15 lines
737 B
Markdown
15 lines
737 B
Markdown
# 4 Chan Webscraper, Version 2
|
|
|
|
Consider doing your own data analysis. If you save your CSV, and make a pull request, I can add it to this repository for plotting word usage changes over time.
|
|
|
|
**Highlights:**
|
|
|
|
- Written in R.
|
|
- Objective: Datamining text, and displaying word frequencies.
|
|
- Uses the following libraries: rvest, tidyverse, tidytext, ggplot2, wordcloud.
|
|
- If you don't have these installed in your RStudio software, then install them.
|
|
- After installing, and running this script into your RStudio IDE, you can download all posts.
|
|
- Downloaded posts are then manipulated to show word frequencies.
|
|
- Differs from V1 by scraping all replies to OP, and has a much larger noise filter.
|
|
- Sentiment analysis is also performed.
|