MaartenGr / MaartenGr/BERTopic

Reproducibility issue in Guided Topic Modeling

Open
#2,277 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

### Have you searched existing issues? 🔎

- [x] #2278

### Desribe the bug

Hi,
I'm running a topic model and passing a seed_topic_list. This helps me generate more meaningful topics, but I cannot reproduce the model.
UMAP's random_state is fixed. This doesn't happen when seed_topic_list is not passed, so I assume it's related to this parameter.
I wonder why this happens and if it's intrinsic to the method. I couldn't find related info, so I'd appreciate some insight into this.
Best,

### BERTopic Version

0.16.4

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 Guided Topic Modeling entry point and reproduce the issue using seed_topic_list with UMAP's fixed random_state, comparing it with a run without seed_topic_list. Confirm whether repeated runs produce different models and document the reproducibility behavior for BERTopic 0.16.4.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.