HHO algorithm removes redundant features, enhancing model performance and reducing computational complexity
Proven Results
Comprehensive evaluation across 4 public datasets (ISOT, Kaggle, ConFake, McIntire) with state-of-the-art performance
Research Publication
This webinar is based on groundbreaking research published in Springer's "Social Network Analysis and Mining" journal, presenting novel approaches to fake news detection using optimized deep learning techniques.
Key Achievements
Featured Speaker
Dr. Mayank Kumar is an Associate Professor at Amity University Rajasthan with 15 years of teaching experience in Computer Science and Engineering. His expertise lies in Natural Language Processing (NLP), Machine Learning (ML), and Image Processing. He is passionate about research and innovation, focusing on AI-driven solutions for real-world challenges.
With strong technical proficiency in Java, Python, C, SQL, and LaTeX, he enjoys mentoring students, collaborating on research projects, and contributing to advancements in AI and computational sciences. His goal is to bridge the gap between theoretical research and practical applications, fostering meaningful impact in academia and industry.
Education
Areas of Interest
Selected Publications
Jain, Mayank Kumar, Dinesh Gopalani, and Yogesh Kumar Meena. "Hybrid CNN-BiLSTM model with HHO feature selection for enhanced fake news detection." Social Network Analysis and Mining 15, no. 1 (2025): 43.
Jain, Mayank Kumar, Dinesh Gopalani, and Yogesh Kumar Meena. "UcConvoNet: unifying customised features for deep CNN-based fake news detection." Multimedia Tools and Applications (2025): 1-32.
Jain, Mayank Kumar, Dinesh Gopalani, Yogesh Kumar Meena, and Anupam Kumar. "Combating fake news utilizing content-based word embedding and language features." In 2025 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), vol. 3, pp. 1-6. IEEE, 2025.
Webinar Curriculum
A comprehensive journey through fake news detection using optimized deep learning, with emphasis on contributing to UN Sustainable Development Goals
Definition of fake news | Real-world impact examples (e.g. Pizzagate, mob lynching, COVID-19 misinformation) | Importance of automatic detection in society and SDG alignment.
How fake news detection supports UN SDG Goals 16, 4, and 9 | Building trustworthy information systems | Contributing to peaceful and inclusive societies.
Feature redundancy and selection issues | Limitations of existing ML/DL models | Dataset biases and generalizability concerns.
Overview of traditional ML classifiers (SVM, RF, NB) | Introduction to CNN, LSTM, BiLSTM models | Strengths and limitations in fake news detection.
Hybrid CNN-BiLSTM model architecture | Harris Hawks Optimization (HHO) algorithm concept | Integration of HHO for intelligent feature selection.
Data preprocessing steps | Linguistic feature extraction (80 features) | HHO-based feature selection process | Integration with CNN for spatial features and BiLSTM for sequential learning.
Performance on ISOT, Kaggle, ConFake, McIntire datasets | Comparative accuracy, precision, recall, F1-score | Advantages over existing state-of-the-art models.
Hyperparameter settings | Tools and libraries (Python, NLTK, LIWC, TextBlob, etc.) | Best practices for reproducibility in research projects.
Extension to other NLP tasks | Potential improvements and ongoing challenges | Contributing to SDG objectives through AI research.
Open discussion to address participant queries on methodology, implementation, research applications, and SDG contributions.
Frequently Asked Questions
Register for Free
Join us for this exclusive webinar on AI-driven fake news detection and learn how your research can contribute to UN Sustainable Development Goals.
Supporting UN Sustainable Development Goals
This webinar directly contributes to achieving multiple UN SDG targets through AI-driven solutions for information integrity and educational advancement.
SDG 16: Peace, Justice and Strong Institutions
Fake news detection enhances information integrity, combats misinformation, and builds trust in institutions, supporting peaceful and inclusive societies.
SDG 4: Quality Education
Educating students and researchers in AI applications and media literacy to build critical thinking skills for the digital age.
SDG 9: Industry, Innovation and Infrastructure
Advancing AI innovation and technological solutions for real-world challenges in information systems and digital infrastructure.
How This Research Contributes to Global Goals
Information Integrity
By developing advanced AI models for fake news detection, we strengthen the foundation for trustworthy information systems, directly supporting democratic institutions and informed decision-making processes.
Educational Impact
This research contributes to quality education by advancing AI literacy, providing practical learning opportunities, and developing tools that can be used in educational settings to teach media literacy and critical thinking.