R package that converts transcripts to graphs (networks), includes parameters relevant to educational research


Many disciplines use transcripts to record sequential information. Transcripts that capture a conversation can become long, making systematic analyses difficult or time-consuming. This package allows researchers to visualize transcripts in a succinct format through the lens of graph theory. Graph theory is a discipline of mathematics involving “nodes” and “edges” that model objects and the relations between them. The goal is to get more information from transcripts through this alternative view.

Graphs, nodes, and edges may be characterized in various ways. For example, the number of edges connected to any particular node is called the node’s degree. Another example, the number of edges in a graph divided by the number of possible edges is called the density of the graph. We consider these characteristics of graphs (calling them “parameters”) and pick out the relevant ones for educational researchers.


To get started installing the package, run the command install.packages('discourseGT') in R, which will download the most stable package from CRAN.

How to Use

The key functions and examples of how to use this package can be found in this document.

How to reach out?

Where do I report bugs?

Please open an issue on GitHub.

How do I contribute to the package?

If you have an idea (but no code yet), open an issue on GitHub. If you want to contribute with a specific feature and have the code ready, fork the repository, add your code, and create a pull request.

Do you need support?

The easiest way is to open an issue - this way, your question is also visible to others who may face similar problems.


This package is MIT Licensed Written by Albert Chai \<@albertchai>, Andrew S. Lee \<@alee4738>, Joshua P. Le \<@jpl038>, Jitarth Sheth \<@jshethbright>, Qi Cui \<@q1cui>, and Stanley M. Lo \<@smlo>

Try the discourseGT package in your browser

Any scripts or data that you put into this service are public.

discourseGT documentation built on July 26, 2023, 5:46 p.m.