topic-clustering

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.

AgendaScope 观澜 · 全球议程设置监控平台：172 国 408 主流媒体实时采集，议题聚类/议程溯源/50精品监控对象社交图谱（每边带新闻证据）/数据开放API；L0-L3 结构化数据库 + 处理状态机 + 分布式任务队列，云端 2C2G 仅做存储与展示，本地算力机做采集与计算。

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

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

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

텍스트 마이닝을 이용한 KEI 연구동향 분석

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

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

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

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

Subtopic clustering for scientific literature, adapted from the Knowledge Navigator project: searches NASA ADS/SciX, embeds papers with OpenAI, clusters subtopics, and generates outlines.

Quora Keyword Optimization Bot SEO-driven

Olivia Rodrigo Album Analysis

SEO Keyword Clustering Tool - Group keywords into topic clusters

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.

A Python-based data collection and analysis project that queries a news API for oil-related headlines and applies statistical and machine learning techniques to explore public attention around oil.