Who are we?
A student organization of the College Of Computing at Georgia Tech.

We work on projects set by the group related to Big Data.
No skill is needed to join the Org, and there are no membership dues.
Make sure to check out our previous projects, sign up to our email list and see what we plan for the 2014-2015 academic year!
How to join
Meeting time:
Mondays at 6:30pm COC017 (College of Computing)
Membership dues:
There are no membership dues
Dinner Plan:
Free Pizza
Interested and want to hear more? Join the email list:
▾ Our project
▴ General Information
RetinaNews
Apply big data to the news!
The goal of the project is to organize news articles serve them intelligently to user. The Retina system has a several components:
  • The Crawler, which collects news articles from many sources.
  • The Clusterer, which runs algorithms to group similar articles together.
  • The UI, which makes news articles for the end user.
  • The API, which makes the database accessible to each component.
As a club member, working on this project will help you gain experience in many aspects of Big Data, and get valuable experience working in a larger team.

Join us Mondays from 6:30 - 8:00 pm in CoC 017, to work on the Missions shown on the right.
 
Clusterer Deploy
Leader: Philippe Laban
Email: plaban3@gatech.edu
Deploying analysis algorithms to Google Compute Engine, to run continuously
0 / 5
This mission hasn't started
 
Link Crawling
Leader: TBD
Email:
Extract all relevant links from crawled news articles, and crawl them.
0 / 6
This mission hasn't started
 
Article Extraction
Leader: TBD
Email:
Improve robustness for field extraction from HTML article documents by parsing metadata.
0 / 4
This mission hasn't started
 
Clusterer Algorithms
Leader: TBD
Email:
Add unsupervised learning for news clustering
0 / 5
This mission hasn't started
 
News Personalization
Leader: TBD
Email:
Finish user log in, and dump UI events in DB. This work leads into personalization.
0 / 5
This mission hasn't started
 
Article Ranking
Leader: TBD
Email:
Use social media shares, article recency, news sites, and other articles to rank news articles for display.
0 / 6
This mission hasn't started
 
Monitoring Dashboard
Leader: TBD
Email:
Display key stats about the database and other subsystems in a web ui
0 / 3
This mission hasn't started