In this article, we describe the concepts and techniques of data analysis. Two categories, supervised data analysis and unsupervised data analysis, are first presented according to their different initial conditions and resultant uses. Two methods for data analysis are then described and illustrated by examples, which are based on probability theory and fuzzy-set theory, respectively. Following this introduction of the fundamental data analysis methods, the methods for data analysis on two types of Internet data, web page and web log, are presented. Further discussions on advanced methods for Internet data analysis are then provided, which are based on rough-set theory and association mining concepts. Finally, we bring this article to a conclusion with the research trends highlighted.
Wiley Encyclopedia of Computer Science and Engineering