Domain Dependent Product Feature and Opinion Extraction Based on E-Commerce Websites. Chapter 25

Bartłomiej Twardowski , Piotr Gawrysiak

Abstract

The rapid growth of the Internet and social web communities has changed on-line merchandising. Opinions expressed on websites by the customers became useful information for new customers and product manufacturers. Opinion mining techniques started to be attractive as a method for processing user generated content with sentiment payload. Presented approach uses product reviews from e-commerce websites for the product feature opinion mining task. Manual data annotation process is avoided by fully automated building training data corpus. As a classifier CRF model is employed. Proof of concept on Polish e-commerce website was performed. Experiment has shown promising results.
Author Bartłomiej Twardowski (FEIT / IN)
Bartłomiej Twardowski,,
- The Institute of Computer Science
, Piotr Gawrysiak (FEIT / IN)
Piotr Gawrysiak,,
- The Institute of Computer Science
Pages261-270
Book Zgrzywa Aleksander, Choroś Kazimierz, Siemiński Andrzej (eds.): Multimedia and Internet Systems: Theory and Practice, Advances in Intelligent Systems and Computing, vol. 183, 2013, Heidelberg New York Dordrecht London, Springer-Verlag, ISBN 978-3-642-32334-8, 272 p., DOI:10.1007/978-3-642-32335-5
wstep.pdf / 106.85 KB / No licence information
DOIDOI:10.1007/978-3-642-32335-5_25
ProjectDevelopment of new methods and algorithms in the following areas: computer graphics, artificial intelligence, and information systems; and distributed systems. Project leader: Rybiński Henryk, , Phone: +48 22 234 7731, start date 26-07-2011, planned end date 31-12-2011, end date 30-11-2012, II/2011/DS/1, Completed
WEiTI Działalność statutowa
Languageen angielski
Score (nominal)0
ScoreMinisterial score = 0.0, 02-02-2020, MonographChapterAuthor
Publication indicators WoS Citations = 0
Citation count*
Cite
Share Share

Get link to the record


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back
Confirmation
Are you sure?