Presentation
A Knowledge-Rich Approach to Feature-Based Opinion Extraction from Product Reviews
Author/s | Cruz Mata, Fermín
![]() ![]() ![]() ![]() ![]() ![]() ![]() Troyano Jiménez, José Antonio ![]() ![]() ![]() ![]() ![]() ![]() ![]() Enríquez de Salamanca Ros, Fernando ![]() ![]() ![]() ![]() ![]() ![]() ![]() Ortega Rodríguez, Francisco Javier ![]() ![]() ![]() ![]() ![]() ![]() ![]() García Vallejo, Carlos Antonio |
Department | Universidad de Sevilla. Departamento de Lenguajes y Sistemas Informáticos |
Publication Date | 2010 |
Deposit Date | 2020-07-09 |
Published in |
|
ISBN/ISSN | 978-1-4503-0386-6 |
Abstract | Feature-based opinion extraction is a task related to infor-
mation extraction, which consists of extracting structured
opinions on features of some object from reviews or other
subjective textual sources. Over the last ... Feature-based opinion extraction is a task related to infor- mation extraction, which consists of extracting structured opinions on features of some object from reviews or other subjective textual sources. Over the last years, this prob-lem has been studied by some researchers, generally in an unsupervised, domain-independent manner. As opposed to that, in this work we propose a rede nition of the problem from a more practical point of view, and describe a domain- speci c, resource-based opinion extraction system. We fo-cus on the description and generation of those resources, and brie y report the extraction system architecture and a few initial experiments. The results suggest that domain-speci c knowledge is a valuable resource in order to build precise opinion extraction systems. |
Citation | Cruz Mata, F., Troyano Jiménez, J.A., Enríquez de Salamanca Ros, F., Ortega Rodríguez, F.J. y García Vallejo, C.A. (2010). A Knowledge-Rich Approach to Feature-Based Opinion Extraction from Product Reviews. En SMUC 2010: 2nd international workshop on Search and mining user-generated contents (13-20), Toronto, ON, Canada: ACM. |
Files | Size | Format | View | Description |
---|---|---|---|---|
A knowledge-rich approach to ... | 1.102Mb | ![]() | View/ | |