What is the of the dataset you are using (e.g., news, tweets, medical papers)?
In BERTopic, topics are often labeled with an integer ID (e.g., Topic 92) and sometimes a sub-label or cluster identifier (the __2 suffix). 💻 Technical Context: Topic 92 in BERTopic 92__2_zip
The top 10 keywords (e.g., "software, developer, github, python"). What is the of the dataset you are using (e
Are you using or another library like Gensim or Top2Vec ? medical papers)? In BERTopic