The term Social Network Analysis (or SNA) often conjures thoughts of social media and cool visualizations. That’s certainly part of the picture, but not all of it. This year at MERLTech, we gave an introductory session on what SNA is, how it can be used, and how to make it work for you. If you missed it, here’s the quick and dirty on what you should know.
SNA isn’t just for social media! SNA is a very versatile tool. It can be used to process big data with applications for cybersecurity and biological and epidemiological projections. Beyond looking at networks of individuals, SNA can explore relationships with concepts through analysis of qualitative data and concept mapping. It can also look at organizational risks and processes (i.e. comparing an organizational chart with who people actually go to for information). Use it to help determine which organization to work with (who is likely to spread ideas to other organizations); which groups to target (who are most excluded from the network); inform projections of sustainability or the spread of information; or evaluate whether you’ve built connections between certain entities.
Learn the lingo! SNA uses a different vocabulary than many other analytic techniques. Links, nodes, attributes, and the different types of centrality measures are useful to understand before delving in.
Use best practices:
1. Define your purpose and questions: Who are your users and what information do they need? Use this to map out what you will need to measure and how.
2. Collect your data: Use customized interviews or surveys, export from existing datasets, or use other maps and software.
3. Crunch your numbers: To understand what your data is telling you, explore the different centrality measures. Make sure to clean the data well (it can be a heavy lift) and recognize the limitations. Use software (there are tons out there!) to help with this.
4. Visualize the network: Most software that you use in Step 3 will also help with this step. Mess around with the different configurations for some great visual depictions of your analysis. Some of the most common software are UCINet, Gephi, and NodeXL.
5. Interpret your results: You have a great picture – so what? How does this relate to your program or the purpose behind why you undertook SNA?
There’s so much more to explore here, so feel free to reach out to either of us for more resources or tips!