Aspect-specific polarity-aware summarization of online reviews

Authors:
Gaoyan Ou;Wei Chen;Peng Liu;Tengjiao Wang;Dongqing Yang;Kai Lei;Yueqin Liu
Affiliations:
Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China,School of Electronics Engineering and Computer Science, Peking University, Beijing, China;Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China,School of Electronics Engineering and Computer Science, Peking University, Beijing, China;Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China,School of Electronics Engineering and Computer Science, Peking University, Beijing, China;Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China,School of Electronics Engineering and Computer Science, Peking University, Beijing, China;Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China,School of Electronics Engineering and Computer Science, Peking University, Beijing, China;The Shenzhen Key Lab for Cloud Computing Technology and Applications (SPCCTA), Peking University Shenzhen Graduate School, Shenzhen, China;Department of Information Science and Technology, University of International Relations, Beijing, China
Venue:
WAIM'13 Proceedings of the 14th international conference on Web-Age Information Management
Year:
2013

Citing 13
Cited 0

Mining and summarizing customer reviews

Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
Seeing stars: exploiting class relationships for sentiment categorization with respect to rating scales

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
OPINE: extracting product features and opinions from reviews

HLT-Demo '05 Proceedings of HLT/EMNLP on Interactive Demonstrations
Multi-facet Rating of Product Reviews

ECIR '09 Proceedings of the 31th European Conference on IR Research on Advances in Information Retrieval
A novel lexicalized HMM-based learning framework for web opinion miningNOTE FROM ACM: A Joint ACM Conference Committee has been determined that the authors of this article violated ACM's publication policy on simultaneous submissions. Therefore ACM has shut off access to this paper.

ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Joint sentiment/topic model for sentiment analysis

Proceedings of the 18th ACM conference on Information and knowledge management
An unsupervised aspect-sentiment model for online reviews

HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Hierarchical sequential learning for extracting opinions and their attributes

ACLShort '10 Proceedings of the ACL 2010 Conference Short Papers
Jointly modeling aspects and opinions with a MaxEnt-LDA hybrid

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Extracting opinion targets in a single- and cross-domain setting with conditional random fields

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Opinion digger: an unsupervised opinion miner from unstructured product reviews

CIKM '10 Proceedings of the 19th ACM international conference on Information and knowledge management
Aspect and sentiment unification model for online review analysis

Proceedings of the fourth ACM international conference on Web search and data mining
Aspect extraction through semi-supervised modeling

ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

With the popularity of various social media platforms, the number of online reviews towards different products and services grows dramatically. Discovering sentiments from online reviews becomes an important and challenging task in sentiment analysis. Current methods either extract aspects without separating aspects and sentiments, or extract aspects and sentiments without separating sentiments according to their polarities. In this paper, we propose two novel probabilistic generative models (APSM and ME-APSM) to extract aspects and aspect-specific polarity-aware sentiments from online reviews. We applied our models to two data sets with three different experiments. Experimental results show that APSM and ME-APSM models can extract aspects and polarity-aware sentiments well. For the sentiment classification task, our models outperform other generative models and come close to supervised classification methods.