WebUsageMiningDiscoveryandApplicationsofUsagePa解读.ppt

結果與分析 在關聯法則的實驗結果，發現瀏覽網頁D018(下午茶)的狀況下也會瀏覽網頁D035(綜合健康檢查簡介) 結果與分析 結果發現，會瀏覽檢驗結果解讀(B002)網頁及血脂肪(D479)網頁而不瀏覽肝臟保健(D306)網頁之顧客，是屬於會瀏覽肝功能(D221)網頁的族群 Conclusions 電子化交易的日漸普及，不僅是商業交易的資料，網站的日誌紀錄也是同樣的與日俱增 資料探勘領域也有大幅的成長 個人化網站的建立，以及適形化的服務也將成為未來的趨勢 透過Web Mining 技術的使用，則可以對現行的資料進行深入的挖掘，從找出的規則中，去進行改變，以創造優勢 Web Usage Mining: Discovery and Applications of UsagePatterns from Web Data 指導教授：黃三益老師 第二組：洪瑞麟 m964020015 蔡育洲 m964020034 陳怡綾 m964020041 SIGKDD Explorations. Copyrightc 2000 ACM SIGKDD, Jan 2000 Outline Introduction Problem statement Detailed data mining Conclusions and critics Introduction Web mining: Data mining efforts associated with the Web content, usage, and structure To discover usage patterns from Web data, in order to understand and better serve the needs of Web-based applications. Classes Web Content Mining: mining the data on the Web (text, image, audio, video, metadata and hyperlinks) Web Structure Mining: mining the Web structure data Web Usage Mining: mining the Web log data (preprocessing, pattern discovery, and pattern analysis ) Data type Content: The real data in the Web pages (text and graphics) Structure: describes the organization of the content. (as a tree structure) Usage: describes the pattern of usage of Web pages (IP addresses, page references, and the date and time of accesses.) User Profile: provides demographic information about users of the Web site. (registration data and customer profile information) Data source (Web traffic ) Server Level Collection log files, Packet sniffing, Cookies, Query data and CGI script Client Level Collection Javascript, Java applet, and the modified browser Proxy Level Collection Proxy caching Data abstractions user a single individual that is accessing file from one or more Web servers through a browser page view consists of every file that contributes to the display on a users browser at one time click-stream a sequential series of page view requests user session the click-stre