Prediction of Hedonic and Eudaimonic Characteristics from User Interactions

Marko Tkalcic; Elham Motamedi; Francesco Barile; Eva Puc; Urša Mars Bitenc

doi:10.1145/3511047.3537656

Prediction of Hedonic and Eudaimonic Characteristics from User Interactions

Marko Tkalcic, Elham Motamedi, Francesco Barile, Eva Puc, Urša Mars Bitenc

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

Abstract

Content-based recommender (CBR) systems take advantage of item characteristics and user propensities for these characteristics in order to select the items that are better suited for a user. Related work has shown that the characteristics of hedonia (pleasure) and eudaimonia (deeper meaning) account for user preferences in the domain of movies. However, labeling items with hedonic/eudaimonic properties and measuring user propensity for eudaimonic/hedonic experiences could be done only through questionnaires. In this work we present the results of our work-in-progress on the prediction of user propensities for eudaimonic and hedonic experiences from a movie preferences dataset. Our results indicate that a range of classifiers that use ratings of movies as features perform substantially better than the average baseline.

Original language	English
Title of host publication	Adjunct Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization
Place of Publication	New York, NY, USA
Publisher	Association for Computing Machinery
Pages	366–370
ISBN (Print)	9781450392327
DOIs	https://doi.org/10.1145/3511047.3537656
Publication status	Published - 2022
Event	30th ACM Conference on User Modeling, Adaptation and Personalization - Barcelona, Spain Duration: 4 Jul 2022 → 7 Jul 2022 https://www.um.org/umap2022/

Conference

Conference	30th ACM Conference on User Modeling, Adaptation and Personalization
Abbreviated title	UMAP 2022
Country/Territory	Spain
City	Barcelona
Period	4/07/22 → 7/07/22
Internet address	https://www.um.org/umap2022/

Keywords

hedonia
movie recommendations
eudaimonia

Access to Document

10.1145/3511047.3537656

https://doi.org/10.1145/3511047.3537656

Cite this

@inproceedings{e64a8a823c4a4016b3d6eed1e25b5e73,

title = "Prediction of Hedonic and Eudaimonic Characteristics from User Interactions",

abstract = "Content-based recommender (CBR) systems take advantage of item characteristics and user propensities for these characteristics in order to select the items that are better suited for a user. Related work has shown that the characteristics of hedonia (pleasure) and eudaimonia (deeper meaning) account for user preferences in the domain of movies. However, labeling items with hedonic/eudaimonic properties and measuring user propensity for eudaimonic/hedonic experiences could be done only through questionnaires. In this work we present the results of our work-in-progress on the prediction of user propensities for eudaimonic and hedonic experiences from a movie preferences dataset. Our results indicate that a range of classifiers that use ratings of movies as features perform substantially better than the average baseline.",

keywords = "hedonia, movie recommendations, eudaimonia",

author = "Marko Tkalcic and Elham Motamedi and Francesco Barile and Eva Puc and {Mars Bitenc}, Ur{\v s}a",

note = "Publisher Copyright: {\textcopyright} 2022 ACM.; 30th ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2022 ; Conference date: 04-07-2022 Through 07-07-2022",

year = "2022",

doi = "10.1145/3511047.3537656",

language = "English",

isbn = "9781450392327",

pages = "366–370",

booktitle = "Adjunct Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization",

publisher = "Association for Computing Machinery",

address = "United States",

url = "https://www.um.org/umap2022/",

}

Tkalcic, M, Motamedi, E, Barile, F, Puc, E & Mars Bitenc, U 2022, Prediction of Hedonic and Eudaimonic Characteristics from User Interactions. in Adjunct Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization. Association for Computing Machinery, New York, NY, USA, pp. 366–370, 30th ACM Conference on User Modeling, Adaptation and Personalization, Barcelona, Spain, 4/07/22. https://doi.org/10.1145/3511047.3537656

Prediction of Hedonic and Eudaimonic Characteristics from User Interactions. / Tkalcic, Marko; Motamedi, Elham; Barile, Francesco et al.
Adjunct Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization. New York, NY, USA: Association for Computing Machinery, 2022. p. 366–370.

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

TY - GEN

T1 - Prediction of Hedonic and Eudaimonic Characteristics from User Interactions

AU - Tkalcic, Marko

AU - Motamedi, Elham

AU - Barile, Francesco

AU - Puc, Eva

AU - Mars Bitenc, Urša

PY - 2022

Y1 - 2022

N2 - Content-based recommender (CBR) systems take advantage of item characteristics and user propensities for these characteristics in order to select the items that are better suited for a user. Related work has shown that the characteristics of hedonia (pleasure) and eudaimonia (deeper meaning) account for user preferences in the domain of movies. However, labeling items with hedonic/eudaimonic properties and measuring user propensity for eudaimonic/hedonic experiences could be done only through questionnaires. In this work we present the results of our work-in-progress on the prediction of user propensities for eudaimonic and hedonic experiences from a movie preferences dataset. Our results indicate that a range of classifiers that use ratings of movies as features perform substantially better than the average baseline.

AB - Content-based recommender (CBR) systems take advantage of item characteristics and user propensities for these characteristics in order to select the items that are better suited for a user. Related work has shown that the characteristics of hedonia (pleasure) and eudaimonia (deeper meaning) account for user preferences in the domain of movies. However, labeling items with hedonic/eudaimonic properties and measuring user propensity for eudaimonic/hedonic experiences could be done only through questionnaires. In this work we present the results of our work-in-progress on the prediction of user propensities for eudaimonic and hedonic experiences from a movie preferences dataset. Our results indicate that a range of classifiers that use ratings of movies as features perform substantially better than the average baseline.

KW - hedonia

KW - movie recommendations

KW - eudaimonia

U2 - 10.1145/3511047.3537656

DO - 10.1145/3511047.3537656

M3 - Conference article in proceeding

SN - 9781450392327

SP - 366

EP - 370

BT - Adjunct Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization

PB - Association for Computing Machinery

CY - New York, NY, USA

T2 - 30th ACM Conference on User Modeling, Adaptation and Personalization

Y2 - 4 July 2022 through 7 July 2022

ER -