chaitra-1.pptx fake news detection using machine learning

Fake news detective using machine learning

1. GOVERNMENT ENGINEERIN G COLLEGE, RAICHUR-584135 Technical seminar on “ FAKE NEWS DETECTION USING MACHINE LEARNING “ Name : K Chaitra USN: 3GU21CS404 Under The  Guidance Of Prof . Dr. Shiva prakash

2. FAKE NEWS DETECTION USING MACHINE LEARNING

3. AGENDA Table of contents Introduction. What is fake news? Proposed system. Methodology. System architecture. Modules Advantages. Disadvantages. Conclusion. References.

4. Introduction Fake news detection using machine learning involves employing algorithms and models to identify misinformation or deceptive content within news articles, social media posts, or other textual sources. This innovative approach leverages the capabilities of machine learning to analyze patterns, linguistic features, and contextual information to distinguish between genuine and fabricated information. By training machine learning models on labeled datasets containing both real and fake news samples, the system learns to recognize subtle patterns and characteristics associated with misinformation. Features such as language style, sentiment, source credibility, and the presence of misleading information contribute to the detection process

5. WHAT IS FAKE NEWS? Fake news refers to false or misleading information presented as factual news. It can be intentionally fabricated or distorted to deceive readers or viewers for various purposes, such as spreading propaganda, influencing opinions, or generating revenue through clicks or views. Fake news refers to false or misleading information presented as legitimate news. Here are some key points about fake news: 1. False Information 2.Misleading Intent 3.Spread Through Various Channels 4. Manipulative Techniques 5. Potential Harm

6. Proposed system Figure1: flow chart for fake news

7. Methodology Existing system : There exists a large body of research on the topic of machine learning methods for deception detection, most of it has been focusing on classifying online reviews and publicly available social media posts. Proposed system : In model is build based on the count vectorizer or a matrix relatives to how often they are used in other artices in your dataset can help . Since this problem is a kind of text classification, Implementing a Naive Bayes classifier will be best as this is standard for text-based processing.

8. System architecture Figure 2:system architecture

9. Modules Data Use Preprocessing Feature Extraction Training the Classifier

10. Advantages Scalability Automation Pattern Recognition Adaptability Multifactor Analysis

11. Disadvantages Bais in Training Data Adaptability to Evolving Tactics Linguistic Nuances and Context Overemphasis on Source Reputation Privacy Concerns

12. Conclusion In conclusion, the use of machine learning for fake news detection holds great promise in addressing the growing challenge of misinformation in today's digital landscape. As discussed, these algorithms leverage advanced techniques such as natural language processing and ensemble methods to analyze patterns, linguistic cues, and contextual information to discern between credible and deceptive content. While machine learning has shown remarkable effectiveness in identifying fake news, it is crucial to acknowledge the ongoing challenges associated with this field.

13. References 1. Academic Journals: - Journal of Artificial Intelligence Research. 2. Conferences:-Conference on Empirical Methods in Natural Language Processing (EMNLP) 3. Reputable Websites and Platforms:- arXiv.org: A preprint repository where many researchers share their work before formal publication. 4.Books:- "Fake News and Africa: Politics, Disinformation, and Power" by Winston Mano and Dumisani Moyo .

14. THANK YOU