Abstract
The availability of electronic word-of-mouth, online consumer reviews, is increasing rapidly. Users frequently look for important aspects of a product or service in the reviews. They are typically interested in sentiment-oriented ratable aspects (i.e., semantic aspects). However, extracting semantic aspects across domains is challenging. We propose a domain-independent topic sentiment model called Joint Multi-grain Topic Sentiment (JMTS) to extract semantic aspects. JMTS effectively extracts quality semantic aspects automatically, thereby eliminating the requirement for manual probing. We conduct both qualitative and quantitative comparisons to evaluate JMTS. The experimental results confirm that JMTS generates semantic aspects with correlated top words and outperforms state-of-the-art models in several performance metrics.
| Original language | English |
|---|---|
| Pages (from-to) | 206-223 |
| Number of pages | 18 |
| Journal | Information Sciences |
| Volume | 339 |
| DOIs | |
| Publication status | Published - 2016 Apr 20 |
Fingerprint
Keywords
- Aspect discovery
- Opinion mining
- Sentiment analysis
- Topic model
ASJC Scopus subject areas
- Artificial Intelligence
- Software
- Control and Systems Engineering
- Theoretical Computer Science
- Computer Science Applications
- Information Systems and Management
Cite this
Joint multi-grain topic sentiment : Modeling semantic aspects for online reviews. / Alam, Md Hijbul; Ryu, Woo Jong; Lee, Sang-Geun.
In: Information Sciences, Vol. 339, 20.04.2016, p. 206-223.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Joint multi-grain topic sentiment
T2 - Modeling semantic aspects for online reviews
AU - Alam, Md Hijbul
AU - Ryu, Woo Jong
AU - Lee, Sang-Geun
PY - 2016/4/20
Y1 - 2016/4/20
N2 - The availability of electronic word-of-mouth, online consumer reviews, is increasing rapidly. Users frequently look for important aspects of a product or service in the reviews. They are typically interested in sentiment-oriented ratable aspects (i.e., semantic aspects). However, extracting semantic aspects across domains is challenging. We propose a domain-independent topic sentiment model called Joint Multi-grain Topic Sentiment (JMTS) to extract semantic aspects. JMTS effectively extracts quality semantic aspects automatically, thereby eliminating the requirement for manual probing. We conduct both qualitative and quantitative comparisons to evaluate JMTS. The experimental results confirm that JMTS generates semantic aspects with correlated top words and outperforms state-of-the-art models in several performance metrics.
AB - The availability of electronic word-of-mouth, online consumer reviews, is increasing rapidly. Users frequently look for important aspects of a product or service in the reviews. They are typically interested in sentiment-oriented ratable aspects (i.e., semantic aspects). However, extracting semantic aspects across domains is challenging. We propose a domain-independent topic sentiment model called Joint Multi-grain Topic Sentiment (JMTS) to extract semantic aspects. JMTS effectively extracts quality semantic aspects automatically, thereby eliminating the requirement for manual probing. We conduct both qualitative and quantitative comparisons to evaluate JMTS. The experimental results confirm that JMTS generates semantic aspects with correlated top words and outperforms state-of-the-art models in several performance metrics.
KW - Aspect discovery
KW - Opinion mining
KW - Sentiment analysis
KW - Topic model
UR - http://www.scopus.com/inward/record.url?scp=84963820824&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84963820824&partnerID=8YFLogxK
U2 - 10.1016/j.ins.2016.01.013
DO - 10.1016/j.ins.2016.01.013
M3 - Article
VL - 339
SP - 206
EP - 223
JO - Information Sciences
JF - Information Sciences
SN - 0020-0255
ER -