https://github.com/soodoku/speech-learn
Modeling Relationship Between Congressional Speech and Ideology
https://github.com/soodoku/speech-learn
ideology nlp speech-data
Last synced: about 1 year ago
JSON representation
Modeling Relationship Between Congressional Speech and Ideology
- Host: GitHub
- URL: https://github.com/soodoku/speech-learn
- Owner: soodoku
- License: mit
- Created: 2015-09-13T15:56:28.000Z (almost 11 years ago)
- Default Branch: master
- Last Pushed: 2023-11-13T20:03:47.000Z (over 2 years ago)
- Last Synced: 2024-10-11T12:14:46.851Z (over 1 year ago)
- Topics: ideology, nlp, speech-data
- Language: Python
- Size: 52.7 KB
- Stars: 1
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: ReadMe.md
- License: License.md
Awesome Lists containing this project
README
### Speech Learn: Model Relationship Between Congressional Speech and Ideology
This is an example for how to use text as data.
#### Steps
1. Using the Sunlight Foundation Capitol Words API, [Download the Congressional Speech Data](scripts/capitol_speech.py)
2. Optional (also part of model): [Clean text data using Python](https://github.com/soodoku/text-as-data/tree/master/preprocess_csv)
3. [Merge speech data with DW-Nominate data from Voteview](scripts/capitol_vote.R)
4. [Model](scripts/capitol_words.md)
#### Suggested Reading
1. See [What Drives Media Slant (pdf)](http://web.stanford.edu/~gentzkow/research/biasmeas.pdf)
2. [A Measure of Media Bias (pdf)](http://www.sscnet.ucla.edu/polisci/faculty/groseclose/pdfs/MediaBias.pdf)
#### License
Scripts are released under the [MIT License](License.md).