Volltext-Downloads (blau) und Frontdoor-Views (grau)

Predicate Acquisition for Opinion Holder Extraction. A Data-Intensive Approach

  • Opinion holder extraction is one of the most important tasks in sentiment analysis. We will briefly outline the importance of predicates for this task and categorize them according to part of speech and according to which semantic role they select for the opinion holder. For many languages there do not exist semantic resources from which such predicates can be easily extracted. Therefore, we present alternative corpus-based methods to gain such predicates automatically, including the usage of prototypical opinion holders, i.e. common nouns, denoting for example experts or analysts, which describe particular groups of people whose profession or occupation is to form and express opinions towards specific items.

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar


Author:Michael WiegandGND
Parent Title (English):Proceedings des 8. Hildesheimer Evaluierungs- und Retrievalworkshop (HiER 2013), Hildesheim, 25.-26. April 2013
Publisher:Institut für Informationswissenschaft und Sprachtechnologie, Universität Hildesheim
Place of publication:Hildesheim
Editor:Joachim Griesbaum, Ben Heuwing, Josef Ruppenhofer, Katrin Werner
Document Type:Conference Proceeding
Year of first Publication:2013
Date of Publication (online):2019/03/22
Tag:Opinion Mining; Sentimentanalyse
GND Keyword:Computerlinguistik; Information Extraction; Natürliche Sprache; Text Mining
First Page:41
Last Page:50
DDC classes:400 Sprache / 400 Sprache, Linguistik
Open Access?:ja
Licence (German):License LogoCreative Commons - Namensnennung-Weitergabe unter gleichen Bedingungen 3.0 Deutschland