Prior Polarity Dictionary Derived from SentiWordNet based on Random Forest Algorithm

DOI

10.2991/amcce-17.2017.145How to use a DOI?

Keywords

Sentiment Analysis; Sentiment Strength; Support Vector Regression; Random Forest

Abstract

The prior polarity of words, as a challenging problem, can make great contribution to the sentiment analysis task. In this paper, we propose a method to generate the prior polarity dictionary based on Random Forest (RF) learning algorithm. We compare the proposed approach with the previous methods. The experimental results show that it is better than the state-of-art Support Vector Regression (SVR) method and it can gain better performance.

Copyright

© 2017, 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  - Xiaobin Li
AU  - Yongquan Dong
AU  - Gai-Ge Wang
AU  - Mo Hou
PY  - 2017/03
DA  - 2017/03
TI  - Prior Polarity Dictionary Derived from SentiWordNet based on Random Forest Algorithm
BT  - Proceedings of the 2017 2nd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 2017)
PB  - Atlantis Press
SP  - 818
EP  - 824
SN  - 2352-5401
UR  - https://doi.org/10.2991/amcce-17.2017.145
DO  - 10.2991/amcce-17.2017.145
ID  - Li2017/03
ER  -