Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/shiyis/politics
The political text ideology classification tool provides a solution to expedite interpreting an author's intentions and subjectivity through quantitative measures.
https://github.com/shiyis/politics
political-analysis political-nlp text-analytics variational-inference
Last synced: about 1 month ago
JSON representation
The political text ideology classification tool provides a solution to expedite interpreting an author's intentions and subjectivity through quantitative measures.
- Host: GitHub
- URL: https://github.com/shiyis/politics
- Owner: shiyis
- License: mit
- Created: 2023-11-13T00:58:34.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-10-29T21:27:42.000Z (about 2 months ago)
- Last Synced: 2024-10-29T23:44:59.196Z (about 2 months ago)
- Topics: political-analysis, political-nlp, text-analytics, variational-inference
- Language: TeX
- Homepage:
- Size: 58.2 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
## P.O.L.I.T.I.C.S. - A Political Opinions, Language, and Ideology Text Interpretation and Classification Solution
This project offers a solution that dynamically measures political subjectivity with Variational Autoencoding methods through quantifying an author's political leaning (their political position gets projected onto a one dimensional scale as an ideal point that ranges from moderate to progressive).
---
### Dynamically Measuring Political Opinions and Subjectivity with VAE
Drawing inspiration from one of the studies conducted on measuring political subjectivity and quantifying author's political stance through variational inference, this project will largely follow [this paper](https://github.com/keyonvafa/tbip) to conduct an ad hoc analysis and unsupervised modeling over political content in the format of tweets for eliciting interpretable results.
A simple EDA (What Is An [Exploratory Data Analysis](https://medium.com/@lamsampathkumar0/eda-exploratory-data-analysis-project-using-python-de90cbf4e128)?) will also be carried out in supporting the final analysis.
---
### Data Collection and Organization
This [repo](https://github.com/shiyis/project-inputs) serves as a sample data collection demo.
(p.s. due to limited permissions of twitter API access, some of the data collected might not be as ideal). The data collection process involves using the Twitter API academic access and building a small tweet retrieving pipeline for the tweets.
---
### Literature Review
Please also check out the [references](https://raw.githubusercontent.com/shiyis/c4fe-tbip/master/references.bib) pertaining to this project. The file includes articles and resources that introduce the sufficient background in order to better understand this particular project.
---
### Final Project Demo
Please check out this [link](https://my-dash-app-ilf47zak6q-uc.a.run.app/) for a final demo. Also check out [dev](https://github.com/shiyis/politics/tree/dev) branch for src code.
Also check out this link for supplementary [docs](https://shiyis.github.io/politics-docs/) for this project.
---
### Privacy and Ethics Disclaimer
This project only explores the open tweets and data retrieved from Twitter API for personal non-commercial use. For a full collection of tweets, please email me at [email protected].