Title: Feature-opinion pair identification method in two-stage based on dependency constraints

Authors: Shulong Liu; Xudong Hong; Zhengtao Yu; Hongying Tang; Yulong Wang

Addresses: School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunan 650500, China ' School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunan 650500, China ' School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunan 650500, China ' School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunan 650500, China ' School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunan 650500, China

Abstract: Feature-opinion pair identification includes opinion words, opinion targets extraction and their relations identification, is important for analysis online reviews. In this paper, we propose a feature-opinion pair identification method in two-stage based on dependency constraints according to the relationship between the identification of feature-opinion pair and dependency constraints. In the first stage, we construct dependency constraints based on the dependency information of words. Then, dependency constraints and seed words are employed to extract opinion words and opinion targets. In the second stage, we use opinion words and opinion targets extracted in the first stage to construct candidate feature-opinion pairs. Thereafter, integrate dependency constraints, location features and part-of-speech features into support vector machine to identify feature-opinion pair. Our experimental result using online reviews demonstrates that the proposed method is effective in the identification of feature-opinion pairs, and the F-score has reached 83.85%.

Keywords: opinion mining; opinion word; opinion target; dependency constraints; feature-opinion pair.

DOI: 10.1504/IJICT.2018.095051

International Journal of Information and Communication Technology, 2018 Vol.13 No.4, pp.454 - 469

Received: 02 Apr 2016
Accepted: 04 Oct 2016

Published online: 21 May 2018 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article