Naslov
Automatic Keywords Extraction - a Basis for Content Recommendation

Autori
Bosnić, Ivana ; Verbert, Katrien ; Duval, Erik

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 4th International Workshop on Search and Exchange of e-le@rning Materials 2010 (SE@M'10) / Massart, David ; Shulman, Elena - Aachen : CEUR-WS, 2010, 51-60

Skup
4th International Workshop on Search and Exchange of e-le@rning Materials 2010 (SE@M'10)

Mjesto i datum
Barcelona, Španjolska, 27.09.2010. - 28.09.2010

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
content; reuse; recommendations; keywords; keyword extraction

Sažetak
This paper describes a use case for an application that recommends learning objects for reuse and is integrated in the authoring environment. The recommendations are based on the automatic detection of content being authored and the context in which this resource is authored or used. The focus of the paper is automatic keyword extraction, evaluated as a starting point for content analysis. The evaluations explore whether automatic keyword extraction from content being authored is a sound basis for recommending relevant learning objects. The results show that automatically extracted keywords are suitable for this purpose, if some observed issues are appropriately addressed.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA