Unveiling the Impact of Fake News on Society
FAKE NEWS
DETECTION
Kavya Reddy Vasa
FAKE NEWS
Data that is false or misleading or whose source cannot be verified.
Why?
To intentionally damage reputations, deceive or to gain attention.
To increase number of clicks and visitors on a site.
To influence public opinion on political decisions or on financial markets.
Rose to popularity in 2016 US presidential elections.
TYPES OF FAKE NEWS
Clickbait
Often eye catchy content, to capture reader’s interest, that might not be facts.
Ex: news articles that start with “you won’t believe this…”
Satire/Parody
Content that is funny or humorous, but some fraction of people consider it as facts.
Propaganda
Content whose main purpose is to mislead the reader and influence him.
Biased
Content that is claim to be impartial but is completely partial.
Unreliable News
Content posted by journalists whose sources are unverified and with no fact checking
by themselves.
WHY SHOULD WE CARE
Considering an example of ongoing pandemic.
Something more dangerous than virus is infodemic
Infodemic is excessive amount of information about a problem that makes the
solution more difficult.
It has caused:
o
Promoting and selling fake cures.
o
Spreading myths and rumors about nature and spread of virus.
o
Conspiracy theories about origin and intention of virus.
o
Encouraging unfounded remedies.
WHAT DOES FAKE NEWS CAUSE
This causes
Fake news concerning health on social media represents a risk to global health.
By impacting reputation of a company, their stock prices can be crashed.
It is speculated it has some impact on 2016 US presidential election results.
DETECTION
There are 2 ways which are normally used to detect fake news.
1.
Manual Fake News Detection
Involves techniques and procedures a person can use to verify news.
It could be visiting fact checking sites or crowd sourcing real news to compare
with unverified news
Due to its gigantic nature, manual verification can be considered an impossible
task.
It might be too late to verify and remove, and damage is already done.
2.
Automated Fake News Detection
Using Natural Language Processing (NLP) and Machine Learning (ML)
approaches, different techniques are developed to automate the detection
process.
AUTOMATED FAKE NEWS DETECTION
A fake news detection framework exploiting social context called tri-relationship
embedding framework TriFN is proposed.
It is based on publisher-news relations and user-news interactions for fake news
classification.
A neural-network based model is proposed which generates comments for news
articles to help classification.
A stance detection model using deep learning architecture based on convolutional
neural networks and long short-term memory is proposed.
Stance detection is considered as a helpful first step towards detection.
Most of these models mainly consider article head, body and author for news
classification.
Dive into the realm of fake news detection and explore the different types of fake news, the importance of addressing misinformation, its detrimental effects, and the role of automated systems in combating false information.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
FAKE NEWS DETECTION
WHY SHOULD WE CARE o o o o
DETECTION 1. 2.
