Performance Analysis of Leveraging Deep Learning Architectures for Identifying Fake News
Scenario -1 :
—————–
Implementation plan:
——————————
Step 1: Initially we collect and load the IFND Dataset.
Step 2: Next we implement data pre preprocessing using the CoreNLP toolkit
Step 3: Next we implement feature extraction process using RMS-BERT-CapsNet method
Step 4: Next we encode and store the textual and visual data using VAE-based Deep-Shallow multimodal fusion method
Step 5: Next we implement EWC-GEM Continuous learning for training process
Step 6: Next we implement a Vision Transformer with a Bidirectional Long Short-Term Memory algorithm to improve the classification accuracy.
Step 7: Finally, Generate the graph for,
7.1: Number of Epochs vs. Accuracy (%)
7.2: Number of Epochs vs. Loss (%)
7.3: Number of Epochs vs. F1-Score (%)
7.4: Number of Epochs vs. Training Loss
7.5: Number of Epochs vs. Validation Loss
Scenario -2 :
—————–
Implementation plan:
——————————
Step 1: Initially we collect and load the albanian-fake-news-corpus Dataset.
Step 2: Next we implement data pre preprocessing using the CoreNLP toolkit
Step 3: Next we implement feature extraction process using RMS-BERT-CapsNet method
Step 4: Next we encode and store the textual and visual data using VAE-based Deep-Shallow multimodal fusion method
Step 5: Next we implement EWC-GEM Continuous learning for training process
Step 6: Next we implement a Vision Transformer with a Bidirectional Long Short-Term Memory algorithm to improve the classification accuracy.
Step 7: Finally, Generate the graph for,
7.1: Number of Epochs vs. Accuracy (%)
7.2: Number of Epochs vs. Loss (%)
7.3: Number of Epochs vs. F1-Score (%)
7.4: Number of Epochs vs. Training Loss
7.5: Number of Epochs vs. Validation Loss
Software Requirement:
———————————
1. Development Tool: Python – 3.11.4
2. Operating System: Windows 11 (64-bit)
Dataset link:
——————
Scenario -1 :
—————–
https://www.kaggle.com/datasets/sonalgarg174/ifnd-dataset
Scenario -2 :
—————–
https://www.kaggle.com/datasets/gentrexha/albanian-fake-news-corpus/data
Note:
——–
1) If the above plan does not satisfy your requirement, please provide the processing details, like the above step-by-step.
2) Please note that this implementation plan does not include any further steps after it is put into implementation.
3) This project is only based on simulations. Not a real time project.
4) If the above plan satisfies your requirement please confirm with us.
EXISTING:
—————
We make an existing process based on Reference 1 – Title: EFND: ASemantic, Visual, and Socially Augmented Deep Framework for Extreme Fake News Detection
