Codebook, data, and code for ArguLens, a conceptual framework and automated technique leveraging an argumentation model to support effective understanding and consolidation of community opinions.
These artifacts are used in the CHI2020 paper titled "ArguLens: Anatomy of Community Opinions On Usability Issues Using Argumentation Models" (preprint available: https://arxiv.org/pdf/2001.06067.pdf)
-
The "Codebook.xlsx" file is the codebook we used during the argumentation analysis study.
-
The "Annotated Corpus.csv" file is the annotated corpus that we created through the argumentation analysis that includes 5123 quotes with their corresponding codes.
-
The "Argument Extraction Program and Results" folder is the machine learning program we used in the argument extraction study, as well as the corresponding data and results. Python with the Scikit Learn library and a Jupyter Notebook environment is needed for running the program. Please see the "README.md" file for information about individual files and instructions for running the program.