Pragmatics-In-Video-Games

---

Alejandro Ciuba, alc307@pitt.edu

February 14, 2022-May 1, 2022

---

Summary

This repository seeks to explore the following avenues on a small sampleset of video game text data:

1. How are orders/requests realized in video game dialogues? Are there more direct or indirect orders?
2. What is the frequency of the 2nd person pronoun, you?
   • Extending that, what are the frequencies of other pronouns?
3. What are some common named entities in video games?
   • Extending this, what are some hapaxes related to named entities?

---

PLEASE NOTE I am only publishing a very small sample of any dataset I did not originally make (excluding meta_kotor.pkl); however, I am including full data of any video game texts I parsed myself. If you wish to obtain a full dataset of any samples, please visit the original repository this research is based on, which can be found here.

---

Overview

Main Files

• final_report.md: The final full-length report where I conclude my exploratory research as well as present the statistics I found.
• Pragmatics in Video Games Presentation: A copy of my original presentation given on April 19, 2022 to my Data Science for Linguists peers and professor, Dr. Na-Rae Han.
• progress_report.md contains status updates on the research and data collected.
• data_description.md succinctly describes and overviews the data.
• README.md this, contains general repository information and necessary citations should one use research/data from this repository.

Misc. Files

• project_plan.md is the repository's initial purpose and highlights a road map of goals, subject to change.
• LICENSE.md is this repository's license, GNU General Public License v3.0

Subdirectories

• sample_data/ contains sample datasets used in this research. Any dataset originally made by me is in full, this includes: hollow_sample.pkl.
• scripts/ contains any full .py scripts I made during this research, mostly parsers. Some might not have been used (... or completed...).
• notebooks/ contains any .ipynb Jupyter Notebook files I made during this research. As well as two Python packages (notebook_funcs and specific_funcs) used throughout the main research.ipynb notebook (a better view of research.ipynb)
• images/ contains all graphs made in matplotlib during the project. Most graphs are used in the final_report.md.

---

Here's what my fellow classmates said about my project while it was in development!

---

Citations

Dataset Based On

van Stegeren, J., & Theune, M. (2020). Fantastic Strings and Where to Find Them: The Quest for High-Quality Video Game Text Corpora. In Intelligent Narrative Technologies Workshop. essay, AAAI Press.

Data Collected From

Bioware. (2003). Star Wars: Knights of the Old Republic (PC Version) [Video Game]. LucasArts.

Torchlight II (PC Version) [Video Game]. (2012). Runic Games.

The Elder Scrolls I-V and The Elder Scrolls Online (PC Versions) [Video Games]. (1994-2014). Bethesda Softworks.

Hollow Knight (PC Version) [Video Game]. (2017). Team Cherry.