DocumentCode :
57084
Title :
Feature Ensemble Plus Sample Selection: Domain Adaptation for Sentiment Classification
Author :
Rui Xia ; Chengqing Zong ; Xuelei Hu ; Cambria, Erik
Author_Institution :
Nanjing Univ. of Sci. & Technol., Nanjing, China
Volume :
28
Issue :
3
fYear :
2013
fDate :
May-June 2013
Firstpage :
10
Lastpage :
18
Abstract :
Domain adaptation problems often arise often in the field of sentiment classification. Here, the feature ensemble plus sample selection (SS-FE) approach is proposed, which takes labeling and instance adaptation into account. A feature ensemble (FE) model is first proposed to learn a new labeling function in a feature reweighting manner. Furthermore, a PCA-based sample selection (PCA-SS) method is proposed as an aid to FE. Experimental results show that the proposed SS-FE approach could gain significant improvements, compared to FE or PCA-SS, because of its comprehensive consideration of both labeling adaptation and instance adaptation.
Keywords :
feature extraction; pattern classification; principal component analysis; FE model; PCA-SS method; PCA-based sample selection; SS-FE approach; domain adaptation problems; feature ensemble plus sample selection; feature reweighting; instance adaptation; labeling adaptation; labeling function; sentiment classification; Adaptation models; Classification; Computational linguistics; Intelligent systems; Natural language processing; Principal component analysis; Text analysis; Adaptation models; Classification; Computational linguistics; Intelligent systems; Natural language processing; Principal component analysis; Text analysis; domain adaptation; instance adaptation; intelligent systems; labeling adaptation; sample selection; sentiment classification;
fLanguage :
English
Journal_Title :
Intelligent Systems, IEEE
Publisher :
ieee
ISSN :
1541-1672
Type :
jour
DOI :
10.1109/MIS.2013.27
Filename :
6461869
Link To Document :
بازگشت