Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Extracting and Integrating Meta-data from online sources: A set of examples leading to improved course and instructor selection
KTH, School of Information and Communication Technology (ICT), Communication Systems, CoS, Radio Systems Laboratory (RS Lab). (CCS)
KTH, School of Information and Communication Technology (ICT), Communication Systems, CoS, Radio Systems Laboratory (RS Lab). (CCS)ORCID iD: 0000-0002-0916-0188
2014 (English)Report (Other academic)
Abstract [en]

The recent advances in Natural Language Processing (NLP), association based algorithms and recommendation systems enabled suppliers to personalize the content offered to their clients / subscribers. However, their use has been limited to either the industrial environment or to the research one, leaving the education environment lacking when it comes to such tools. This report focuses on exploring the use of recommendation systems in education. First, it presents methods that are suitable for extracting meta-data that can be used to derive certain associations and / or suggestions. Second, it proposes a method that suggests courses and / or tutors based on a student's interest. Third, it provides DocAid, which is an API suitable for extracting meta-data from different sources. Finally, a web application is built on top of DocAidto make the aforementioned functionality available for others to use.

Abstract [sv]

De senaste framstegen inom Natural Language Processing (NLP), föreningsbaserade algoritmer och rekommendationssystem möjlig leverantörerna att anpassa det innehåll som erbjuds till sina kunder / abonnenter. Dremot har användningen varit begränsad till antingen den industriella miljön eller till forskning en, lämnar utbildningsmiljön saknas när det kommer till sådana verktyg. Denna rapport fokuserar på att utforska anvndningen av rekommen- dationssystem i utbildningen. Först presenterar det metoder som är lämpliga för extraktion av meta-data som kan användas fr att härleda vissa föreningar och / eller förslag. För det andra föreslås en metod som tyder på kurser och / eller handledare som bygger på en studerandes intresse. För det tredje ger det DocAid, vilket är ett API som lämpar sig för att extrahera metadata från olika källor. Slutligen är en webbapplikation byggd ovanpå DocAid för att göra den tidigare nämnda funktioner tillgängliga för andra att använda.

Place, publisher, year, edition, pages
2014. , vii,40 p.
Series
TRITA-ICT-COS, ISSN 1653-6347 ; 1409
Keyword [en]
keyword extraction, keyphrases extraction, recommender systems, suggestion, algorithms
Keyword [sv]
nyckelord extraktion, nyckelfras extraktion, rekommenderat system, förslag, algoritmer
National Category
Communication Systems
Identifiers
URN: urn:nbn:se:kth:diva-147203OAI: oai:DiVA.org:kth-147203DiVA: diva2:728514
Note

Project for IK2553

QC 20140708

Available from: 2014-06-24 Created: 2014-06-24 Last updated: 2014-07-08Bibliographically approved

Open Access in DiVA

fulltext(915 kB)141 downloads
File information
File name FULLTEXT01.pdfFile size 915 kBChecksum SHA-512
3db21cc05b979b1f22aa99a978571d02e8ee38c9254a5c6a7101f14b219bd1894d6b0747b3074aae77b1edf7b6ac4f957df836aca0eb5db274be8a4d81f3d96d
Type fulltextMimetype application/pdf
DocAid(244997 kB)0 downloads
File information
File name SOFTWARE01.gzFile size 244997 kBChecksum SHA-512
c53f06db0ac27a968be17005c10e6e24e13d686db35e303c3fa14b3c3cfb07a933686e25c9881f0bbe13fde865341283b9332a3878c87424ee241e4a5b839760
Type softwareMimetype application/x-gzip

Authority records BETA

Prelipcean, Adrian Corneliu

Search in DiVA

By author/editor
Kokkalis, AndreasPrelipcean, Adrian Corneliu
By organisation
Radio Systems Laboratory (RS Lab)
Communication Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 141 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 214 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf