Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Exploiting social media for natural language processing: Bridging the gap between language-centric and real-world applications

: Ponzetto, S.P.

Volltext urn:nbn:de:0011-n-2793413 (69 KByte PDF)
MD5 Fingerprint: c0c8e309399ca8723fc37516633ed288
Erstellt am: 25.2.2014

Association for Computational Linguistics -ACL-:
51st Annual Meeting of the Association for Computational Linguistics, ACL 2013. Proceedings of the Conference Tutorial Abstracts : 4-9 August 2013, Sofia, Bulgaria
Madison, Wisconsin: Omnipress, 2013
Association for Computational Linguistics (ACL Annual Meeting) <51, 2013, Sofia>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IOSB ()

Social media like Twitter and micro-blogs provide a goldmine of text, shallow markup annotations and network structure. These information sources can all be exploited together in order to automatically acquire vast amounts of up-to-date, wide-coverage structured knowledge. This knowledge, in turn, can be used to measure the pulse of a variety of social phenomena like political events, activism and stock prices, as well as to detect emerging events such as natural disasters (earthquakes, tsunami, etc.).
The main purpose of this tutorial is to introduce social media as a resource to the Natural Language Processing (NLP) community both from a scientific and an application-oriented perspective. To this end, we focus on micro-blogs such as Twitter, and show how it can be successfully mined to perform complex NLP tasks such as the identification of events, topics and trends. Furthermore, this information can be used to build high-end socially intelligent applications that tap the wisdom of the crowd on a large scale, thus successfully bridging the gap between computational text analysis and real-world, mission-critical applications such as financial forecasting and natural crisis management.