Debunking multi-lingual social media posts using deep learning.

Area of Science:

• Artificial Intelligence
• Natural Language Processing
• Computational Linguistics

Background:

• Fake news on social media poses a significant threat to public opinion.
• Detecting multilingual fake news requires advanced computational methods.

Purpose of the Study:

• To develop and evaluate a deep learning model for debunking multilingual social media posts.
• To create a robust system for identifying and classifying fake news in English and Hindi.

Main Methods:

• Web scraping and Natural Language Processing (NLP) techniques were used to build a dataset of English and Hindi social media posts.
• A deep learning model was trained using features such as ELMo embeddings, TF-IDF, sentiment analysis, and Named Entity Recognition (NER).
• Classifiers were evaluated on datasets exceeding 45,000 articles, comparing Machine Learning (ML) and Deep Learning (DL) algorithms.

Main Results:

• The proposed Debunking Multi-Lingual Social Media Posts using Deep Learning (DSMPD) approach demonstrated effectiveness in classifying news.
• The model categorizes news into five levels: real, could be real, could be fabricated, fabricated, or dangerously fabricated.
• Performance comparison between ML and DL algorithms identified the optimal model for fake news detection.

Conclusions:

• Deep learning models offer a promising solution for detecting fake news across multiple languages.
• The DSMPD approach provides a framework for analyzing social media content to combat the spread of misinformation.
• Further research can refine these models for enhanced accuracy and broader language support.