This document provides an overview of several international case studies that use data for social good. It summarizes projects that have used data to:
1. Predict homelessness in New York City to allow for early intervention.
2. Analyze mentoring engagements to understand what makes them successful for an online mentoring program.
3. Cluster arts organizations to help them benchmark and improve based on peer analysis.
It then lists additional examples of using data for social good, such as helping fundraising campaigns succeed, measuring literacy through poetry, and prioritizing vacant property rehabilitation.
6. Social Good
A good or service that benefits the largest
number of people in the largest possible way.
Classic Examples
Clean air, clean water, education, social welfare, human rights
Modern Examples
Healthcare, internet
Related Concepts
Common good, public service, corporate social responsibility
7. Data
⼀一個概念
Big Data for Social Good
Data Science
“Good people using data to do good things.”
12. Background
• 53,000 people in living in homeless shelters in New York during
November 2013, including over 12,000 families with over 22,000
children.
• Eviction is one of the top reasons families lose their homes and
transition into to the city’s shelter system.
Question
• What if we could predict which families are at heightened risk of
homelessness via eviction?
• Early warning -> early intervention
Early Results
• A tool that allows social workers and advocates to predict the likelihood
of an eviction notice leading to shelter entry, as well as the timeframe
available for prevention.
What’s Next • Help NGOs use the prediction results to communicate with at-risk
families.
http://blog.sumall.org/post/88610177356/the-numbers-behind-the-words
16. Background
iCouldBe’s e-mentoring program has served over 19,000 at-risk youth
since 2000, providing middle and high school students with an online
community of professional mentors that empowers them to stay in school,
plan for future careers and achieve in life.
Question
• Need definitions for their organizational goals and metrics to improve
their program.
• “What makes a mentoring engagement successful?”
Early Results
• Defined a “successful” mentee/mentor engagement as one where a
mentee completes at least 3 “quests” or learning modules in 3 months.
• Identified the characteristics of engagements and interactions.
• "I'm here for you.”
• A Predictive model to identify key predictors
• A framework for text analysis
What’s Next • Find more indicators of success/failure
• Review current programs
http://www.datakind.org/projects/uncovering-the-abcs-of-successful-online-mentoring/
18. Background
• The Cultural Data Project (CDP) not only collects financial and
programmatic data from over 11,000 arts and cultural institutions across
the U.S., it delivers that information back to the organizations
themselves, to the funders who support them and into the hands of
advocates and policy makers who believe in them.
• Each year, organizations ranging from small, all-volunteer dance
troupes to multi-million dollar museums across the country submit data
to CDP as part of the grant application process with public and private
funders. This means CDP has collected a broad dataset with 50,000
records, including up to 1,200 data points on each organization.
Question • What makes an art organisation successful?
• How can we create more effective tools and training?
Early Results
• Found clusters of art organizations
• Compared the financial success of the five clusters that resulted from
the CDP Team's segmentation.
• “cluster-4,” is the one cluster that does not achieve financial success.
This cluster is a mixed cluster, not dominated by any one type of
organization.
What’s Next
• Improve the categorisation of art organizations
• Develop targeted services to organizations and enabling them to
benchmark themselves to understand how they’re doing in relation to
their peers.
http://www.datakind.org/projects/clustering-arts-organizations-to-help-them-thrive/
22. Background
• GlobalGiving is the world's first and largest crowdfunding community for
nonprofits. Since 2002, more than 400,000 donors have given $150
million to more than 10,500 projects in 160 countries.
• GlobalGiving also helps them learn fundraising and operational best
practices to improve their efficiency and increase their impact.
Question
• GlobalGiving wanted to help their community be even more successful
by looking at their past fundraising campaigns or “projects” to
determine what factors lead to projects being successfully funded.
• They wanted to know - was there a formula for project success?
Early Results
• Success factors: project title, funding amount, photos, speed of
funding?
• Projects focused on hunger did better than projects focused on
economic development and nearly 50% of donors skip the predefined
donation values, choosing instead to enter their own donation amount.
• A correlation between specificity of language and project success.
• “arts” < “photography exhibit"
What’s Next • Take a deeper look at the data
• Improve data quality
http://www.datakind.org/projects/helping-great-causes-get-funded/
24. Background
• The literacy gap poses the greatest threat to the future of America.
Nearly two-thirds of fourth graders don't meet reading proficiency
standards.
• Power Poetry is a social platform that brings young poets together.
Users can write, post, share, and comment on each other’s poems. For
some youth in low-income communities, community support is next to
impossible in real life, but with Power Poetry, an expansive network of
young poets can instill a sense of empowerment and motivation to
change.
Question • Can we measure literacy through poetry?
Early Results
• Those who publish at least 10 poems on Power Poetry saw a visible
progression of their language scores
• It was possible to map poems and their language scores to respective
low-income and high-income zip codes.
• Among powerpoetry.org users the literacy gap between low-income
and high-income neighborhoods appears to be about 9 percentiles.
• Active poets seemed to be able to advance their language score by
about 4-percentiles which is the equivalent of half of the gap between
more affluent and less affluent zipcodes.
What’s Next
• To create an assessment tool through which parents, educators,
policymakers can use to make informed decisions for their families,
schools, and society.
http://www.sumall.org/project-overview/power-poetry/
27. Background
• Boarded up buildings and overgrown lots have plagued Chicago’s low-income
neighborhoods for decades.
• Over the past five years, however, vacant and abandoned properties
have spread beyond the inner city and into the suburbs, disrupting
formerly stable working and middle class communities and prompting
the creation of a county-wide land bank, a new tool for fighting blight.
• Properties become vacant or abandoned because of weak real estate
markets in impoverished neighborhoods or because of the recent
region-wide foreclosure crisis.
Question
• The Cook County Land Bank has one job: to acquire vacant and
abandoned properties throughout Cook County and return them to
productive use.
• There are tens of thousands of boarded up homes and overgrown lots
in Cook County, and the land bank’s budget is limited.
• How will the agency figure out which of these properties to acquire, and
what to do with them?
Early Results • A database to search and analyze vacant properties.
• A model to compare the quality of neighborhoods.
What’s Next
• Engage stakeholders in communities to come up with mutually
acceptable criteria.
• A clear, justifiable plan of action for putting vacant properties back to
work.
http://dssg.uchicago.edu/2014/01/20/cclb-real-estate-finder-for-vacants.html
30. Background
• HURIDOCS is an international NGO that helps other human rights
organizations liberate, illuminate and manage this kind of data to make
a positive impact on the human rights situation worldwide.
• They had already collected over 40,000 processed judgments from the
ECHR HUDOC database and fed them into their Caselaw Analyzer to
make it easier for people to access.
Question
• How could they use this data to improve the human rights situation in
Europe and further address the obfuscation of states' accountability?
• How judges were ranking cases as important and look for potential
patterns?
• linked to data from another ECHR website to show whether the case
judgment was ultimately enforced.
Early Results
• Scraped data from the Council of Ministers website showing the
execution of case decisions.
• Made data connections between case judgement and enforcement
• One-stop shopping for human right law cases
What’s Next • Enhance government accountability
• Study the trends of cases