Go to JKU Homepage
institute-for-application-oriented-knowledge-processing
What's that?

Institutes, schools, other departments, and programs create their own web content and menus.

To help you better navigate the site, see here where you are at the moment.

Nachrichtenempfehlungen auf Basis eines Graphen aus IPTC- und Wikipedia-Kategorien

Student: Harald Holzner     (2024)


Supervisor: a.Univ.-Prof. DI Dr. Wolfram Wöß
 

Content

A company in the news environment would like to facilitate the recommendation of news articles. Currently, the recommendation of articles is based on keywords (tags) to be
selected. To improve the recommendation algorithm, a way to categorize these tags is being explored. Based on the assigned categories, the selection of newspaper providers can be extended. Therefore, a graph consisting of IPTC Media Topics andWikipedia categories, as well as the associated tags, is generated. By using the graph, related categories can be identified. The central problem is how to combine these two data sources in a meaningful way. Finally, the different approaches of the unification are evaluated with respect to their hit rate.