Using Complex Network Model for Online Comment Target Extraction and Identification in Opinion Mining

DOI

10.2991/aeecs-18.2018.47How to use a DOI?

Keywords

Online comments, Complex network, Opinion mining, Shortest path.

Abstract

Identification on the comment target contained in online comments plays a guiding role in opinion mining and sentiment analysis. This paper proposes a Directed-Weighted-Network-based model for modeling online comments, which aggregates important information from numerous comments as a whole object for research. Based on this network model, this paper further studies a candidate comment target set extraction algorithm based on network statistical features and an implement comment target identification algorithm for the comments containing no explicit comment target. A group of empirical experiments on public available English product reviews dataset and manually annotating Chinese news comments dataset are conducted. Experiment results show that the proposed algorithms can achieve satisfactory precision for comment target set extraction and comment target identification. It also shows that the proposed complex network model well captures key features from comment sets.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Tao Xu
PY  - 2018/03
DA  - 2018/03
TI  - Using Complex Network Model for Online Comment Target Extraction and Identification in Opinion Mining
BT  - Proceedings of the 2018 2nd International Conference on Advances in Energy, Environment and Chemical Science (AEECS 2018)
PB  - Atlantis Press
SP  - 278
EP  - 284
SN  - 2352-5401
UR  - https://doi.org/10.2991/aeecs-18.2018.47
DO  - 10.2991/aeecs-18.2018.47
ID  - Xu2018/03
ER  -