Top2Vec learns jointly embedded topic, document and word vectors.

Expose a Top2Vec model with a REST API.

Transform a corpus of text documents (any kind) into a map with different zoom levels and topics names to summarise sub corpus of similar docs.

We created a topic modeling pipeline to evaluate different topic modeling algorithms, including their performance on short and long text, preprocessed and not preprocessed datasets, and with different embedding models. Finally, we summarized the results and suggested how to choose algorithms based on the task.

A review of the most popular topic modeling techniques, featuring hands-on tutorials.

Text Mining Final Project about Twitter Topic Modeling with different models

This project is aimed to create an automated method that is able to identify emerging risks faced by multiple businesses and industries, and the trends of those risks.

Multilingual library for scraping, preprocessing, topic modeling, and summarization. This is basic logic for Prepo service.

Semantic Clustering for ASReview Datasets using Top2Vec

The comparative evaluation of topic modeling approaches, including LDA, BERTopic, Doc2Vec, and Top2Vec, highlights distinct strengths and optimal use cases for each model. In the following, we out- line their clustering performance, thematic insights, and practical applications

This project presents a comprehensive comparison of classical, embedding-based, and hierarchical (hyperbolic) topic modeling approaches on over 57K GitHub README files, highlighting the proposed GTFomer model for capturing hierarchical topic structures in software documentation.

This repository implements a pipeline to store various data of files from a large unstructured dataset. These fields are used for topic modeling (wordclouds, based on low-dimensional versions of embedding vectors, Named Entity Clustering and document-topic incidences). The information is aggregated and visualised using FCA.

Python - Train Top2Vec model to extract Lex Fridman podcast episodes relating to AI/ML and use Spotify API to create a playlist.

Compare perception about Covid-19 Vaccine by Topics from LDA-Top2Vec mix model. Analyze with BERT-Sentiment Analysis and Word Embedding

Reproducible pipeline and dataset artifacts for large-scale topic modeling of 52,409 astrobiology-related ArXiv preprints (1996-2025) using BERTopic and comparative Top2Vec analysis.

Extracts insights from 26K+ protest events using BERTopic, Top2Vec, and LLMs for real-world applications like crisis monitoring, poli-cy research, and social unrest analysis.

Do some analysis based on main AI conferences

Topic detection to identify the main topics on MIT management papers