Biterm Topic Model

Cluster multilingual search terms captured from different time windows into semantically relevant topics.

古诗词爬虫和文本挖掘，含13个朝代的3万多条诗人数据、85万多条诗词数据，包括主题聚类、相关诗词推荐、藏头诗生成、诗词翻译等算法实现

100% client-side entity-based topic clustering tool. ML models run in your browser — extract entities, resolve to Wikidata, visualize as knowledge graph.

Master's thesis project, combining topic clustering, sentiment analysis, optimisation and stock trading RNN's

Con-S2V: A Generic Framework for Incorporating Extra-Sentential Context into Sen2Vec

Contains a content-based recommendation system of scraped arXiv articles.

텍스트 마이닝을 이용한 KEI 연구동향 분석

Investigative narrative dashboard for semantic search, trend analysis, topic clustering, and network exploration over social media datasets.

Real-time news intelligence - multi-source feeds, auto-clustered by topic and sentiment-scored as it happens.

Exploring and benchmarking chunking methods for Retrieval-Augmented Generation (RAG), including fixed-size, recursive, sliding, semantic, and hybrid chunking strategies.

Quora Keyword Optimization Bot SEO-driven

CX‑360 Insight Engine uses LLM‑powered RAG, sentiment analysis, and topic clustering to transform raw customer feedback into actionable insights. It identifies themes, names clusters, analyzes sentiment trends, and generates business recommendations through an interactive Streamlit dashboard.

Olivia Rodrigo Album Analysis

SEO Keyword Clustering Tool - Group keywords into topic clusters

Data exploration scripts for oss4geo.org based on text embeddings for semantic search and topic clustering based on dimensionality reduction

Lyric generation with MLM and topic detection with FastText

Publication network analyser - co-author graphs, citation trends, topic clusters from Google Scholar

Aggregates AI news, filters by relevance, and sends structured multilingual summaries with push notifications