drob-xx/TopicTuner
HDBSCAN Tuning for BERTopic Models
When analyzing large sets of text documents to identify key themes and topics, it's common to end up with too many fragmented topics or too many documents left uncategorized. This tool takes your BERTopic model and helps you refine its clustering parameters to get more meaningful topics and ensure more of your documents contribute to those topics. It's designed for data analysts, researchers, and content strategists working with text data.
No commits in the last 6 months.
Use this if you are using BERTopic for topic modeling and are struggling to get a manageable number of relevant topics or find too many of your documents are being ignored.
Not ideal if you need to use a topic modeling algorithm other than BERTopic or if your primary goal is not optimizing topic quality and document assignment.
Stars
52
Forks
3
Language
Python
License
GPL-3.0
Category
Last pushed
Jun 05, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/drob-xx/TopicTuner"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MIND-Lab/OCTIS
OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models...
i-dot-ai/themefinder
A topic modelling Python package for analysing one-to-many question-answer data.
andifunke/topic-labeling
The project proposes a framework to apply topic models on a text-corpus and eventually topic...
bab2min/tomotopy
Python package of Tomoto, the Topic Modeling Tool
bobxwu/TopMost
A Topic Modeling System Toolkit (ACL 2024 Demo)