The Leiden Weibo Corpus is powered by:

• Amazon Web Services
• Go & SQLite, behind Caddy, on Amazon Linux
• Leaflet & OpenStreetMap
• Gentium by SIL International

Data sources:

• Sina Weibo API
• CC-CEDICT (Mandarin dictionary data)
• Google Geocoding API
• Google Translate

Java NLP tools from the Stanford Natural Language Processing Group:

• Chinese Word Segmenter (2011-09-14)
• POS tagger (3.1.0, 2012-01-06)
• Parser (2.0, 2012-02-03)

We owe a great debt of gratitude to everyone who contributed to these projects.