Extracting semantic entities and events from sports tweets
|Conference paper (help)|
|Extracting semantic entities and events from sports tweets|
|Authors:||Smitashree Choudhury, John Breslin|
|Citation:||Proceedings of the ESWC2011 Workshop on 'Making Sense of Microposts': Big things come in small packages 718 in CEUR Workshop Proceedings : 2011 May|
|Editors:||Matthew Rowe, Milan Stankovic, Aba-Sah Dadzie, Mariann Hardey|
|Meeting:||Making Sense of Microposts|
|Web:||DuckDuckGo Bing Google Yahoo! — Google PDF|
|Article:||Google Scholar PubMed|
|Restricted:||DTU Digital Library|
The researcher collect 3 difference twitter data sets (query: #cricket, #cwc2001, ICC cricket world cup, #cwc11)
The tasks was to extract named entities and micro-events (goal in soccer match, wicket in cricket match) within a sport event tweets. Human annotators extracted events and players from the posts. Person names occure not often as full name, but instead as first name, surname, initials or other variation.
- "Named entities proved to be difficult"
- "Events can be detected with light computation"