TechPrufer
Get started
Cohere
Cohere logoCohere · Feature trail

Topic Modeling with BERTopic

3 posts · Mar 2024 – Mar 2025

What this trail covers

This post introduces topic modeling capabilities using the BERTopic library, enabling users to discover and analyze underlying themes within their data. It details the integration of BERTopic with Cohere's language AI models to enhance the accuracy and relevance of topic extraction, particularly for unstructured text data. The approach leverages advanced embedding techniques and clustering algorithms to group similar documents and identify representative topics. This post specifically applies the technique to analyze 10,000 Hacker News posts.

All Cohere trails
  1. Topic Modeling with BERTopic - Talking Language AIThis post details the technical implementation of an AI-powered Magic the Gathering card generator, focusing on prompt engineering, data preparation, and model fine-tuning to produce game-specific content. It leverages BERTopic for topic modeling to discover and analyze themes within the data, enhancing the accuracy and relevance of topic extraction for unstructured text. The approach integrates BERTopic with Cohere's language AI models, utilizing advanced embedding techniques and clustering algorithms to group similar documents and identify representative topics.
  2. Combing For Insight in 10,000 Hacker News Posts With Text ClusteringThis post details the application of BERTopic for topic modeling on a large dataset of 10,000 Hacker News posts. It describes the process of using Cohere's embedding models to generate document embeddings, followed by BERTopic's clustering and topic representation techniques. The post highlights the challenges of handling a large corpus and the insights gained from identifying key themes within the data.
  3. What’s Trending in AI — Topic Modeling of AI Papers in 2022This post details the application of BERTopic for topic modeling on a dataset of AI research papers from 2022. It outlines the process of using Cohere's embedding models to generate document embeddings, followed by BERTopic's clustering and topic representation techniques to identify key themes and trends within the AI research landscape. The analysis reveals trending topics such as 'Agentic AI', 'LLM Inference', and 'RAG', providing insights into the evolution of AI research.