RumorLens

UMSI Professor of Information Paul Resnick is developing an interactive rumor analysis system with practical applications in computational journalism.  RumorLens will aid journalists in finding posts that spread or correct a particular rumor on Twitter by exploring the size of the audiences that those posts have reached. 

The application will aid journalists and the general public in recognizing misleading information and will exhibit the spread and reach of particular rumors and their accompanying corrections on Twitter.

Start date: 3/1/2014
End date: 3/1/2015

Read More

The RumorLens application analyzes the spread of rumors on Twitter, allowing users to submit a tweet that characterizes a topic that interests them. The application will retrieve additional tweets related to the subject and prompt user feedback to classify results as propagating, debunking or unrelated to the original rumor. It will then use a text classifier to garner more widespread results. 

At the end of the process, RumorLens will present the user with a set of tweets that either support or discredit the rumor. The system will also provide accompanying data visualizations so that the user can see how many people were exposed to the original rumor, how many were exposed to the correction, and how many retweeted each. 

In addition to helping journalists and the general public detect misleading information, RumorLens will help users identify who had the most impact in spreading information about a particular rumor and measure the effectiveness of corrections in stopping the spread of the rumor.

Professor Resnick received a $60,000 award from Google, with an additional $20,000 of Google Cloud credits, to support the development of the RumorLens project. The grant is one of Google’s Computational Journalism Research Awards.

The project is planning for a public deployment of the RumorLens system in the summer of 2014 in order to gain feedback from users. 

Video detailing the RumorLens application and project:



 

Grants

Google Computational Journalism Research Award, Google Research: $80,000

Google Research Awards are one-year awards structured as unrestricted gifts to universities to support the work of world-class full-time faculty members at top universities around the world.


This project is also based upon work supported by the following grant:

SoCS: Assessing Information Credibility without Authoritative Sources, National Science Foundation: $765,994

The National Science Foundation is an independent federal agency created by Congress in 1950 "to promote the progress of science; to advance the national health, prosperity, and welfare; to secure the national defense…"