biolab / biolab/orange3-text

Topic Modeling: show word weights

Open
#700 0 comments 0 reactions 0 assignees View on GitHub
enhancement
Dominant language
Python
Stars
134
Forks
86
Avg merge
6d 5h
Merged PRs (30d)
1

Description

**Is your feature request related to a problem? Please describe.**
When looking at the results of topic modeling, it is unclear from the image what weights are assigned to each word.

**Describe the solution you'd like**
Show weights in some sensible way. Perhaps with different levels of bold? Colors (shades of grey)? Sizes (probably not)?

**Describe alternatives you've considered**
Ok, one can observe the weights in the Data Table, but this requires another widget and parallel windows. It would be nice to have this information directly in the widget.

**Additional context**
Some words have very low weights so it is not entirely clear how to interpret a topic unless one knows the weights.

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by locating the topic modeling widget and reviewing how its image is generated. Compare the word weights shown in the Data Table with the widget’s current visualization, then determine a readable visual encoding for those weights. Done means the widget communicates low and high word weights directly without requiring a separate Data Table.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
data-visualization, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.