Mission Statement Topics
TL:DR
Below I use Prismatic’s API to tag the mission statements of approximately 500 colleges in the U.S. in order to evaluate the “focus” of each, which I define as the topics extracted from the API. In addition, I also consider the competitive nature of various schools, commonly referred to as the “Competitor Set.”
Out of the gate, I considered more than 1,000 schools for this study…
Quick Side Note
This is intended to be a quick post on playing around with the recently released Prismatic Interest Graph API. I encourage you to take a few minutes to scan the blog post; very cool stuff!
For me, the timing couldn’t be better…
As I am wrapping up the work on this post, I noticed they just enhanced the API to search for related topics. Awesome! I put together a basic R Package prismaticR. Let me know what you think!
I am going to use the API to extract topics…
I encourage you to head over to my Github repo to review my code where all data collect is done within R, no point-and-click necessary! …
The Data
First, a talk about the schools that I am including in this work…
- The institution is located in the domestic US (and is not a military institution)
- Public 4-year and Private, 4-year not-for-private degree-granting institutions
- Enrolled more than 300 first-year students
After getting this list of about 1,000 schools, I crawled each institutions’ College Navigator page to parse out the URL for their mission statement…
To make this analysis possible, I used RNeo4j
to put these datasets into a graph, using the data model shown below:
Our dataset has two types of nodes, School
and Topic
…
Explore the Graph
The table below shows 10 rows of data were schools are connected to topics.
school | name | topic | score |
---|---|---|---|
100663 | University of Alabama at Birmingham | Budgets and Budgeting | 0.5017 |
100663 | University of Alabama at Birmingham | Birmingham, Alabama | 0.5091 |
100663 | University of Alabama at Birmingham | Higher Education | 0.5124 |
100663 | University of Alabama at Birmingham | Colleges and Universities | 0.5603 |
100751 | The University of Alabama | Colleges and Universities | 0.6104 |
100751 | The University of Alabama | Alabama | 0.6066 |
100751 | The University of Alabama | Mobile, Alabama | 0.5434 |
100751 | The University of Alabama | Research | 0.5433 |
100751 | The University of Alabama | Higher Education | 0.5294 |
100751 | The University of Alabama | Montgomery, Alabama | 0.5261 |
Analysis
Let’s start to ask some questions from the database…
Summary
I am still new to Neo4j to solve business problems, but hopefully you found at least some part of this post interesting or helpful…
Brock Tibert © 2021
Published with Wowchemy — the free, open source website builder that empowers creators. ```
This conversion retains the main content of the original HTML page, transforming links and images into Quarto-compatible markdown, while maintaining the integrity of the body text and structure.