Research on Methods of Microblogging Sentiment Feature Extraction Based on Dependency Parsing

DOI

10.2991/isrme-15.2015.120How to use a DOI?

Keywords

Microblogging; Dependency Parsing; Opinion Word Expansion; Sentiment Feature Extraction

Abstract

Microblogging emotional elements extraction recall rate is extremely low without opinion words expansion. Aiming at the feature extraction of Microblogging sentiment, a sentiment feature extraction method based on dependency parsing for the Microblogging emotional has been proposed in this paper, abbreviated as MSFE_DP. The specific steps are as follows: First, the existing opinion words were expanded to build a special emotional thesaurus. Second, according to the six dependencies modes of emotional words and evaluation objects, evaluation units were identified and extracted automatically. Finally, a complete evaluation object was obtained in combination with the evaluation object merging algorithm. Through participating in NLP&CC Chinese Microblogging emotional public evaluation, MSFE_DP took the third place among the 22 approaches in the evaluation tasks, which indicates that our method is effective.

Copyright

© 2015, 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  - Yonggan Li
AU  - Xueguang Zhou
AU  - Wei Guo
AU  - Huanguo Zhang
PY  - 2015/04
DA  - 2015/04
TI  - Research on Methods of Microblogging Sentiment Feature Extraction Based on Dependency Parsing
BT  - Proceedings of the 2015 International Conference on Intelligent Systems Research and Mechatronics Engineering
PB  - Atlantis Press
SP  - 581
EP  - 589
SN  - 1951-6851
UR  - https://doi.org/10.2991/isrme-15.2015.120
DO  - 10.2991/isrme-15.2015.120
ID  - Li2015/04
ER  -