Skip to content

Latest commit

 

History

History
12 lines (11 loc) · 621 Bytes

README.md

File metadata and controls

12 lines (11 loc) · 621 Bytes
Raw

Purposes

Generating data from Twitter, also known as Company X, and applying Stanza sentiment analysis. Keywords for query: 1. "#anzbank" 2. "#anz bank"

Steps

  1. Scraping data about "#anzbank" and "#anz bank" from Twitter by using twscrape library: https://github.com/vladkens/twscrape. twscrape_anz.py Notes: I collected the tweets on 4th September, 2023. Twitter may forbid the usage of twscrape library in the future.
  2. Preprocessing data: preprocess.ipynb
  3. Sentiment analysis by Stanza: stanza_analysis.ipynb
  4. Visualizing: visualize.ipynb
  5. Word frequency analysis: frequency.ipynb