Text Network Analysis

Frederik Elwert - Ruhr-University Bochum

Many applications of historical network analysis apply concepts originating from social network analysis (SNA). They focus on persons (or groups) as central units, and they aim at studying social structures. Texts are then used as sources of information about relevant actors and their relations.

Another way of combining text and network analysis is to study the text itself as a network of meaning. Then, words for the nodes of the network, not persons. Relations between words are inferred from shared context, or from similar usage patterns across the text. Networks can then be used to analyse and visualize text structures, semantic relations, or fields of meaning.

The workshop will cover several approaches to text network analysis. It will show how to use natural language processing in order to prepare texts, how to convert texts to networks, and how to visualize and analyse those networks.

If you want to discuss possible applications of text network analysis with regard to your own material, please contact us in advance.

For natural language processing, we will use the WebLicht. WebLicht is accessible through many European universities. Please try out if you can log into WebLicht using your institution. In case you experience difficulties, please contact the workshop organizers.

For text network analysis, we will use various Python packages. Please bring a Laptop with Python installed, as explained in the description of the Python workshop. You can find installation instructions for the text networks software on this page, and you can download the data files used in the workshop.