Constructing Web User Profiles

Web User Profiles consist y Page Interest Estimators (PIE) Web Access Graphs (WAG) y .

We can apply learning algorithm to induce classifiers that predict if a page is of interest to the user.Page Interest Estimators (PIE) y We can identify the patterns of pages that constitute user·s interest. y . These classifiers are called Page Interest Estimators (PIE).

. our user profile contains a Web Access Graph (WAG). A WAG is a weighted directed graph that represents a user·s access behavior.Web Access Graph (WAG) y In addition to the Page Interest Estimator (PIE).

is the application of data mining techniques to discover patterns from the Web. Web usage mining y Web content mining y Web structure mining y .What is Web Mining ? y Web mining .

whereas some others might be interested in multimedia data. .e users history.Web usage mining Web usage mining is a process of extracting useful information from server logs i. Some users might be looking at only textual data. Web usage mining is the process of finding out what users are looking for on the Internet.

because the text content is the most widely researched area.Web content mining y Web content mining is the process to discover useful information from text. audio or video data in the web. y . image. Web content mining sometimes is called web text mining.

2. Extracting patterns from hyperlinks in the web: a hyperlink is a structural component that connects the web page to a different location. web structure mining can be divided into two kinds: y 1. Mining the document structure: analysis of the tree-like structure of page structures to describe HTML or XML tag usage. y .Web structure mining y Web structure mining is the process of using graph theory to analyze the node and connection structure of a web site. According to the type of web structural data.

.Clustering y Clustering techniques can be used to find pages that are closely associated with each other and are likely to be accessed by the user consecutively.

Utilization of user profile y Analysis of search results. Recommendations of new and interesting pages y .

Algorithm y y y y y y y y y User profile registration User visits Total number of visit·s on each page Insert visit records into MYSQL database Preparing and processing data Page interest Estimators (PIE). Clustering Recommendations of new and interesting pages. Web Access Graphs (WAG). .

Diagram Database Data Processing Data Collection User Visits User Site Results .

Software & Hardware requirements y Software : y x WAMP Server Hardware : x Linux Server y Frontend : x PHP x Our frontend is PHP. We are using PHP script for processing our algorithm. insert data into database and to display the results. y Backend : x MYSQL x Our backend is MYSQL. We are using MYSQL to store collected data . data collection.

Saves time of user. It makes system more intelligent. y y .Advantages : y User can easily find what they are searching for.

4(2). G. S. (2001). R.. (2007). Rivers.. Informed recommender: Basing recommendations on consumer product reviews. W. 121²132. J. & Park. 234²248. Simoff. Lee..22(3). M. R. Profiling students· adaptation styles in web-based learning. . G. (1980). IEEE Intelligent Systems. & Debenham. & Storrs. 36.. Journal of Consumer Research. 7(December). D.REFERENCES Aciar.Computers & Education.. (1985). Behaviour and Information Technology. Zhang. y Bettman . y y y Canter. 39²47. J.. Characterising users navigation through complex data structures. C. Effects of prior knowledge and experience and phase of the choice process on consumer decision processes: A protocol analysis. S. 93²102. D.

Sign up to vote on this title
UsefulNot useful