作者: Mário J. Silva , Paulo Batista
DOI:
关键词:
摘要: With the explosive growth of data available on Internet, personalization this information space become a necessity. An important component web is automatic knowledge extraction from log files. However, analysis large files complex task not fully addressed by existing access analyzers. Using commercial software, we applied well-known mining techniques (association rules and clustering) to analyze records collected newspaper. This paper identifies several reading patterns discusses approaches for data.