Supporting data for "Exploring Storytelling with Natural Language Processing: Representation, Non-linguistic Factors, and Narrative Engagement"

The uploaded datasets comprise 1) A Project Gutenberg Protagonist-based dataset consisting of 300 protagonists found in 261 books. This dataset includes narrative features analyzed using time series data for these 300 fictional characters. 2) A dataset containing over 3 million time-synchronic comments obtained from 240 movies. Additionally, linguistic features of the comments from each movie are computed using Linguistic Inquiry and Word Count. The uploaded files also include essential information about the books and movies.