Stage-oe-small.jpg

Techreport3025: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
 
Zeile 13: Zeile 13:
 
}}
 
}}
 
{{Publikation Details
 
{{Publikation Details
|Download=JH paper 2013.pdf,  
+
|Abstract=Large amounts of data are being produced daily
 +
as detailed records of Web usage behavior, but the
 +
task of deriving actionable knowledge from them
 +
remains a challenge. Investigations of user browsing
 +
behavior at multiple websites, while more beneficial
 +
than studies restricted to a single site, still need to
 +
tackle the problems of information heterogeneity and
 +
mapping usage logs to meaningful events from the
 +
application domain.
 +
 
 +
Focusing on the problem of modeling cross-site
 +
browsing behavior, we present a formalization approach
 +
based on a Web browsing Activity Model
 +
(WAM). We introduce a novel two-staged approach
 +
for the semantic enrichment of usage logs with
 +
domain knowledge, bringing together Semantic Web
 +
technologies and Machine Learning techniques.
 +
For learning the semantic types of logs, we present
 +
a supervised multi-class classification formulation,
 +
deploying structural Support Vector Machines with
 +
new sequential input features.
 +
 
 +
We provide an implementation
 +
of these approaches and show the results
 +
of evaluation with real-world data.
 +
|Download=JH paper 2013.pdf,
 
|Forschungsgruppe=Wissensmanagement
 
|Forschungsgruppe=Wissensmanagement
 
}}
 
}}

Aktuelle Version vom 23. Mai 2013, 08:49 Uhr

Semantic Formalization of Cross-site User Browsing Behavior




Published: 2012 November
Type: Research Technical Report
Institution: Institut AIFB, KIT
Erscheinungsort / Ort: Karlsruhe
Archivierungsnummer:3025

BibTeX



Kurzfassung
Large amounts of data are being produced daily as detailed records of Web usage behavior, but the task of deriving actionable knowledge from them remains a challenge. Investigations of user browsing behavior at multiple websites, while more beneficial than studies restricted to a single site, still need to tackle the problems of information heterogeneity and mapping usage logs to meaningful events from the application domain.

Focusing on the problem of modeling cross-site browsing behavior, we present a formalization approach based on a Web browsing Activity Model (WAM). We introduce a novel two-staged approach for the semantic enrichment of usage logs with domain knowledge, bringing together Semantic Web technologies and Machine Learning techniques. For learning the semantic types of logs, we present a supervised multi-class classification formulation, deploying structural Support Vector Machines with new sequential input features.

We provide an implementation of these approaches and show the results of evaluation with real-world data.

Download: Media:JH paper 2013.pdf



Forschungsgruppe

Wissensmanagement


Forschungsgebiet