Week 2 Deliverable: From Raw Text to Visual Patterns
Course: Topical Reading: Digital Humanities (BA3 Korean Studies)
Date: October 17
Instructors: Aron van der Pol & Steven Denney
Objective
Recreate the in-class DEMO (Oct 17) workflow to understand how preprocessing affects text representation and visualization in Orange Data Mining (ODM).
Tasks
- Replicate the DEMO workflow
- Import the provided
.csvcorpus. - Apply basic preprocessing and other steps in ODM.
- Create a Word Cloud and a Bar Chart of Word Frequencies.
- For the bar chart, select one word of personal or analytical interest and explore its relative frequency.
- Import the provided
- Document your workspace
- Screenshot your Orange canvas showing the full workflow:
- Screenshot or export both the Word Cloud and Bar Chart outputs.
- Write your reflection (
README.md)- Explain briefly what you did, why you did it, and what you learned about preprocessing and visualization.
- Around 200 words is fine. You can write more.
- Save your .ows file (this is your ODM file/workflow).
Deliverables
Place the following files in your GitHub repo folder for week02 assignment:
Folder structure:
/week02/
│
├── workflow_screenshot.png
├── wordcloud.png
├── barchart.png
├── week02.ows
└── README.md
Optional (R Track)
For students in the R Programming extension, complete:
DataCamp – Introduction to Text Analysis in R
- Module 1: Wrangling Text
- Module 2: Visualizing Text
R track assignments are due before the next class.