Mini-Project: Finding Allies Based on Mission Statements

An important aspect of developing a campaign for social change is finding your allies. A broad approach to this problem might simply be to identify organizations that share your aims. But building a coalition around similar aims is not sufficient, as conflict may arise around strategy if your organizations do not share similar values.

Two organizations may share aims, but if there is a large difference in values, they will not agree on strategy.

Thus, in order to find new organizations to ally with as part of an organizing campaign, it would be useful if there were a way to draw out the values of an organization. This can be hard to do even as a human, since many organizations will not explicitly shout their values for fear of alienating donors and funders that are not ideologically aligned.

I decided to look at mission statements of several nonprofits in Chicago that are related to community development and housing, to see if I could use natural language processing and topic modeling to identify organizations that would be closely aligned with the coalition to Lift the Ban on rent control.

---

Step 1: Get the Data
I was lucky enough to start with a list of URLs that pointed either to mission statements or 'about us'/'our history' pages for my 80 different non-profits in Chicago. I grabbed the <p> tags for these websites using BeautifulSoup, and removed case and punctuation. I chose not to use any stemming algorithms, since 'organize' and 'organizer' imply a very different value than 'organized' or 'organization.'

Step 2: Topic Modeling
I removed some uninformative words from the text (names of neighborhoods, bids to share on social media) and tried some different tools to elucidate hidden 'topics' in the mission statements. Essentially, by finding certain words that show up together in documents, we can pull out topics that are not necessarily explicitly stated.

Below are some representative words that define two 'latent' topics in our mission statements.

Representative Words - Topic  8
people, justice, communities, organization, organizing, work, chicago, racial, power, working

Representative Words - Topic  9
support, development, training, opportunities, equity, programs, providing, program, provide, resources

For Topic 8, we see that words like 'justice', 'organizing', 'power' and 'working' are likely to co-occur. These are likely organizations that are more focused on an approach of collective action. In contrast, Topic 9 has words like 'support', 'training', 'opportunities', 'provide', and 'programs' - these are probably organizations that focus more on direct services and developing individuals. Next I was able to identify how strongly aligned a particular organization's mission statement is with each topic. For example, a shelter that provides job training and organizes around getting funding for shelters might be a little aligned with Topic 8, but mostly aligned with Topic 9. The coalition to Lift the Ban on rent control is heavily focused on collective action, and seeks similar allies. I set a threshold to filter for organizations heavily aligned with Topic 8.  nd voila, I had a list of 25 organizations - approximately half were already allied with the coalition (up from 10% frequency in the dataset), and the remaining organizations are now flagged for us to approach and ask to join the coalition!