Intelligence and Visualisation

Aus elib.at
Wechseln zu: Navigation, Suche

Open Data Companies Visualisation of Top 500 Companies working with and/or providing OpenData (https://us-open-data.silk.co/), 2014.

Overview: Processing and Visualisation Tools

eLib.at: See also Tools:Natural Language Processing.

NLP-Pipeline - Software Ideas

Ideas from this presentation

  • Content Management: Apache Jackrabbit / Hadoop
  • Text Extraction: Apache Tika / boilerplate
  • Named-Entity Recognition: Apache uima (nlp pipeline), GATE general architecture for text engineering (Gazetteer approach), Apache openNLP (model, context aware, maximum entropy)
  • Geo-Tags?: GeoNames
  • Clustering/Classification:
  • Indexing: Solr/Lucene (incl. hierarchical synonym sets)

Semantic Annotation and Discovery

Data Extraction

Solr

Manifold Connectors

  • Manifold offers a range of connectors for Apache projects, including Solr. The End-user documentation offers an overview.

Data Mining

Software

Digital Humanities

Rapidminer

Orange Canvas

WEKA and MOA

Apache UIMA and CLEREZZA

Visualisation

D3.js-based

Bookworm (Ngram, Culturomics)

Solr Plugins

Geospatial

Python-based

Datasets

Mirror of Kevin Chai's Blogpost

Blog articles which provide dataset directories

Dataset directories

Data sets for a specific field

Link Analysis / Social Networks

Recommender systems

Forums

Blogs

Wikis

Webpages

Misc


Topic Modeling

Open Source Business Intelligence

Desktop Data Mining / Business Intelligence / Modeling Software

Background & Examples

Innovation in Wien

Plugins

FAQs

  • DataScience Masters: The open-source curriculum for learning Data Science. Foundational in both theory and technologies, the OSDSM breaks down the core competencies necessary to make data useful.
  • Content Detection with R