The pursuit of satisfaction

Affective state in group recommender systems

Research output: Chapter in Book/Report/Conference proceedingConference contribution

16 Citations (Scopus)

Abstract

This paper describes three algorithms to model and predict the satisfaction experienced by individuals using a group recommender system which recommends sequences of items. Satisfaction is treated as an affective state. In particular, we model the wearing off of emotion over time and assimilation effects, where the affective state produced by previous items influences the impact on satisfaction of the next item. We compare the algorithms with each other, and investigate the effect of parameter values by comparing the algorithms' predictions with the results of an earlier empirical study. We show a way in which affective state can be used in recommender systems, which is useful for recommendations not only to groups but also to individuals.

Original languageEnglish
Title of host publicationUser Modeling 2005
Subtitle of host publicationProceedings of the 10th International Conference, UM 2005, Edinburgh, Scotland, UK, July 24-29, 2005
EditorsLiliana Ardissono, Paul Brna, Antonija Mitrovic
Place of PublicationBerlin, Germany
PublisherSpringer-Verlag
Pages297-306
Number of pages10
ISBN (Print)3540278850 , 978-3540278856
Publication statusPublished - 18 Jul 2005

Publication series

NameLecture Notes in Artificial Intelligence
PublisherSpringer-Verlag
Number3538

Fingerprint

Recommender systems

Keywords

  • user modeling
  • group modeling
  • recommender system
  • affective state

Cite this

Masthoff, J. (2005). The pursuit of satisfaction: Affective state in group recommender systems. In L. Ardissono, P. Brna, & A. Mitrovic (Eds.), User Modeling 2005: Proceedings of the 10th International Conference, UM 2005, Edinburgh, Scotland, UK, July 24-29, 2005 (pp. 297-306). (Lecture Notes in Artificial Intelligence; No. 3538). Berlin, Germany: Springer-Verlag.

The pursuit of satisfaction : Affective state in group recommender systems. / Masthoff, Judith.

User Modeling 2005: Proceedings of the 10th International Conference, UM 2005, Edinburgh, Scotland, UK, July 24-29, 2005 . ed. / Liliana Ardissono; Paul Brna; Antonija Mitrovic. Berlin, Germany : Springer-Verlag, 2005. p. 297-306 (Lecture Notes in Artificial Intelligence; No. 3538).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Masthoff, J 2005, The pursuit of satisfaction: Affective state in group recommender systems. in L Ardissono, P Brna & A Mitrovic (eds), User Modeling 2005: Proceedings of the 10th International Conference, UM 2005, Edinburgh, Scotland, UK, July 24-29, 2005 . Lecture Notes in Artificial Intelligence, no. 3538, Springer-Verlag, Berlin, Germany, pp. 297-306.
Masthoff J. The pursuit of satisfaction: Affective state in group recommender systems. In Ardissono L, Brna P, Mitrovic A, editors, User Modeling 2005: Proceedings of the 10th International Conference, UM 2005, Edinburgh, Scotland, UK, July 24-29, 2005 . Berlin, Germany: Springer-Verlag. 2005. p. 297-306. (Lecture Notes in Artificial Intelligence; 3538).
Masthoff, Judith. / The pursuit of satisfaction : Affective state in group recommender systems. User Modeling 2005: Proceedings of the 10th International Conference, UM 2005, Edinburgh, Scotland, UK, July 24-29, 2005 . editor / Liliana Ardissono ; Paul Brna ; Antonija Mitrovic. Berlin, Germany : Springer-Verlag, 2005. pp. 297-306 (Lecture Notes in Artificial Intelligence; 3538).
@inproceedings{e700b1a486c84b3cbd4495488fa15695,
title = "The pursuit of satisfaction: Affective state in group recommender systems",
abstract = "This paper describes three algorithms to model and predict the satisfaction experienced by individuals using a group recommender system which recommends sequences of items. Satisfaction is treated as an affective state. In particular, we model the wearing off of emotion over time and assimilation effects, where the affective state produced by previous items influences the impact on satisfaction of the next item. We compare the algorithms with each other, and investigate the effect of parameter values by comparing the algorithms' predictions with the results of an earlier empirical study. We show a way in which affective state can be used in recommender systems, which is useful for recommendations not only to groups but also to individuals.",
keywords = "user modeling, group modeling, recommender system, affective state",
author = "Judith Masthoff",
year = "2005",
month = "7",
day = "18",
language = "English",
isbn = "3540278850",
series = "Lecture Notes in Artificial Intelligence",
publisher = "Springer-Verlag",
number = "3538",
pages = "297--306",
editor = "Liliana Ardissono and Paul Brna and Antonija Mitrovic",
booktitle = "User Modeling 2005",

}

TY - GEN

T1 - The pursuit of satisfaction

T2 - Affective state in group recommender systems

AU - Masthoff, Judith

PY - 2005/7/18

Y1 - 2005/7/18

N2 - This paper describes three algorithms to model and predict the satisfaction experienced by individuals using a group recommender system which recommends sequences of items. Satisfaction is treated as an affective state. In particular, we model the wearing off of emotion over time and assimilation effects, where the affective state produced by previous items influences the impact on satisfaction of the next item. We compare the algorithms with each other, and investigate the effect of parameter values by comparing the algorithms' predictions with the results of an earlier empirical study. We show a way in which affective state can be used in recommender systems, which is useful for recommendations not only to groups but also to individuals.

AB - This paper describes three algorithms to model and predict the satisfaction experienced by individuals using a group recommender system which recommends sequences of items. Satisfaction is treated as an affective state. In particular, we model the wearing off of emotion over time and assimilation effects, where the affective state produced by previous items influences the impact on satisfaction of the next item. We compare the algorithms with each other, and investigate the effect of parameter values by comparing the algorithms' predictions with the results of an earlier empirical study. We show a way in which affective state can be used in recommender systems, which is useful for recommendations not only to groups but also to individuals.

KW - user modeling

KW - group modeling

KW - recommender system

KW - affective state

M3 - Conference contribution

SN - 3540278850

SN - 978-3540278856

T3 - Lecture Notes in Artificial Intelligence

SP - 297

EP - 306

BT - User Modeling 2005

A2 - Ardissono, Liliana

A2 - Brna, Paul

A2 - Mitrovic, Antonija

PB - Springer-Verlag

CY - Berlin, Germany

ER -