Emotional Analysis Oriented to Short Texts

DOI

10.2991/amcce-18.2018.98How to use a DOI?

Keywords

Emotion analysis, Short text, Weighted word vector.

Abstract

With the development of the mobile Internet, short subjective information such as Weibo comments and product reviews has been rapidly increasing, and massive textual information makes manual management more and more difficult. This paper takes the short text as the research object to analyze the emotion. This paper proposes word vector superposition method and weighted word vector method to extract text features based on word vectors, so that the short text features can be further extracted. In the comparison of the performance of the comment emotion analysis model, the effectiveness of the proposed method is illustrated.

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  - Jiewei Luo
PY  - 2018/05
DA  - 2018/05
TI  - Emotional Analysis Oriented to Short Texts
BT  - Proceedings of the 2018 3rd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 2018)
PB  - Atlantis Press
SP  - 567
EP  - 570
SN  - 2352-5401
UR  - https://doi.org/10.2991/amcce-18.2018.98
DO  - 10.2991/amcce-18.2018.98
ID  - Luo2018/05
ER  -