Abstract
The rapid increase of user-generated content (UGC) is a rich source for reputation management of entities, products, and services. Looking at online product reviews as a concrete example, in reviews, customers usually give opinions on multiple attributes of products, therefore the challenge is to automatically extract and cluster attributes that are mentioned. In this paper, we investigate efficient attribute extraction models using a semi-supervised approach. Specifically, we formulate the attribute extraction issue as a sequence labeling task and design a bootstrapped schema to train the extraction models by leveraging a small quantity of labeled reviews and a larger number of unlabeled reviews. In addition, we propose a clustering By committee (CBC) approach to cluster attributes according to their semantic similarity. Experimental results on real world datasets show that the proposed approach is effective.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 279-288 |
| Number of pages | 10 |
| Journal | Frontiers of Computer Science |
| Volume | 8 |
| Issue number | 2 |
| DOIs | |
| State | Published - 2014 |
| Externally published | Yes |
Fingerprint
Keywords
- attribute clustering
- attribute extraction
- opinion mining
ASJC Scopus subject areas
- Computer Science(all)
- Theoretical Computer Science
Cite this
Entity attribute discovery and clustering from online reviews. / Miao, Qingliang; Li, Qiudan; Zeng, Dajun; Meng, Yao; Zhang, Shu; Yu, Hao.
In: Frontiers of Computer Science, Vol. 8, No. 2, 2014, p. 279-288.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Entity attribute discovery and clustering from online reviews
AU - Miao, Qingliang
AU - Li, Qiudan
AU - Zeng, Dajun
AU - Meng, Yao
AU - Zhang, Shu
AU - Yu, Hao
PY - 2014
Y1 - 2014
N2 - The rapid increase of user-generated content (UGC) is a rich source for reputation management of entities, products, and services. Looking at online product reviews as a concrete example, in reviews, customers usually give opinions on multiple attributes of products, therefore the challenge is to automatically extract and cluster attributes that are mentioned. In this paper, we investigate efficient attribute extraction models using a semi-supervised approach. Specifically, we formulate the attribute extraction issue as a sequence labeling task and design a bootstrapped schema to train the extraction models by leveraging a small quantity of labeled reviews and a larger number of unlabeled reviews. In addition, we propose a clustering By committee (CBC) approach to cluster attributes according to their semantic similarity. Experimental results on real world datasets show that the proposed approach is effective.
AB - The rapid increase of user-generated content (UGC) is a rich source for reputation management of entities, products, and services. Looking at online product reviews as a concrete example, in reviews, customers usually give opinions on multiple attributes of products, therefore the challenge is to automatically extract and cluster attributes that are mentioned. In this paper, we investigate efficient attribute extraction models using a semi-supervised approach. Specifically, we formulate the attribute extraction issue as a sequence labeling task and design a bootstrapped schema to train the extraction models by leveraging a small quantity of labeled reviews and a larger number of unlabeled reviews. In addition, we propose a clustering By committee (CBC) approach to cluster attributes according to their semantic similarity. Experimental results on real world datasets show that the proposed approach is effective.
KW - attribute clustering
KW - attribute extraction
KW - opinion mining
UR - http://www.scopus.com/inward/record.url?scp=84897965983&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84897965983&partnerID=8YFLogxK
U2 - 10.1007/s11704-014-3043-8
DO - 10.1007/s11704-014-3043-8
M3 - Article
AN - SCOPUS:84897965983
VL - 8
SP - 279
EP - 288
JO - Frontiers of Computer Science
JF - Frontiers of Computer Science
SN - 2095-2228
IS - 2
ER -