Addressing Scalability Issues in Semantics-Driven Recommender Systems

Mounir M. Bendouch; Flavius Frasincar; Tarmo Robal

doi:10.1145/3486622.3493963

Addressing Scalability Issues in Semantics-Driven Recommender Systems

Mounir M. Bendouch
, Flavius Frasincar
, Tarmo Robal

Econometrics

Erasmus School of Health Policy and Management (ESHPM)
Tallinn University of Technology

Research output: Chapter/Conference proceeding › Conference proceeding › Academic › peer-review

6 Citations (Scopus)

Abstract

Content-based semantics-driven recommender systems are often used in the small-scale news recommendation domain. These recommender systems improve over TF-IDF by taking into account (domain) semantics through semantic lexicons or domain ontologies. Our work explores the application of such recommender systems to other domains, using the case of large-scale movie recommendations. We propose new methods to extract semantic features from various item descriptions, and for scaling up the semantics-driven approach with pre-computation of the cosine similarities and gradient learning of the model. The results of the study on a large-scale dataset of user ratings demonstrate that semantics-driven recommenders can be extended to more complex domains and outperform TF-IDF on ROC, PR, F1, and Kappa metrics.

Original language	English
Title of host publication	Proceedings - 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021
Publisher	Association for Computing Machinery (ACM)
Pages	56-63
Number of pages	8
ISBN (Electronic)	9781450391153
DOIs	https://doi.org/10.1145/3486622.3493963
Publication status	Published - 14 Dec 2021
Event	2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021 - Virtual, Online, Australia Duration: 14 Dec 2021 → 17 Dec 2021

Publication series

Series	ACM International Conference Proceeding Series

Conference

Conference	2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021
Country/Territory	Australia
City	Virtual, Online
Period	14/12/21 → 17/12/21

Bibliographical note

Publisher Copyright:
© 2021 ACM.

Access to Document

10.1145/3486622.3493963

Cite this

@inproceedings{ad9bc09da9104ee3be1f7ef659cd77bd,

title = "Addressing Scalability Issues in Semantics-Driven Recommender Systems",

abstract = "Content-based semantics-driven recommender systems are often used in the small-scale news recommendation domain. These recommender systems improve over TF-IDF by taking into account (domain) semantics through semantic lexicons or domain ontologies. Our work explores the application of such recommender systems to other domains, using the case of large-scale movie recommendations. We propose new methods to extract semantic features from various item descriptions, and for scaling up the semantics-driven approach with pre-computation of the cosine similarities and gradient learning of the model. The results of the study on a large-scale dataset of user ratings demonstrate that semantics-driven recommenders can be extended to more complex domains and outperform TF-IDF on ROC, PR, F1, and Kappa metrics.",

author = "Bendouch, \{Mounir M.\} and Flavius Frasincar and Tarmo Robal",

note = "Publisher Copyright: {\textcopyright} 2021 ACM.; 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021 ; Conference date: 14-12-2021 Through 17-12-2021",

year = "2021",

month = dec,

day = "14",

doi = "10.1145/3486622.3493963",

language = "English",

series = "ACM International Conference Proceeding Series",

pages = "56--63",

booktitle = "Proceedings - 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

}

Bendouch, MM, Frasincar, F & Robal, T 2021, Addressing Scalability Issues in Semantics-Driven Recommender Systems. in Proceedings - 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021. Association for Computing Machinery (ACM), ACM International Conference Proceeding Series, pp. 56-63, 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021, Virtual, Online, Australia, 14/12/21. https://doi.org/10.1145/3486622.3493963

Addressing Scalability Issues in Semantics-Driven Recommender Systems. / Bendouch, Mounir M.; Frasincar, Flavius; Robal, Tarmo.
Proceedings - 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021. Association for Computing Machinery (ACM), 2021. p. 56-63 (ACM International Conference Proceeding Series).

Research output: Chapter/Conference proceeding › Conference proceeding › Academic › peer-review

TY - GEN

T1 - Addressing Scalability Issues in Semantics-Driven Recommender Systems

AU - Bendouch, Mounir M.

AU - Frasincar, Flavius

AU - Robal, Tarmo

PY - 2021/12/14

Y1 - 2021/12/14

N2 - Content-based semantics-driven recommender systems are often used in the small-scale news recommendation domain. These recommender systems improve over TF-IDF by taking into account (domain) semantics through semantic lexicons or domain ontologies. Our work explores the application of such recommender systems to other domains, using the case of large-scale movie recommendations. We propose new methods to extract semantic features from various item descriptions, and for scaling up the semantics-driven approach with pre-computation of the cosine similarities and gradient learning of the model. The results of the study on a large-scale dataset of user ratings demonstrate that semantics-driven recommenders can be extended to more complex domains and outperform TF-IDF on ROC, PR, F1, and Kappa metrics.

AB - Content-based semantics-driven recommender systems are often used in the small-scale news recommendation domain. These recommender systems improve over TF-IDF by taking into account (domain) semantics through semantic lexicons or domain ontologies. Our work explores the application of such recommender systems to other domains, using the case of large-scale movie recommendations. We propose new methods to extract semantic features from various item descriptions, and for scaling up the semantics-driven approach with pre-computation of the cosine similarities and gradient learning of the model. The results of the study on a large-scale dataset of user ratings demonstrate that semantics-driven recommenders can be extended to more complex domains and outperform TF-IDF on ROC, PR, F1, and Kappa metrics.

UR - https://www.scopus.com/pages/publications/85128629136

U2 - 10.1145/3486622.3493963

DO - 10.1145/3486622.3493963

M3 - Conference proceeding

AN - SCOPUS:85128629136

T3 - ACM International Conference Proceeding Series

SP - 56

EP - 63

BT - Proceedings - 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021

PB - Association for Computing Machinery (ACM)

T2 - 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021

Y2 - 14 December 2021 through 17 December 2021

ER -

Bendouch MM, Frasincar F, Robal T. Addressing Scalability Issues in Semantics-Driven Recommender Systems. In Proceedings - 2021 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2021. Association for Computing Machinery (ACM). 2021. p. 56-63. (ACM International Conference Proceeding Series). doi: 10.1145/3486622.3493963

Addressing Scalability Issues in Semantics-Driven Recommender Systems

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this