MaartenGr / MaartenGr/BERTopic

UMAP-n_components

Open
#2,340 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
7.8k
Forks
920
Avg merge
22h 24m
Merged PRs (30d)
5

Description

When I used bertopic to process comment data (more than 90,000 comments), I found that when using the default dimension of UMAP to 5 dimensions, even if I adjusted other parameters, a large amount of useful text was classified as outliers (maybe it was my data problem). When I increased the dimension reduction, the situation would be better. Is it reasonable for me to change the dimension reduction next?Thanks!

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the BERTopic and UMAP configuration described in the issue, focusing on the default n_components value of 5 and the reported outliers in a dataset of more than 90,000 comments. Reproduce the behavior if the dataset or a comparable example is available, then determine whether higher-dimensional reduction is expected and what guidance or change would resolve the question.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.