Proceedings of the 2019 International Conference on Electronical, Mechanical and Materials Engineering (ICE2ME 2019)

Research on Sentiment Analysis and Abnormal Feature Extraction Technology Based on Comments Data

Authors
Hui Yan, Xufu Peng, Xiaowan Zhu
Corresponding Author
Xufu Peng
Available Online March 2019.
DOI
10.2991/ice2me-19.2019.20How to use a DOI?
Keywords
basic sentiment dictionary; Micro-Blog sentiment dictionary; sentiment analysis; knapsack model; abnormal text
Abstract

With the promotion of Micro-Blog’s influence, the influence of Micro-Blog public opinion has been continuously strengthened. Therefore, based on the low recognition rate of Micro-Blog sentiment words in the traditional basic sentiment dictionary, this study designed and used the Micro-Blog emotional words to expand the basic emotion dictionary. And the fused dictionary is used to analyze the network comment texts. Moreover, according to the results of sentiment analysis, the abnormal criteria is formulated, then, the classical Knapsack model is used to solve the problem of constructing the abnormal comment text collection. Finally, the effectiveness of the sentiment analysis technology based on Micro-Blog dictionary and the method of extracting abnormal text collection using the backpack model are verified by experiments. The emotional tendency of user comments is grasped from the massive data, so as to understand the user's concern, which realized the important practical significance of the management of Micro-Blog public opinion.

Copyright
© 2019, 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 2019 International Conference on Electronical, Mechanical and Materials Engineering (ICE2ME 2019)
Series
Advances in Engineering Research
Publication Date
March 2019
ISBN
978-94-6252-685-3
ISSN
2352-5401
DOI
10.2991/ice2me-19.2019.20How to use a DOI?
Copyright
© 2019, 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  - Hui Yan
AU  - Xufu Peng
AU  - Xiaowan Zhu
PY  - 2019/03
DA  - 2019/03
TI  - Research on Sentiment Analysis and Abnormal Feature Extraction Technology Based on Comments Data
BT  - Proceedings of the 2019 International Conference on Electronical, Mechanical and Materials Engineering (ICE2ME 2019)
PB  - Atlantis Press
SP  - 90
EP  - 94
SN  - 2352-5401
UR  - https://doi.org/10.2991/ice2me-19.2019.20
DO  - 10.2991/ice2me-19.2019.20
ID  - Yan2019/03
ER  -