GlobeLab
@ The Boston Globe
in partnership with
NULab for Texts, Maps, and Networks
and
The Boston Area Research Initiative,
with the help of
a distinguished advisory board,
present a new kind of data collaboration.
Get Inspired!
On October 17, Northeastern University will host a "skill-a-thon" where you will have the opportunity to get an overview of state-of-the-art data analysis methods from prominent researchers and scholars. The goal of these 20-30 minute sessions is to expose you to a wide range of approaches your team can use to analyze the various types of data with which you'll be working. Topics include:
- Best practices for extracting and cleaning data
- Sentiment analysis and topic modeling using natural language processing
- Classification and prediction using machine learning
- Relational data using network analysis methods
- Analyzing geo-spatial data using GIS methods
- Developing interactive data visualizations
There is limited space but open to anyone interested in hearing about novel ways to manipulate data. Register for the event here!
Introducing...The Data
We have assembled a team of Data Guardians who will explain and share their exciting datasets at the event. Each team will be focused a specific set, but will have access to all the datasets for supporting material. Aside from our official Data Guardians, there will be an opportunity for anyone to offer a dataset to share with the group. Anything is "in bounds" for your research, but the group that best showcases their dataset will have an advantage.
Full articles and metadata from The Boston Globe online, January 2011-present.
Enigma empowers the discovery of hidden facts and connections across the universe of big public data. Access everything from import bills of lading, to aircraft ownership, lobbying activity, spectrum licenses, financial filings, liens, government spending contracts and much, much more.
Media Cloud is an open source, open data platform that allows researchers to answer quantitative questions about the content of online media. Using Media Cloud, researchers, journalism critics and interested citizens can examine what media sources cover which stories, what language different media outlets use in conjunction with different stories, and how stories spread from one media outlet to another
Digital Public Library of America
The DPLA “offers a single point of access to millions of items—photographs, manuscripts, books, sounds, moving images, and more—from libraries, archives, and museums around the United States.” More pertinently for this meeting, the DPLA “contains metadata records” for 4.5 million “photographs, manuscripts, books, sounds, moving images, and more from libraries, archives, and museums around the United States.”
2012 Presidential Campaign Contributions
Using public data from the FEC since 2001, we track the contributions from all donors in the Boston area and link these contributors to street addresses, employers, and occupations.
The City of Boston's Assessing Department is responsible for the administration of property tax records, tracking for all parcels (i.e., the smallest ownable unit) a variety of details, including address, current owner, square footage, land use, assessed value, and whether it is owner-occupied, as well as other related details. The database is updated yearly. The City of Boston and the Boston Area Research Initiative have teamed up to construct a version of this database that runs from 2000 to present, providing a longitudinal snapshot of the physical and economic landscape of Boston and its neighborhoods. The database has been mapped in such a way that it is compatible with both City administrative databases (e.g., 911 calls) and census geographies (e.g., block groups, tracts).
Our Distinguished Advisory Board
- Barry Bluestone
- Beth Noveck
- Curt Savoie
- Gary King
- Latanya Sweeney
- Rob Sampson
- Chris Winship
- Beth Altringer
- Mauro Martino
- Jennifer Chayes
- Sandy Pentland
- Ethan Zuckerman
- Sarah Williams
- Dietmar Offenhuber
- Steve Poftak
- Jessica Martin
- Mark Warren
- Michael Johnson
- Georges Grinstein
- Holly St. Clair
- Joan Fitzgerald
- Eric Gordon
- Jessica Casey
- Nathan Phillips
And Many Thanks to our Planning Committee!
- Adrienne Debigare
- David Lazer
- Brian Keegan
- Daniel O'Brien
- Nathan Matias