STAT 5901 Final Project

In this project, a sentiment lexicon is created using Facebook reactions data.

Running files

Before starting, you must download

• The dataset from here: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/XJN5L5
• The dependencies and outputs from here: https://drive.google.com/drive/folders/1L1NvcaC7N-tuDBnM6si4OwvaGhd0HKsZ?usp=sharing

These files are too large to upload to GitHub.

Run the files in the following order, ensuring the working directory has been set appropriately:

• clean_data.R
• create_lexicon.R
• prepare_SLDA.R
• compare_NRC.R
• compare_AFINN.R