Personality modelling and sentiment analysis on Chinese micro-blog posts
by Kai Gao; Chongyang Yue; Siyu Li; Duoxing Liu; Erliang Zhou; Herbert Daly
International Journal of Intelligent Information and Database Systems (IJIIDS), Vol. 11, No. 1, 2018

Abstract: Intelligent information process such as opinion mining and sentiment analysis on social media remains an ongoing challenge, and it is also useful in public opinion surveillance. Analysing micro-blog posts is often hampered by their very brief content as well as the use of misspelled or abbreviated words. This paper focuses on personality modelling and sentiment analysis on Chinese micro-blog posts. Social media data pre-processing, to identify named entities and word sense disambiguation, is essential. The proposed pre-processing includes the double-array trie based segmentation and viterbi based word sense disambiguation, together with the co-occurrence probability based processing of unknown words. The personality modelling procedure vectorises micro-blog posts into high dimension eigenvectors. As for the sentiment analysis, this paper proposes the multi-convolutional neural method to solve the sentiment tendency determination problem. The experimental results show the feasibility of the approach, and existing problems and future works are also present in the end.

Online publication date: Tue, 08-May-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Intelligent Information and Database Systems (IJIIDS):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com