Uses topic modeling to identify context between follower relationships of Twitter users

This repo contains unsupervised models including the Latent Dirichlet Allocation (LDA) model applied to a corpus of research papers and a clustering analysis applied to customer segmentation.

Drake Analysis: a deeper look into the discography of Canada's Rap King using various NLP techniques.

Topic modeling for NYT articles.

workflow for topic modeling a personal library of PDFs

This project contains the data, code and results used in the paper: Denter, N., Seeger, F., & Moehrle, M. G. (2022). How can Blockchain technology support patent management? A systematic literature review. International Journal of Information Management, Article 102506. Advance online publication. https://doi.org/10.1016/j.ijinfomgt.2022.102506.

Multiclass Intent Classification using MLP, LSTM, and BERT (subtask: Topic Modelling).

Python Notebooks for Collecting Tweets and Analyze their text using various text classification and clustering techniques

React Component for LDAvis

E-Commerce Comment Classification with Logistic Regression and LDA model

A Project on Topic Modeling using alogoriths like LSA/LSI, LDA, NMF on RACE dataset

Automatic Keyphrase Extraction from Russian-Language Scholarly Papers in Computational Linguistics

Topic modeling on tweets from users in India over a 2-year period to discover trending topics and discussions

Topic Modelling with LDA on Journalistic Turkish Texts

기관 협업 공동 연구(23.08~12) - 한국기초과학지원연구원(Korea Basic Science Institute)

Discovering latent features in restaurant reviews using Topic Modeling

This repo contains a demonstration of the Latent Dirichlet Allocation Model (LDA) for topic modelling using Gensim Package, and pyLDAvis to visualize the LDA topics.

A Jupyter notebook analyzing the major reasons for Tesla order cancellation and how Elon Musk's tweets correlate with order cancellation.

Extracting Topics according to relevance using LDA

A complete end-to-end system for document topic modeling and clustering using Latent Dirichlet Allocation (LDA) and KMeans. Features auto-tuned models, real-time predictions, rich visualizations (pie chart, word cloud, pyLDAvis), and a responsive Streamlit app for exploring insights from raw or uploaded text documents.