Twitter IE is a named entity recognition service specially tuned to use Twitter data. It performs:
* tokenisation, sentence splitting and part-of-speech tagging, using a model trained specifically for Tweets
* normalisation of abbreviations and shortened word forms frequently found in Tweets ("brb", "ttyl", "gr8", "2day", etc.)
* tagging of Twitter-specific entities such as hashtags and @mentions, as well as URLs and emoticons
* general named-entity recognition to identify basic entity types such as Person, Location, Organization, Money amounts, Time and Date expressions, etc.
* mappings of entities discovered in text to reference data from the DBpedia knowledge graph
Acknowledgements: The Twitter analytics service of S4 is based on the TwitIE open source information extraction pipeline by the GATE platform by the University of Sheffield