SIRUP: Serendipity In Recommendations via User Perceptions

V. Maccatrozzo; L.M. Aroyo; Manon Terstall; Guus Schreiber

doi:https://doi.org/10.1145/3025171.3025185

SIRUP: Serendipity In Recommendations via User Perceptions

V. Maccatrozzo, L.M. Aroyo, Manon Terstall, Guus Schreiber

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

Abstract

In this paper, we propose a model to operationalise serendipity in content-based recommender systems. The model, called SIRUP, is inspired by the Silvia's curiosity theory, based on the fundamental theory of Berlyne, aims at (1) measuring the novelty of an item with respect to the user profile, and (2) assessing whether the user is able to manage such level of novelty (coping potential). The novelty of items is calculated with cosine similarities between items, using Linked Open Data paths. The coping potential of users is estimated by measuring the diversity of the items in the user profile. We deployed and evaluated the SIRUP model in a use case with TV recommender using BBC programs dataset. Results show that the SIRUP model allows us to identify serendipitous recommendations, and, at the same time, to have 71% precision.

Original language	English
Title of host publication	Proceedings of the 22nd International Conference on Intelligent User Interfaces
Place of Publication	New York, NY, USA
Publisher	ACM
Pages	35-44
Number of pages	10
ISBN (Electronic)	9781450343480
DOIs	https://doi.org/10.1145/3025171.3025185
Publication status	Published - Mar 2017

Keywords

Curiosity
Design Methods
Entertainment
Personalization
Qualitative Methods
Recommender System
Serendipity
Television/Video
User Studies
User and Cognitive models

Access to Document

https://doi.org/10.1145/3025171.3025185

Handle.net

Persistent link

Cite this

@inproceedings{f2a2acf0b42e4893a43e0316505550b2,

title = "SIRUP: Serendipity In Recommendations via User Perceptions",

abstract = "In this paper, we propose a model to operationalise serendipity in content-based recommender systems. The model, called SIRUP, is inspired by the Silvia's curiosity theory, based on the fundamental theory of Berlyne, aims at (1) measuring the novelty of an item with respect to the user profile, and (2) assessing whether the user is able to manage such level of novelty (coping potential). The novelty of items is calculated with cosine similarities between items, using Linked Open Data paths. The coping potential of users is estimated by measuring the diversity of the items in the user profile. We deployed and evaluated the SIRUP model in a use case with TV recommender using BBC programs dataset. Results show that the SIRUP model allows us to identify serendipitous recommendations, and, at the same time, to have 71% precision.",

keywords = "Curiosity, Design Methods, Entertainment, Personalization, Qualitative Methods, Recommender System, Serendipity, Television/Video, User Studies, User and Cognitive models",

author = "V. Maccatrozzo and L.M. Aroyo and Manon Terstall and Guus Schreiber",

year = "2017",

month = mar,

doi = "https://doi.org/10.1145/3025171.3025185",

language = "English",

pages = "35--44",

booktitle = "Proceedings of the 22nd International Conference on Intelligent User Interfaces",

publisher = "ACM",

}

TY - GEN

T1 - SIRUP: Serendipity In Recommendations via User Perceptions

AU - Maccatrozzo, V.

AU - Aroyo, L.M.

AU - Terstall, Manon

AU - Schreiber, Guus

PY - 2017/3

Y1 - 2017/3

N2 - In this paper, we propose a model to operationalise serendipity in content-based recommender systems. The model, called SIRUP, is inspired by the Silvia's curiosity theory, based on the fundamental theory of Berlyne, aims at (1) measuring the novelty of an item with respect to the user profile, and (2) assessing whether the user is able to manage such level of novelty (coping potential). The novelty of items is calculated with cosine similarities between items, using Linked Open Data paths. The coping potential of users is estimated by measuring the diversity of the items in the user profile. We deployed and evaluated the SIRUP model in a use case with TV recommender using BBC programs dataset. Results show that the SIRUP model allows us to identify serendipitous recommendations, and, at the same time, to have 71% precision.

AB - In this paper, we propose a model to operationalise serendipity in content-based recommender systems. The model, called SIRUP, is inspired by the Silvia's curiosity theory, based on the fundamental theory of Berlyne, aims at (1) measuring the novelty of an item with respect to the user profile, and (2) assessing whether the user is able to manage such level of novelty (coping potential). The novelty of items is calculated with cosine similarities between items, using Linked Open Data paths. The coping potential of users is estimated by measuring the diversity of the items in the user profile. We deployed and evaluated the SIRUP model in a use case with TV recommender using BBC programs dataset. Results show that the SIRUP model allows us to identify serendipitous recommendations, and, at the same time, to have 71% precision.

KW - Curiosity

KW - Design Methods

KW - Entertainment

KW - Personalization

KW - Qualitative Methods

KW - Recommender System

KW - Serendipity

KW - Television/Video

KW - User Studies

KW - User and Cognitive models

UR - http://www.scopus.com/inward/record.url?scp=85016458567&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016458567&partnerID=8YFLogxK

U2 - https://doi.org/10.1145/3025171.3025185

DO - https://doi.org/10.1145/3025171.3025185

M3 - Conference contribution

SP - 35

EP - 44

BT - Proceedings of the 22nd International Conference on Intelligent User Interfaces

PB - ACM

CY - New York, NY, USA

ER -

SIRUP: Serendipity In Recommendations via User Perceptions

Abstract

Keywords

Access to Document

Handle.net

Other files and links

Fingerprint

Cite this