SemStim at the LOD-RecSys 2014 challenge

Benjamin Heitmann; Conor Hayes

doi:10.1007/978-3-319-12024-9_22

SemStim at the LOD-RecSys 2014 challenge

Benjamin Heitmann, Conor Hayes

Computer Science

University of Galway

Research output: Chapter in Book or Conference Publication/Proceeding › Chapter › peer-review

11 Citations (Scopus)

Abstract

SemStim is a graph-based recommendation algorithm which is based on Spreading Activation and adds targeted activation and duration constraints. SemStim is not affected by data sparsity, the cold-start problem or data quality issues beyond the linking of items to DBpedia. The overall results show that the performance of SemStim for the diversity task of the challenge is comparable to the other participants, as it took 3rd place out of 12 participants with 0.0413 F1@20 and 0.476 ILD@20. In addition, as SemStim has been designed for the requirements of cross-domain recommendations with different target and source domains, this shows that SemStim can also provide competitive single-domain recommendations.

Original language	English
Title of host publication	Semantic Web Evaluation Challenge - SemWebEval 2014 at ESWC 2014, Revised Selected Papers
Editors	Tommaso Di Noia, Valentina Presutti, Diego Reforgiato Recupero, Iván Cantador, Christoph Lange, Christoph Lange, Anna Tordai, Christoph Lange, Milan Stankovic, Erik Cambria, Angelo Di Iorio
Publisher	Springer-Verlag
Pages	170-175
Number of pages	6
ISBN (Electronic)	9783319120232
DOIs	https://doi.org/10.1007/978-3-319-12024-9_22
Publication status	Published - 2014

Publication series

Name	Communications in Computer and Information Science
Volume	475
ISSN (Print)	1865-0929

Access to Document

10.1007/978-3-319-12024-9_22

Cite this

Heitmann, B., & Hayes, C. (2014). SemStim at the LOD-RecSys 2014 challenge. In T. Di Noia, V. Presutti, D. R. Recupero, I. Cantador, C. Lange, C. Lange, A. Tordai, C. Lange, M. Stankovic, E. Cambria, & A. Di Iorio (Eds.), Semantic Web Evaluation Challenge - SemWebEval 2014 at ESWC 2014, Revised Selected Papers (pp. 170-175). (Communications in Computer and Information Science; Vol. 475). Springer-Verlag. https://doi.org/10.1007/978-3-319-12024-9_22

Heitmann, Benjamin ; Hayes, Conor. / SemStim at the LOD-RecSys 2014 challenge. Semantic Web Evaluation Challenge - SemWebEval 2014 at ESWC 2014, Revised Selected Papers. editor / Tommaso Di Noia ; Valentina Presutti ; Diego Reforgiato Recupero ; Iván Cantador ; Christoph Lange ; Christoph Lange ; Anna Tordai ; Christoph Lange ; Milan Stankovic ; Erik Cambria ; Angelo Di Iorio. Springer-Verlag, 2014. pp. 170-175 (Communications in Computer and Information Science).

@inbook{7ca8df2c722441f6bee681f5ea2a5ee9,

title = "SemStim at the LOD-RecSys 2014 challenge",

abstract = "SemStim is a graph-based recommendation algorithm which is based on Spreading Activation and adds targeted activation and duration constraints. SemStim is not affected by data sparsity, the cold-start problem or data quality issues beyond the linking of items to DBpedia. The overall results show that the performance of SemStim for the diversity task of the challenge is comparable to the other participants, as it took 3rd place out of 12 participants with 0.0413 F1@20 and 0.476 ILD@20. In addition, as SemStim has been designed for the requirements of cross-domain recommendations with different target and source domains, this shows that SemStim can also provide competitive single-domain recommendations.",

author = "Benjamin Heitmann and Conor Hayes",

note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2014.",

year = "2014",

doi = "10.1007/978-3-319-12024-9\_22",

language = "English",

series = "Communications in Computer and Information Science",

publisher = "Springer-Verlag",

pages = "170--175",

editor = "\{Di Noia\}, Tommaso and Valentina Presutti and Recupero, \{Diego Reforgiato\} and Iv{\'a}n Cantador and Christoph Lange and Christoph Lange and Anna Tordai and Christoph Lange and Milan Stankovic and Erik Cambria and \{Di Iorio\}, Angelo",

booktitle = "Semantic Web Evaluation Challenge - SemWebEval 2014 at ESWC 2014, Revised Selected Papers",

