Proceedings of the 2016 International Conference on Mechatronics Engineering and Information Technology

A Hierarchical ML-kNN Method for Complex Emotion Analysis on Customer Reviews

Authors
Hongwei Qi, Yanquan Zhou, Qi Guo
Corresponding Author
Hongwei Qi
Available Online August 2016.
DOI
10.2991/icmeit-16.2016.5How to use a DOI?
Keywords
Sentiment classification, multi-label learning, kNN, hierarchical.
Abstract

Aim at multi-label sentiments classification of customer reviews. This paper presents a hierarchical ML-kNN algorithm. Different from the traditional ML-kNN algorithm, this algorithm can capture the connection of labels by introducing auxiliary labels. The experimental results show that our proposed approach can improve the performances of multi-label sentiments classification of customer reviews. In addition, due to the effective use of auxiliary information, our algorithm can greatly reduce the interference of noises.

Copyright
© 2016, 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)

Volume Title
Proceedings of the 2016 International Conference on Mechatronics Engineering and Information Technology
Series
Advances in Engineering Research
Publication Date
August 2016
ISBN
10.2991/icmeit-16.2016.5
ISSN
2352-5401
DOI
10.2991/icmeit-16.2016.5How to use a DOI?
Copyright
© 2016, 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/).

Cite this article

TY  - CONF
AU  - Hongwei Qi
AU  - Yanquan Zhou
AU  - Qi Guo
PY  - 2016/08
DA  - 2016/08
TI  - A Hierarchical ML-kNN Method for Complex Emotion Analysis on Customer Reviews
BT  - Proceedings of the 2016 International Conference on Mechatronics Engineering and Information Technology
PB  - Atlantis Press
SP  - 26
EP  - 31
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmeit-16.2016.5
DO  - 10.2991/icmeit-16.2016.5
ID  - Qi2016/08
ER  -