An Automatic Construction Approach for Sentiment Dictionary Based on Weibo Emoticons

DOI

10.2991/ncce-18.2018.49How to use a DOI?

Keywords

Emoticon; sentiment classification; sentiment dictionary; sentiment polarity; natural language processing.

Abstract

Different from common texts, microblog texts have large amount of emotions and net-words. Its words and sentences expression are more colloquial and network popular, so traditional sentiment dictionary does not suit for the context of modern microblog short texts. This article puts forward an approach to automatically construct the sentiment dictionary based on microblog emoticons. Collected microblog texts are annotated by emoticons and form sentiment text corpus. To conduct consolidation according to existing sentiment dictionary, extract the sentiment words in the microblog texts per rule of part of speech, calculate the information added value of sentiment words in microblog texts as feature weight, and classify the sentiment words in the method of SVM to get the sentiment dictionary. This article improves the construction method of existing sentiment dictionary. The experimental result shows that the accuracy rate of sentiment dictionary after improvement reaches above 90%, and the overall F value reaches 85%, which are obviously better than existing dictionaries

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  - Xiaohong Hao
AU  - Yifan Jia
AU  - Qun Gu
PY  - 2018/05
DA  - 2018/05
TI  - An Automatic Construction Approach for Sentiment Dictionary Based on Weibo Emoticons
BT  - Proceedings of the 2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)
PB  - Atlantis Press
SP  - 312
EP  - 320
SN  - 1951-6851
UR  - https://doi.org/10.2991/ncce-18.2018.49
DO  - 10.2991/ncce-18.2018.49
ID  - Hao2018/05
ER  -