UAd

Aus wiki.sembase.at Semantic Wiki

Wechseln zu: Navigation, Suche
Do you think that items on this page are out of date? You can clean its cache to manually update all dynamic parts to the latest data from the wiki.



UAd Logo
UAd Logo

Inhaltsverzeichnis

Summary

UAd (Understanding Advertising) is a research project funded by FIT-IT. In UAd we focus on media understanding in the domain of market research. Along with the product information stemming from ads, UAd examines information available in public knowledge sources (the Web, discussion forums, freelance writing jobs philippines, etc.).

Objectives and System Overview

Advertising is a huge market. Each year 70 billion Euro are spent only in the European Union. Analysis of advertising sector is a task of media monitoring companies, which is currently mainly performed manually. Recently performed research projects have contributed to automate parts of the workflow, however, technologies are concentrating on multi-modal low level analysis and fusion of those results. Semantic knowledge, e.g. driven by domain specific media monitoring ontologies, has not been considered so far. Systems for highly automated trend analysis, identification of new business areas, product / company analysis are currently not available. On the other hand media monitoring companies and market research institutes would greatly benefit from such tools in order to ease their work and make results faster available.

We will perform research into a semantic media analysis framework (SEMAF) capable of taking as input low level feature metadata received from visual analysis of advertisements and public knowledge (i.e. company website info, stock market info, etc.). SEMAF will be a generic framework of modules with open interfaces which can be tailored easily by instantiation to specific domains of customer queries – e.g. trends for advertising expenditure in automotive sector as domain. Within the UAd application area specific ontologies and rules will be developed and applied together with the public knowledge in order to relate and homogenize information from heterogeneous sources and generate an answer to the user query.

Main challenges and at the same time innovations will be to take context information into consideration - such as ontologies, rules, public knowledge and low level feature results - next to a dynamic adaptation of the knowledge model represented by the UAd ontologies by application of the rules. Furthermore a major challenge will be also to take user feedback into account. Application areas of UAd will be not only restricted to advertising market but results can be applied to media monitoring in general. I.e. the generic SEMAF framework could be utilized for analysis of political campaigns, market research, social studies and so on. It is a project target to keep the framework as open as possible so that new instances on specific application areas can be made with as little effort as possible.

The project results enable the industrial partner HS-Art digital service GmbH to provide a future generation of technical solutions to the targeted media-monitoring market. HS-Art is with its current product portfolio successfully entering the niche-market of (semi-)automatic commercial analysis in multimedia contents. Although the products have been warmly welcomed in the market they are still quite a low-level solution in terms of semantic context. Thus the next generation of methodologies needs to be developed in the next few years to provide a continuously improved set of solutions to the media-monitoring market.

An overview of the UAd system is given in Fig. 1.

Fig. 1: UAd System Overview
Fig. 1: UAd System Overview


The UAd system architecture is depicted in Fig. 2.

Fig. 2: UAd System Architecture
Fig. 2: UAd System Architecture

Topics

Participating Organisations

Institut für Informationssysteme und Informationsmanagement

Key Researchers

Publications and Results

Papers and Thesis

W. Halb, Y. Raimond, M. Hausenblas. Building Linked Data For Both Humans and Machines. Accepted for the Linked Data on the Web Workshop at WWW08.

W. Weiss, M. Hausenblas. Visual Exploration, Query, and Debugging of RDF Graphs. Accepted for the Semantic Web User Interaction at CHI 2008

M. Hausenblas, H. Rehatschek. mle: Enhancing the Exploration of Mailing List Archives Through Making Semantics Explicit. Semantic Web Challenge 2007, collocated with the 6th International Semantic Web Conference (ISWC). Nov 2007.

W. Weiss. Visual Exploration, Query, and Debugging of RDF-Graphs and Ontologies. Master Thesis. FH Joanneum University of Applied Sciences, 2007.

M. Hausenblas, W. Slany, D. Ayers. A Performance and Scalability Metric for Virtual RDF Graphs. 3rd Workshop on Scripting for the Semantic Web (SFSW 07), collocated with the European Semantic Web Conference (ESWC). Jun 2007.

Software

Visual Analysis: PrimaRS

A media mining tool: PrimaRS.

PKI: Harvester/Mapper (HaMA)

HaMa - the Web HarvesterMapper (cf. Fig. 3). Currently a desktop Java application to harvest and map information from the Web to the UAd knoweledge base.

Fig. 3: UAd HaMa Tool
Fig. 3: UAd HaMa Tool

PKI: Discussion Tracer

An experimental prototype of the UAd Discussion Tracer: mle, the semantic Mailing List Explorer.

PKI: riese - Making statistical data available to UAd Analyser

On 2008-01-31 we launched the riese (RDFizing and Interlinking the EuroStat Data Set Effort). See the following Fig. 4, depicting the riese system architecture:

Fig. 4: riese architecture
Fig. 4: riese architecture

UAd Analyser

A first prototype of the UAd Analyser is available at http://uad.joanneum.at/analyser/ - a couple of discussion forums are available for exploration.

In The News

Key Data

Facts about UAd — Click + to find similar pages.View as RDF
Relations to other articles
FundedByFIT-IT  +
Deals withMediaSemantics   +, Ontologie   +, Rules   +, and Werbung   +
Wird vertreten vonHerwig Rehatschek  +
Attribute values
Projektname UAd  +
Homepage http://wiki.sembase.at/index.php?title=UAd  +
Email mailto:herwig.rehatschek@joanneum.at  +
Projektstart 2,007  +
Projektende 2,008  +
Laufzeit 24,00   +
Budget 300,000  +
Persönliche Werkzeuge