150 likes | 277 Views
Interception of User’s Interests on the Web. Michal Barla. barla @fiit.stuba.sk. Supervisor : prof. Mária Bieliková. Motivation. Adaptation is based on user model Manual filling of user model brings several issues Not what a user really wants to do User may over/under estimate herself
E N D
Interception of User’s Interestson the Web Michal Barla barla@fiit.stuba.sk Supervisor: prof. Mária Bieliková
Motivation • Adaptation is based on user model • Manual filling of user model brings several issues • Not what a user really wants to do • User may over/under estimate herself • User may not know exactly some needed characteristics • Goal: Estimate user characteristics automatically by analyzing user behavior within a system Interception of User's Interests on the Web
Process Peter Brusilovsky. Methods and techniques of adaptive hypermedia. User Modelingand User-Adapted Interaction, 6(2-3):87–129, 1996. Interception of User's Interests on the Web
Data Collection • We create logs of user activities • Usually done on server side • Advantage: always available • Issue: server is not aware of all performed actions • Back button and browser cache • Active elements on a page – e.g. hover, hiding • Monitoring on client side • Use of client web technologies (JavaScript, Java applets) • Advantage: we can capture all actions with exact timestamps • Issue: we have no control on execution of logging tool Interception of User's Interests on the Web
Data Collection – our approach • Combination of server-side and client-side logging • Client Side Action Recorder – Click • Monitoring on client side • SemanticLog • Specialized server side logging tool Interception of User's Interests on the Web
Click • Based on JavaScript • Native access to DOM • Captures events fired by browser • Load, Unload, Click, Mouseover,… • For each event, it records • Type of event • Timestamp • Event context (e.g. what link was pressed) • Event handling based on W3C DOM Level 2 Event Specification • Easy integration into existing static pages and dynamic pages • Communication with server is done asynchronously using AJAX Interception of User's Interests on the Web
Data analysis - challenge • No direct connection between user behavior and user characteristics • User may behave in contrast with what seems to be logic (which can also be stored as a characteristic ) • People are changing characteristics are changing • Goal: Estimate characteristics • Each characteristic has some confidence • Not all possible characteristics (suitable for a set of domainspecific characteristics) Interception of User's Interests on the Web
Data analysis - approaches • Analysis of navigation • What path did user choose to reach desired information? • Analysis of user feedback • Explicit or implicit • What are the reasons of different ratings? • Analysis of consistent behavior • Does user behave according to previous sessions? • Is user model still valid? Interception of User's Interests on the Web
Analysis of navigation Interception of User's Interests on the Web
Usage patterns identification • Usage patterns • pre-defined according to navigation model of a web site • Pattern lookup ~ sequence matching • Using a suffix tree data structure • Suffix trie = compressed trie (from “retrieval”) Interception of User's Interests on the Web
Analysis of user feedback • Searching for implicit feedback patterns on information objects • Selection, duration, retention of information • Evaluation of feedback rating • Rating does not give user characteristics • Why user rated A differently than B? • Why user rated P same as Q? • We get characteristics by comparing concepts Interception of User's Interests on the Web
Concept Comparing - example • Two similar job offers differs only in duty location • They get different rating We can raise the relevance of duty location characteristic. We can also estimate desired/unwanted values. • Two different job offers have the same rating If we find some common aspect, we can raise relevance of appropriate characteristic Interception of User's Interests on the Web
Analysis of consistent behavior • Sequential patterns mining on previous user sessions • Typical user behavior • Actual session should be mapped to some pattern • Reasons of inconsistent behavior • User is in “special” mood, does not follow presumed goal • User is looking for information on behalf of somebody else • User has changed • It has been a long time from previous session • We invalidate the model and start over Interception of User's Interests on the Web
LogAnalyzer Interception of User's Interests on the Web
Conclusions • User modeling based on user behavior analysis • Acquiring of activity logs on client and server side • JavaScript based logging tool – Click • Various approaches to analysis of acquired logs • Navigation • Feedback ~ Concept Comparing • LogAnalyzer Interception of User's Interests on the Web