Title :
Comparative opinion sentences identification and elements extraction
Author :
Chengxiang Liu ; Ruifeng Xu ; Jie Liu ; Peng Qu ; He Wang ; Chengtian Zou
Author_Institution :
Key Lab. of Network Oriented Intell. Comput., Harbin Inst. of Technol., Shenzhen, China
Abstract :
This paper presents a subsystem for analyzing the comparative opinion sentences. This subsystem consists of three modules. Firstly, rule-based and CSR-based method is developed to identify comparative sentences, respectively. Secondly, in opinion element extraction module, CRFs model is applied to label elements. Finally, in the polarity determination module, some heuristic rules are complied to classify different types of comparative sentences. The evaluations on COAE2012 dataset show that the proposed analysis subsystem achieves a good result.
Keywords :
information retrieval; knowledge based systems; pattern classification; COAE2012 dataset; CSR-based method; classical sequential rules; comparative opinion sentences identification; heuristic rules; opinion element extraction module; polarity determination module; rule-based method; Abstracts; Comparative relations extraction; Comparative sentences; Opinion analysis;
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2013 International Conference on
Conference_Location :
Tianjin
DOI :
10.1109/ICMLC.2013.6890903
