Editorial

We are pleased to present this special issue of the Knowledge and Information Systems Journal consisting of six selected papers from the 10th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) held in Singapore in April 2006. The Pacific-Asia Conference on Knowledge Discovery and Data Mining is a leading international conference in the area of data mining and knowledge discovery. It is an annual conference that provides an international forum for researchers and industry practitioners to share their new ideas, original research results and practical development experiences from all aspects of KDD data mining, including data warehousing, machine learning, databases, statistics, knowledge acquisition, automatic scientific discovery, data visualization, causal induction, and knowledge-based systems. PAKDD 2006 received 501 paper submissions from 38 countries and regions in Asia, Australia, North America and Europe, of which 67 (13.4%) papers were accepted as regular papers and 33 (6.6%) papers as short papers. The six papers presented in this issue are selected from among the best papers accepted in PAKDD 2006 in terms of their technical contributions and paper presentation. The paper on “Learning to Extract and Summarize Hot Item Features from Multiple Auction Web Sites” by Tak-Lam Wong and Wai Lam presents a graph-based approach to model dependencies among entities using Conditional Random Fields. This allows one to automatically semantically tag text segments in Web pages and express their relationships and dependencies. In this way, tags corresponding to product features can be identified from