Data-Science-for-Linguists-2024/Stance-Taking-in-Spontaneous-Speech

Maya Asher's term project

Stance Taking in Spontaneous Speech

By: Maya Asher (they/them)

Contact me at mia83@pitt.edu

Last edit: April 28, 2024

Project description: Using transcripts from the Santa Barbara Corpus of Spoken American English (SBCSAE), I extracted lexical items and discourse markers to examine investment in spontaneous speech. The theoretical background for my study comes from Kiesling (2022).

Directory

• final_report.md is my final report write-up
• reprocessing_sbcsae.ipynb is my main processing code. Since GitHub mangles section links, here's the same notebook through Jupyter's nbviewer
• analyzing_sbcsae.ipynb is where I analyze my data. Here's the nbviewer and here's the output folder: targets_w_context/
• annotations/ includes all of my annotations regarding investment
• figures/
• data_samples/ is a folder of all the data used in my processing/analysis
• progress_report.md includes my progress reports from throughout the term
• file_summary.md is a summary of the transcripts included in my processing/analysis.
• final_presentation.pdf is my final presentation that was presented in class on 4/17/24
• LICENSE.md contains my licensing info
• project_plan.md was my initial project plan
• processing_sbcsae.ipynb is the ugly duckling of the family (aka my first go at processing the sbcsae)...you can ignore it...or check out the nbviewer if you dare

Guestbook

Check out the lounge and add some feedback!