Dr. Haiko Lietz & Dr. N. Gizem Bacaksizlar Turbic

Computational Social Science is often concerned with the traces of human behavior like those left by uses of social media, messaging services, or cell phones. Such digital behavioral data is genuinely relational and can, therefore, be studied using the formal techniques of network analysis. The basic units of networks called nodes can be actors (e.g., users), communicative symbols (e.g., hashtags), or even transactions (e.g., tweets). By focusing on the edges (relations) among nodes, network analysis is capable of creating insights that are not possible by merely doing statistics on the nodes and their attributes. In the workshop, we will give an introduction to how network data should be organized, how networks can be created in Python, and how they can be analyzed on three levels. On the micro level, we will introduce centrality analysis which results in numerical descriptions of nodes. On the meso level, we will introduce community detection, which results in sets of nodes that form groups or clusters. On the macro level, we will introduce measures that describe homophily, assortativity of the network in its entirety. We will be using network data from the Copenhagen Networks Study, which describes four different types of social relations among students over time. The workshop will alternate between live-coding demonstrations and periods in which participants apply that knowledge in context, both using Jupyter Notebooks. The software we will be using is NetworkX, a standard Python library that is simple to understand, provides a breadth of options and has a large user community.