License: Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported license (CC BY-NC-ND 3.0)
When quoting this document, please refer to the following
DOI: 10.4230/OASIcs.ICCSW.2012.56
URN: urn:nbn:de:0030-drops-37653
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2012/3765/
Go to the corresponding OASIcs Volume Portal

Ginsca, Alexandru Lucian

Fine-Grained Opinion Mining as a Relation Classification Problem

pdf-format:
10.pdf (0.5 MB)

Abstract

The main focus of this paper is to investigate methods for opinion extraction at a more detailed level of granularity, retrieving not only the opinionated portion of text, but also the target of that expressed opinion. We describe a novel approach to fine-grained opinion mining that, after an initial lexicon based processing step, treats the problem of finding the opinion expressed towards an entity as a relation classification task. We detail a classification workflow that combines the initial lexicon based module with a broader classification part that involves two different models, one for relation classification and the other for sentiment polarity shift identification. We provided detailed descriptions of a series of classification experiments in which we use an original proximity based bag-of-words model. We also introduce a new use of syntactic features used together with a tree kernel for both the relation and sentiment polarity shift classification tasks.

BibTeX - Entry

@InProceedings{ginsca:OASIcs:2012:3765,
  author =	{Alexandru Lucian Ginsca},
  title =	{{Fine-Grained Opinion Mining as a Relation Classification Problem}},
  booktitle =	{2012 Imperial College Computing Student Workshop},
  pages =	{56--61},
  series =	{OpenAccess Series in Informatics (OASIcs)},
  ISBN =	{978-3-939897-48-4},
  ISSN =	{2190-6807},
  year =	{2012},
  volume =	{28},
  editor =	{Andrew V. Jones},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2012/3765},
  URN =		{urn:nbn:de:0030-drops-37653},
  doi =		{10.4230/OASIcs.ICCSW.2012.56},
  annote =	{Keywords: Opinion Mining, Opinion Target Identification, Syntactic Features}
}

Keywords: Opinion Mining, Opinion Target Identification, Syntactic Features
Collection: 2012 Imperial College Computing Student Workshop
Issue Date: 2012
Date of publication: 09.11.2012

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI