Keyphrase Network Analysis
Masterclass Description
Keyphrase network analysis is a natural language processing (NLP) method that makes use of pre-trained language models (PLMs) to extract a keyphrase network from a text corpus. This network text analysis (NTA) or semantic network analysis approach offers a way to uncover patterns and trends that might otherwise remain hidden.
Keyphrase network analysis can effectively identify and extract important keywords or phrases that represent the main topics within a text document. These keyphrases are then used to construct a graph-based representation of the relationships between them, creating a keyphrase network.
The network structure allows the visualisation and analysis of how different keyphrases are connected through co-occurrence patterns. By analysing these connections, researchers can gain deeper insights into the semantic structure and organization of the text corpus, as well as uncover hidden relationships between various topics or concepts within the document.
During the workshop, we will use Python and Gephi to explore the keyphrase network analysis method by creating and visualizing a keyphrase network. A basic understanding of Python is useful, although both the method’s procedures and the theoretical and epistemological underpinnings of content will be discussed.
Speaker Biography
Pedro Jacobetty is a sociologist currently working at the University of Potsdam. His research interests intersect include technology, digital culture, knowledge production and circulation, media and communication. He is also interested in social theory and in innovative ways of using digital methods for social sciences and artistic production.
Booking Information
Upon booking, attendees will receive an automated confirmation email. This event will take place on Zoom. Attendees will receive a second email closer to the event date which will provide the Zoom link. Please use the same email for registering and when logging into Zoom.
Please inform us of any access requirements by emailing cdcs@ed.ac.uk. Further details about how CDCS uses your information obtained from booking onto our events can be found in our Events Privacy Statement.
