Abstract
The number of opinions and reviews about different products and services is growing online. Users frequently look for important aspects of a product or service in the reviews. Usually, they are interested in semantic (i.e., sentiment-oriented) aspects. However, extracting semantic aspects with supervised methods is very expensive. We propose a domain independent unsupervised model to extract semantic aspects, and conduct qualitative and quantitative experiments to evaluate the extracted aspects. The experiments show that our model effectively extracts semantic aspects with correlated top words. In addition, the conducted evaluation on aspect sentiment classification shows that our model outperforms other models by 5-7% in terms of macro-average F1.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - IEEE International Conference on Data Mining, ICDM |
| Pages | 816-821 |
| Number of pages | 6 |
| DOIs | |
| Publication status | Published - 2012 Dec 1 |
| Event | 12th IEEE International Conference on Data Mining, ICDM 2012 - Brussels, Belgium Duration: 2012 Dec 10 → 2012 Dec 13 |
Other
| Other | 12th IEEE International Conference on Data Mining, ICDM 2012 |
|---|---|
| Country | Belgium |
| City | Brussels |
| Period | 12/12/10 → 12/12/13 |
Fingerprint
Keywords
- Aspect discovery
- Opinion mining
- Sentiment analysis
- Topic model
ASJC Scopus subject areas
- Engineering(all)
Cite this
Semantic aspect discovery for online reviews. / Alam, Md Hijbul; Lee, Sang-Geun.
Proceedings - IEEE International Conference on Data Mining, ICDM. 2012. p. 816-821 6413739.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Semantic aspect discovery for online reviews
AU - Alam, Md Hijbul
AU - Lee, Sang-Geun
PY - 2012/12/1
Y1 - 2012/12/1
N2 - The number of opinions and reviews about different products and services is growing online. Users frequently look for important aspects of a product or service in the reviews. Usually, they are interested in semantic (i.e., sentiment-oriented) aspects. However, extracting semantic aspects with supervised methods is very expensive. We propose a domain independent unsupervised model to extract semantic aspects, and conduct qualitative and quantitative experiments to evaluate the extracted aspects. The experiments show that our model effectively extracts semantic aspects with correlated top words. In addition, the conducted evaluation on aspect sentiment classification shows that our model outperforms other models by 5-7% in terms of macro-average F1.
AB - The number of opinions and reviews about different products and services is growing online. Users frequently look for important aspects of a product or service in the reviews. Usually, they are interested in semantic (i.e., sentiment-oriented) aspects. However, extracting semantic aspects with supervised methods is very expensive. We propose a domain independent unsupervised model to extract semantic aspects, and conduct qualitative and quantitative experiments to evaluate the extracted aspects. The experiments show that our model effectively extracts semantic aspects with correlated top words. In addition, the conducted evaluation on aspect sentiment classification shows that our model outperforms other models by 5-7% in terms of macro-average F1.
KW - Aspect discovery
KW - Opinion mining
KW - Sentiment analysis
KW - Topic model
UR - http://www.scopus.com/inward/record.url?scp=84874104662&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84874104662&partnerID=8YFLogxK
U2 - 10.1109/ICDM.2012.65
DO - 10.1109/ICDM.2012.65
M3 - Conference contribution
AN - SCOPUS:84874104662
SN - 9780769549057
SP - 816
EP - 821
BT - Proceedings - IEEE International Conference on Data Mining, ICDM
ER -