KoBERTopic은 BERTopic을 한국어 데이터에 적용할 수 있도록 토크나이저와 BERT를 수정한 코드입니다.

We present our concept of a new type of Active-Learning for Deep Learning with NLP text classification and experimentally prove its performance against Random Sampling as well as its runtime performance on the Security Threat dataset from CySecAlert. These new Active Learning algorithms are based on Sentence-BERT and BERTopic clustering algorith…

Natural Language Processing with Twitter data

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.

Repository for code and original datasets for MSc Dissertation - University of Sussex 2022

We take on the challenge of combining spatialisation and ML. We propose a Network TD-SOM, which means Network and Self-organised maps of the topic documents. The Master’s theses dataset from NOVA IMS are used as an opportunity to evaluate the performance of Network TD-SOM. We exploit the results to design various kinds of spatialisation dedicate…

BERT-based Topic Modeling on New York Times Headlines (160k rows)

A Quotebank data analysis to build a political party classifier based on quotes, explained with a data story. Includes sentiment analysis, grammatical structure/complexity analysis and topic labeling.

NLP Topic Modeling Techniques (LDA, LSA & BERTopic)

Hierarchical Topic Modeling

Text Mining Final Project about Twitter Topic Modeling with different models

This study aims to analyze the sentiment and identify the main topics discussed in Meta Quest 2 product reviews scraped from the Argos website

A data visualization dashboard powered by Dash framework & Python for Higher Education Institution (HEI) Online Reputation System (Final Year Project)

Celem projektu było wykonanie analizy budżetów partycypacyjnych polskich miast pod kątem istniejących w nich wspólnych tematów, trendów, zależności.

Tool that allows characterizing territorial issues through news processing. It performs topic clustering, sentiment analysis, and data analysis using BERTopic & ChatGPT.

A content-based recommendation system for Hacker News using topic modeling (BERTopic)

BoardTopic is a friendly way to understand your big data. BoardTopic uses state-of-the-art frameworks for topic modeling (BERTopic) and language models to help you analyze and makes sense of your data, no coding required.

Scrape website content and extract topics

This project involved analysing the collected dataset about people experiencing insomnia. This repository contains the code to construct a dataset using the Twitter API, then some data should be annotated with sentiments which is used for training transformer models. The data can be clustered into topics for further analysis with BERTopic.

HDBSCAN Tuning for BERTopic Models