Date of Completion

2022

Document Type

Honors College Thesis

Department

Mathematics

Thesis Type

Honors College

First Advisor

Chris Danforth

Second Advisor

Peter Dodds

Keywords

timeseries, Stephen King, language, literature, word frequency, emotion

Abstract

Sentiment analysis, the computational inference of emotion in text through Natural Language Processing, is increasingly used to analyze social and cultural trends. In this thesis, we create narrative time-series and word-shift graphs for each of Stephen King’s novels using the Hedonometer, quantifying the lexical changes responsible for emotional arcs found in each story. Our results suggest King’s work has increasingly shifted in genre from horror to science fiction. The work contributes to a growing science of stories being developed by the Computational Story Lab.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.

Share

COinS