Jump to contentJump to search

005

Titel / Titel:

The critical role of the cold-start problem and incentive systems in emotional Web 2.0 services

Author / Autor

Siebenlist, T., Knautz, K.

 

Source / Quelle

Indexing and Retrieval of Non-Text Information (pp. 376-405). Berlin, Boston, MA: De Gruyter Saur.

Language / Sprache

English / Englisch

 

The critical role of the cold-start problem and incentive systems in emotional Web 2.0 services.

Some content in multimedia resources can depict or evoke certain emotions
in users. The aim of Emotional Information Retrieval (EmIR) is to identify
knowledge about emotional-laden documents and to use these findings in a new kind of World Wide Web information service that allows users to search and browse by emotion. The cold-start problem arises in systems where users need to rate or tag documents when there is not sufficient information to draw interferences from these documents and the existing ratings or tags for those. The cold-start problem can be divided into three situations: cold-start system, coldstart user and cold-start item. In this paper we will refer to the first one and the last one. We will discuss the cold-start problem of the specialized search engine for emotional-laden multimedia documents called MEMOSE in this article and provide a solution using a combination of using content-based features to overcome the start-up phase and an incentive system for getting and keeping users motivated to use MEMOSE.

undefinedPDF

Tobias Siebenlist
Heinrich-Heine-Universität Düsseldorf
Institut für Sprache und Information
Abt. Informationswissenschaft
Universitätsstr. 1
D - 40225 Düsseldorf
E-Mail: tobias.siebenlist@uni-duesseldorf.de

Kathrin Knautz
Institut für Sprache und Information
Abt. Informationswissenschaft
Heinrich-Heine-Universität Düsseldorf
Universitätsstr. 1
D - 40225 Düsseldorf
E-Mail: Kathrin.Knautz@uni-duesseldorf.de

Responsible for the content: