The Immunity of Users’ Item Selection from Serial Position Effects in Multi-Attribute Item Recommendation Scenarios

Trang Tran; Carmen Isabella Baumann; Alexander Felfernig; Viet-Man Le

The Immunity of Users’ Item Selection from Serial Position Effects in Multi-Attribute Item Recommendation Scenarios

Trang Tran, Carmen Isabella Baumann, Alexander Felfernig, Viet-Man Le

Institute of Software Technology (7160)

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

Abstract

Serial position effects are triggered in recommendation scenarios where users focus on evaluating items shown at the beginning and at the end of a list. In this paper, we analyze these effects in the context of multi-attribute item recommendation scenarios where the recommended items are presented to users in the form of a list of relevant attributes. We conducted a user study in different item domains to examine if the item selection of users is affected by the order of the attributes of the recommended items presented to them. The experimental results show that the order of the attributes does not affect users’ item selection. When selecting a recommended item, users tend to focus on evaluating the value of the attributes that reflect their preferences for the desired item but do not care about the order of the attributes. This finding brings us to a conclusion that in the context of multi-attribute item recommendation scenarios, the selection of a recommended item from a list of candidate items is immune to serial position effects.

Original language	English
Title of host publication	Proceedings of the 8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS 2021), Online Event, September 25 and September 29, 2021.
Subtitle of host publication	co-located with 15th ACM Conference on Recommender Systems (RecSys 2021)
Editors	Peter Brusilovsky, Marco de Gemmis, Alexander Felfernig, Elisabeth Lex, Pasquale Lops, Giovanni Semeraro, Martijn C. Willemsen
Pages	101-111
Number of pages	11
Volume	2948
Publication status	Published - 20 Sept 2021
Event	8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems: co-located with 15th ACM Conference on Recommender Systems (RecSys 2021) - Amsterdam, Netherlands, Amsterdam, Netherlands Duration: 25 Sept 2021 → 29 Sept 2021 https://recsys.acm.org/recsys21/intrs/

Publication series

Name	CEUR Workshop Proceedings
Volume	2948
ISSN (Electronic)	1613-0073

Workshop

Workshop	8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems
Abbreviated title	IntRS 2021
Country/Territory	Netherlands
City	Amsterdam
Period	25/09/21 → 29/09/21
Internet address	https://recsys.acm.org/recsys21/intrs/

Keywords

Decision biases
Human decision making
Item selection
Multi-attribute items
Recommender systems
Serial position effects

ASJC Scopus subject areas

Computer Science(all)

Access to Document

http://ceur-ws.org/Vol-2948/short2.pdfLicence: CC BY 4.0

Cite this

Tran, T., Baumann, C. I., Felfernig, A., & Le, V-M. (2021). The Immunity of Users’ Item Selection from Serial Position Effects in Multi-Attribute Item Recommendation Scenarios. In P. Brusilovsky, M. de Gemmis, A. Felfernig, E. Lex, P. Lops, G. Semeraro, & M. C. Willemsen (Eds.), Proceedings of the 8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS 2021), Online Event, September 25 and September 29, 2021.: co-located with 15th ACM Conference on Recommender Systems (RecSys 2021) (Vol. 2948, pp. 101-111). (CEUR Workshop Proceedings; Vol. 2948). http://ceur-ws.org/Vol-2948/short2.pdf

The Immunity of Users’ Item Selection from Serial Position Effects in Multi-Attribute Item Recommendation Scenarios. / Tran, Trang; Baumann, Carmen Isabella; Felfernig, Alexander et al.

Proceedings of the 8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS 2021), Online Event, September 25 and September 29, 2021.: co-located with 15th ACM Conference on Recommender Systems (RecSys 2021). ed. / Peter Brusilovsky; Marco de Gemmis; Alexander Felfernig; Elisabeth Lex; Pasquale Lops; Giovanni Semeraro; Martijn C. Willemsen. Vol. 2948 2021. p. 101-111 (CEUR Workshop Proceedings; Vol. 2948).

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

Tran, T, Baumann, CI, Felfernig, A & Le, V-M 2021, The Immunity of Users’ Item Selection from Serial Position Effects in Multi-Attribute Item Recommendation Scenarios. in P Brusilovsky, M de Gemmis, A Felfernig, E Lex, P Lops, G Semeraro & MC Willemsen (eds), Proceedings of the 8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS 2021), Online Event, September 25 and September 29, 2021.: co-located with 15th ACM Conference on Recommender Systems (RecSys 2021). vol. 2948, CEUR Workshop Proceedings, vol. 2948, pp. 101-111, 8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems, Amsterdam, Netherlands, 25/09/21. <http://ceur-ws.org/Vol-2948/short2.pdf>

Tran T, Baumann CI, Felfernig A , Le V-M. The Immunity of Users’ Item Selection from Serial Position Effects in Multi-Attribute Item Recommendation Scenarios. In Brusilovsky P, de Gemmis M, Felfernig A, Lex E, Lops P, Semeraro G, Willemsen MC, editors, Proceedings of the 8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS 2021), Online Event, September 25 and September 29, 2021.: co-located with 15th ACM Conference on Recommender Systems (RecSys 2021). Vol. 2948. 2021. p. 101-111. (CEUR Workshop Proceedings).

Tran, Trang ; Baumann, Carmen Isabella ; Felfernig, Alexander et al. / The Immunity of Users’ Item Selection from Serial Position Effects in Multi-Attribute Item Recommendation Scenarios. Proceedings of the 8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS 2021), Online Event, September 25 and September 29, 2021.: co-located with 15th ACM Conference on Recommender Systems (RecSys 2021). editor / Peter Brusilovsky ; Marco de Gemmis ; Alexander Felfernig ; Elisabeth Lex ; Pasquale Lops ; Giovanni Semeraro ; Martijn C. Willemsen. Vol. 2948 2021. pp. 101-111 (CEUR Workshop Proceedings).

@inproceedings{62dea9ac45f948a5bcc11885fa14c35a,

title = "The Immunity of Users{\textquoteright} Item Selection from Serial Position Effects in Multi-Attribute Item Recommendation Scenarios",

abstract = "Serial position effects are triggered in recommendation scenarios where users focus on evaluating items shown at the beginning and at the end of a list. In this paper, we analyze these effects in the context of multi-attribute item recommendation scenarios where the recommended items are presented to users in the form of a list of relevant attributes. We conducted a user study in different item domains to examine if the item selection of users is affected by the order of the attributes of the recommended items presented to them. The experimental results show that the order of the attributes does not affect users{\textquoteright} item selection. When selecting a recommended item, users tend to focus on evaluating the value of the attributes that reflect their preferences for the desired item but do not care about the order of the attributes. This finding brings us to a conclusion that in the context of multi-attribute item recommendation scenarios, the selection of a recommended item from a list of candidate items is immune to serial position effects.",

keywords = "Decision biases, Human decision making, Item selection, Multi-attribute items, Recommender systems, Serial position effects",

author = "Trang Tran and Baumann, {Carmen Isabella} and Alexander Felfernig and Viet-Man Le",

year = "2021",

month = sep,

day = "20",

language = "English",

volume = "2948",

series = "CEUR Workshop Proceedings",

pages = "101--111",

editor = "Peter Brusilovsky and {de Gemmis}, Marco and Alexander Felfernig and Elisabeth Lex and Pasquale Lops and Giovanni Semeraro and Willemsen, {Martijn C.}",

booktitle = "Proceedings of the 8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS 2021), Online Event, September 25 and September 29, 2021.",

note = "8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems : co-located with 15th ACM Conference on Recommender Systems (RecSys 2021), IntRS 2021 ; Conference date: 25-09-2021 Through 29-09-2021",

url = "https://recsys.acm.org/recsys21/intrs/",

}

TY - GEN

T1 - The Immunity of Users’ Item Selection from Serial Position Effects in Multi-Attribute Item Recommendation Scenarios

AU - Tran, Trang

AU - Baumann, Carmen Isabella

AU - Felfernig, Alexander

AU - Le, Viet-Man

PY - 2021/9/20

Y1 - 2021/9/20

N2 - Serial position effects are triggered in recommendation scenarios where users focus on evaluating items shown at the beginning and at the end of a list. In this paper, we analyze these effects in the context of multi-attribute item recommendation scenarios where the recommended items are presented to users in the form of a list of relevant attributes. We conducted a user study in different item domains to examine if the item selection of users is affected by the order of the attributes of the recommended items presented to them. The experimental results show that the order of the attributes does not affect users’ item selection. When selecting a recommended item, users tend to focus on evaluating the value of the attributes that reflect their preferences for the desired item but do not care about the order of the attributes. This finding brings us to a conclusion that in the context of multi-attribute item recommendation scenarios, the selection of a recommended item from a list of candidate items is immune to serial position effects.

AB - Serial position effects are triggered in recommendation scenarios where users focus on evaluating items shown at the beginning and at the end of a list. In this paper, we analyze these effects in the context of multi-attribute item recommendation scenarios where the recommended items are presented to users in the form of a list of relevant attributes. We conducted a user study in different item domains to examine if the item selection of users is affected by the order of the attributes of the recommended items presented to them. The experimental results show that the order of the attributes does not affect users’ item selection. When selecting a recommended item, users tend to focus on evaluating the value of the attributes that reflect their preferences for the desired item but do not care about the order of the attributes. This finding brings us to a conclusion that in the context of multi-attribute item recommendation scenarios, the selection of a recommended item from a list of candidate items is immune to serial position effects.

KW - Decision biases

KW - Human decision making

KW - Item selection

KW - Multi-attribute items

KW - Recommender systems

KW - Serial position effects

UR - http://www.scopus.com/inward/record.url?scp=85115762424&partnerID=8YFLogxK

M3 - Conference paper

VL - 2948

T3 - CEUR Workshop Proceedings

SP - 101

EP - 111

BT - Proceedings of the 8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS 2021), Online Event, September 25 and September 29, 2021.

A2 - Brusilovsky, Peter

A2 - de Gemmis, Marco

A2 - Felfernig, Alexander

A2 - Lex, Elisabeth

A2 - Lops, Pasquale

A2 - Semeraro, Giovanni

A2 - Willemsen, Martijn C.

T2 - 8th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems

Y2 - 25 September 2021 through 29 September 2021

ER -

The Immunity of Users’ Item Selection from Serial Position Effects in Multi-Attribute Item Recommendation Scenarios

Abstract

Publication series

Workshop

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Cite this