In pursuit of satisfaction and the prevention of embarrassment

affective state in group recommender systems

Judith Masthoff, Albert Gatt

Research output: Contribution to journalArticle

96 Citations (Scopus)
7 Downloads (Pure)

Abstract

This paper deals in depth with some of the emotions that play a role in a group recommender system, which recommends sequences of items to a group of users. First, it describes algorithms to model and predict the satisfaction experienced by individuals. Satisfaction is treated as an affective state. In particular, we model the decay 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 discuss the difficulty of evaluating affective models, and present an experiment in a learning domain to show how some empirical evaluation can be done. Secondly, this paper proposes modifications to the algorithms to deal with the effect on an individual's satisfaction of that of others in the group. In particular, we model emotional contagion and conformity, and consider the impact of different relationship types. Thirdly, this paper explores the issue of privacy (feeling safe, not accidentally disclosing private tastes to others in the group) which is related to the emotion of embarrassment. It investigates the effect on privacy of different group aggregation strategies and proposes to add a virtual member to the group to further improve privacy.

Original languageEnglish
Pages (from-to)281-319
Number of pages39
JournalUser Modelling and User-Adapted Interaction
Volume16
Issue number3-4
DOIs
Publication statusPublished - Sep 2006

Keywords

  • group modelling
  • affective state
  • satisfaction
  • recommender systems
  • privacy
  • emotional contagion
  • individual-differences
  • mood
  • behavior
  • television
  • context
  • program
  • impact
  • Group modelling
  • Affective state
  • Satisfaction
  • Recommender systems
  • Privacy

Cite this

In pursuit of satisfaction and the prevention of embarrassment : affective state in group recommender systems. / Masthoff, Judith; Gatt, Albert.

In: User Modelling and User-Adapted Interaction, Vol. 16, No. 3-4, 09.2006, p. 281-319.

Research output: Contribution to journalArticle

@article{73c05d892c5b44dc9d8e7e184bac6122,
title = "In pursuit of satisfaction and the prevention of embarrassment: affective state in group recommender systems",
abstract = "This paper deals in depth with some of the emotions that play a role in a group recommender system, which recommends sequences of items to a group of users. First, it describes algorithms to model and predict the satisfaction experienced by individuals. Satisfaction is treated as an affective state. In particular, we model the decay 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 discuss the difficulty of evaluating affective models, and present an experiment in a learning domain to show how some empirical evaluation can be done. Secondly, this paper proposes modifications to the algorithms to deal with the effect on an individual's satisfaction of that of others in the group. In particular, we model emotional contagion and conformity, and consider the impact of different relationship types. Thirdly, this paper explores the issue of privacy (feeling safe, not accidentally disclosing private tastes to others in the group) which is related to the emotion of embarrassment. It investigates the effect on privacy of different group aggregation strategies and proposes to add a virtual member to the group to further improve privacy.",
keywords = "group modelling, affective state, satisfaction, recommender systems, privacy, emotional contagion, individual-differences, mood, behavior, television, context, program, impact, Group modelling, Affective state, Satisfaction, Recommender systems, Privacy",
author = "Judith Masthoff and Albert Gatt",
year = "2006",
month = "9",
doi = "10.1007/s11257-006-9008-3",
language = "English",
volume = "16",
pages = "281--319",
journal = "User Modelling and User-Adapted Interaction",
issn = "0924-1868",
publisher = "Springer Netherlands",
number = "3-4",

}

TY - JOUR

T1 - In pursuit of satisfaction and the prevention of embarrassment

T2 - affective state in group recommender systems

AU - Masthoff, Judith

AU - Gatt, Albert

PY - 2006/9

Y1 - 2006/9

N2 - This paper deals in depth with some of the emotions that play a role in a group recommender system, which recommends sequences of items to a group of users. First, it describes algorithms to model and predict the satisfaction experienced by individuals. Satisfaction is treated as an affective state. In particular, we model the decay 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 discuss the difficulty of evaluating affective models, and present an experiment in a learning domain to show how some empirical evaluation can be done. Secondly, this paper proposes modifications to the algorithms to deal with the effect on an individual's satisfaction of that of others in the group. In particular, we model emotional contagion and conformity, and consider the impact of different relationship types. Thirdly, this paper explores the issue of privacy (feeling safe, not accidentally disclosing private tastes to others in the group) which is related to the emotion of embarrassment. It investigates the effect on privacy of different group aggregation strategies and proposes to add a virtual member to the group to further improve privacy.

AB - This paper deals in depth with some of the emotions that play a role in a group recommender system, which recommends sequences of items to a group of users. First, it describes algorithms to model and predict the satisfaction experienced by individuals. Satisfaction is treated as an affective state. In particular, we model the decay 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 discuss the difficulty of evaluating affective models, and present an experiment in a learning domain to show how some empirical evaluation can be done. Secondly, this paper proposes modifications to the algorithms to deal with the effect on an individual's satisfaction of that of others in the group. In particular, we model emotional contagion and conformity, and consider the impact of different relationship types. Thirdly, this paper explores the issue of privacy (feeling safe, not accidentally disclosing private tastes to others in the group) which is related to the emotion of embarrassment. It investigates the effect on privacy of different group aggregation strategies and proposes to add a virtual member to the group to further improve privacy.

KW - group modelling

KW - affective state

KW - satisfaction

KW - recommender systems

KW - privacy

KW - emotional contagion

KW - individual-differences

KW - mood

KW - behavior

KW - television

KW - context

KW - program

KW - impact

KW - Group modelling

KW - Affective state

KW - Satisfaction

KW - Recommender systems

KW - Privacy

U2 - 10.1007/s11257-006-9008-3

DO - 10.1007/s11257-006-9008-3

M3 - Article

VL - 16

SP - 281

EP - 319

JO - User Modelling and User-Adapted Interaction

JF - User Modelling and User-Adapted Interaction

SN - 0924-1868

IS - 3-4

ER -