Affiliations: [a] School of Management, Hefei University of Technology, Hefei, Anhui, China | [b] School of Business, Beifang University of Nationalities, Yinchuan, Ningxia, China
Correspondence:
[*]
Corresponding author: Jin-Yun Wang, School of Management, Hefei University of Technology, Hefei 230009, Anhui, China. E-mail:jywang1016@sina.com
Abstract: The stability and self-adaption for combination texts must be processed in
Web Texts Environment. Therefore a language and technology method for
self-adapting environment of web texts is needed. To do this, we have built
an adaptive data-stream method in which the abnormal data mining process is
started. The resource consumption of abnormal data in a text includes the
resource consumption of error text and the total resource consumptions of
relating with the previously executed texts which are dependent on the error
text. In this paper an adaptive data-stream method is applied to implement
the Abnormal Data Mining in Web Texts Environment. Proved by simulation
verification, we proposed this adaptive data-stream method is efficient for
solving the problem of abnormal data mining in web texts environment.
Keywords: Self-adaption, text environment, state transition, data mining
