Skip to content

Latest commit

 

History

History
75 lines (57 loc) · 3.17 KB

README.md

File metadata and controls

75 lines (57 loc) · 3.17 KB
Raw

fake-news-project

S3 Project to tackle the problem of fake news on the web and social media.

Fake News

Currently social media has given a lot of power to every individual to raise his voice and raise his/her concern. People also use this medium to make other masses aware of the current world situation by telling news. People sometimes use this opportunity for other malicious activity by spreading fake news. This is done by for many reasons for gaining fame, misinforming society to change their opinion on any subject, etc. This has a huge impact on the society’s thinking and sometimes may cause social unrest.

Our objective is to design a classifier that distinguishes between authentic and fake news.

Design thinking

Problem

News content has some properties:

  1. Source (optional)
  2. Timestamp
  3. Content: Text, Images, Video
  4. Subject
  5. Title
  6. Medium

But many news are Fake, the problem is that the truth about news, could be different to each person depending on their political views, education, culture, etc.

The costs in time and human resource needed to verify a message can be reduced if we have an automatic system to classify content as Fare or Fact.

Solutions

  1. Train a classifier using text content only.
  2. Train a classifier or predict a trust measure for sources.
  3. Search for similar news in other sources and give a weight depending on the source.
  4. Calculate a probability of the event described in the news. My dog was abducted by a UFO.
  5. Generate fake news for training our classifiers.
  6. Crowd source the classification task, asking persons what they think about the news.

Each member selected a solution to build prototype (or details about the solution)

Members / Solutions

  1. Mario García Valdez
  2. Chenxu Hu 3
  3. Rahul Mishra 1,5,6
  4. Dong Pil Yu 1
  5. Junghwan Lee 1
  6. Mario Alejandro 1
  7. Taishi Ito 1

Proposed Tutorials:

Evolutionary Computation: A Unified Approach Kenneth De Jong, Krasnow Institute Monday, July 16, 09:00-10:40 Conference Room D (3F)

Introducing Learning Classifier Systems: Rules that Capture Complexity Ryan Urbanowicz, University of Pennsylvania Danilo Vargas, Kyushu University Sunday, July 15, 09:30-11:10 Conference Room Medium (2F)

Evolution of Neural Networks Risto Miikkulainen, The University of Texas at AustinSunday, July 15, 12:50-14:30 Terrsa Hall (1F)

Evolutionary Computation for Digital Art Aneta Neumann, The University of Adelaide Frank Neumann, The University of Adelaide

Evolutionary Computation and Evolutionary Deep Learning for Image Analysis, Signal Processing and Pattern Recognition Mengjie Zhang, Victoria University of Wellington Stefano Cagnoni, University of Parma Monday, July 16, 16:00-17:40 Conference Room D (3F)

Cloudy Distributed Evolutionary Computation JJ Merelo, University of Granada Monday, July 16, 14:00-15:40 AV Study Room (2F)

Evolution of Neural Networks Risto Miikkulainen, The University of Texas at Austin Sunday, July 15, 12:50-14:30 Terrsa Hall (1F)