Modelling on microblog posts clustering based on iteration feature selection and abstractive summarisation
by Kai Gao; Bao-quan Zhang
International Journal of Modelling, Identification and Control (IJMIC), Vol. 24, No. 2, 2015

Abstract: With the coming of big data era, data mining and intelligent processing become more and more important, and modelling on novel big data processing is necessary. As micro-blog posts' properties on short texts and the linguistic unreliable features, it is necessary to analyse and cluster these similar posts together for further data mining and recommendation. This paper uses the classical clustering algorithm of k-means, and then presents a novel modelling approach to partition the micro-blog posts into the corresponding k similar groups. Furthermore, a feature selection model based on 2-phase iteration is proposed. Based on this model, a clustering algorithm is presented. The proposed algorithm takes use of the partition idea and avoids the influence of the outliers or noise data. Lastly, a proposed cluster abstractive summarisation approach is presented to summarise every individual cluster. On the basis of this, it is easy for users to know the main content about a cluster. Experiment shows the feasibility of the approach, and some existing problems and further works are also presented in the end.

Online publication date: Tue, 22-Sep-2015

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 Modelling, Identification and Control (IJMIC):
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