}

Heitmann, B & Hayes, C 2014, SemStim at the LOD-RecSys 2014 challenge. in T Di Noia, V Presutti, DR Recupero, I Cantador, C Lange, C Lange, A Tordai, C Lange, M Stankovic, E Cambria & A Di Iorio (eds), Semantic Web Evaluation Challenge - SemWebEval 2014 at ESWC 2014, Revised Selected Papers. Communications in Computer and Information Science, vol. 475, Springer-Verlag, pp. 170-175. https://doi.org/10.1007/978-3-319-12024-9_22

SemStim at the LOD-RecSys 2014 challenge. / Heitmann, Benjamin; Hayes, Conor.
Semantic Web Evaluation Challenge - SemWebEval 2014 at ESWC 2014, Revised Selected Papers. ed. / Tommaso Di Noia; Valentina Presutti; Diego Reforgiato Recupero; Iván Cantador; Christoph Lange; Christoph Lange; Anna Tordai; Christoph Lange; Milan Stankovic; Erik Cambria; Angelo Di Iorio. Springer-Verlag, 2014. p. 170-175 (Communications in Computer and Information Science; Vol. 475).

Research output: Chapter in Book or Conference Publication/Proceeding › Chapter › peer-review

TY - CHAP

T1 - SemStim at the LOD-RecSys 2014 challenge

AU - Heitmann, Benjamin

AU - Hayes, Conor

N1 - Publisher Copyright: © Springer International Publishing Switzerland 2014.

PY - 2014

Y1 - 2014

N2 - SemStim is a graph-based recommendation algorithm which is based on Spreading Activation and adds targeted activation and duration constraints. SemStim is not affected by data sparsity, the cold-start problem or data quality issues beyond the linking of items to DBpedia. The overall results show that the performance of SemStim for the diversity task of the challenge is comparable to the other participants, as it took 3rd place out of 12 participants with 0.0413 F1@20 and 0.476 ILD@20. In addition, as SemStim has been designed for the requirements of cross-domain recommendations with different target and source domains, this shows that SemStim can also provide competitive single-domain recommendations.

AB - SemStim is a graph-based recommendation algorithm which is based on Spreading Activation and adds targeted activation and duration constraints. SemStim is not affected by data sparsity, the cold-start problem or data quality issues beyond the linking of items to DBpedia. The overall results show that the performance of SemStim for the diversity task of the challenge is comparable to the other participants, as it took 3rd place out of 12 participants with 0.0413 F1@20 and 0.476 ILD@20. In addition, as SemStim has been designed for the requirements of cross-domain recommendations with different target and source domains, this shows that SemStim can also provide competitive single-domain recommendations.

UR - http://www.scopus.com/inward/record.url?scp=84908510148&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-12024-9_22

DO - 10.1007/978-3-319-12024-9_22

M3 - Chapter

T3 - Communications in Computer and Information Science

SP - 170

EP - 175

BT - Semantic Web Evaluation Challenge - SemWebEval 2014 at ESWC 2014, Revised Selected Papers

A2 - Di Noia, Tommaso

A2 - Presutti, Valentina

A2 - Recupero, Diego Reforgiato

A2 - Cantador, Iván

A2 - Lange, Christoph

A2 - Tordai, Anna

A2 - Lange, Christoph

A2 - Stankovic, Milan

A2 - Cambria, Erik

A2 - Di Iorio, Angelo

PB - Springer-Verlag

ER -

Heitmann B, Hayes C. SemStim at the LOD-RecSys 2014 challenge. In Di Noia T, Presutti V, Recupero DR, Cantador I, Lange C, Lange C, Tordai A, Lange C, Stankovic M, Cambria E, Di Iorio A, editors, Semantic Web Evaluation Challenge - SemWebEval 2014 at ESWC 2014, Revised Selected Papers. Springer-Verlag. 2014. p. 170-175. (Communications in Computer and Information Science). doi: 10.1007/978-3-319-12024-9_22

SemStim at the LOD-RecSys 2014 challenge

Abstract

Publication series

Access to Document

Other files and links

Fingerprint

Cite this