Exploring users' perception of collaborative explanation styles

Ludovik Coba; Markus Zanker; Laurens Rook; Panagiotis Symeonidis

doi:10.1109/CBI.2018.00017

Exploring users' perception of collaborative explanation styles

Ludovik Coba, Markus Zanker, Laurens Rook, Panagiotis Symeonidis

Economics of Technology and Innovation

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

5 Citations (Scopus)

Abstract

Collaborative filtering systems heavily depend on user feedback expressed in product ratings to select and rank items to recommend. In this study we explore how users value different collaborative explanation styles following the user-based or item-based paradigm. Furthermore, we explore how the characteristics of these rating summarizations, like the total number of ratings and the mean rating value, influence the decisions of online users. Results, based on a choice-based conjoint experimental design, show that the mean indicator has a higher impact compared to the total number of ratings. Finally, we discuss how these empirical results can serve as an input to developing algorithms that foster items with a, consequently, higher probability of choice based on their rating summarizations or their explainability due to these ratings when ranking recommendations.

Original language	English
Title of host publication	Research Papers
Editors	H.A. Proper , S. Strecker, C. Huemer
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	70-78
Number of pages	9
Volume	1
ISBN (Print)	978-153867016-3
DOIs	https://doi.org/10.1109/CBI.2018.00017
Publication status	Published - 2018
Event	20th IEEE International Conference on Business Informatics, CBI 2018 - Vienna, Austria Duration: 11 Jul 2018 → 13 Jul 2018

Conference

Conference	20th IEEE International Conference on Business Informatics, CBI 2018
Country/Territory	Austria
City	Vienna
Period	11/07/18 → 13/07/18

Keywords

Collaborative filtering
Conjoint experiment
Explanations
Recommender systems

Access to Document

10.1109/CBI.2018.00017

Cite this

@inproceedings{903b8b52b8d64fdd91c9a7ac73e1c4a2,

title = "Exploring users' perception of collaborative explanation styles",

abstract = "Collaborative filtering systems heavily depend on user feedback expressed in product ratings to select and rank items to recommend. In this study we explore how users value different collaborative explanation styles following the user-based or item-based paradigm. Furthermore, we explore how the characteristics of these rating summarizations, like the total number of ratings and the mean rating value, influence the decisions of online users. Results, based on a choice-based conjoint experimental design, show that the mean indicator has a higher impact compared to the total number of ratings. Finally, we discuss how these empirical results can serve as an input to developing algorithms that foster items with a, consequently, higher probability of choice based on their rating summarizations or their explainability due to these ratings when ranking recommendations.",

keywords = "Collaborative filtering, Conjoint experiment, Explanations, Recommender systems",

author = "Ludovik Coba and Markus Zanker and Laurens Rook and Panagiotis Symeonidis",

year = "2018",

doi = "10.1109/CBI.2018.00017",

language = "English",

isbn = "978-153867016-3",

volume = "1",

pages = "70--78",

editor = "{Proper }, H.A. and Strecker, { S.} and {Huemer }, C.",

booktitle = "Research Papers",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "20th IEEE International Conference on Business Informatics, CBI 2018 ; Conference date: 11-07-2018 Through 13-07-2018",

}

Coba, L, Zanker, M, Rook, L & Symeonidis, P 2018, Exploring users' perception of collaborative explanation styles. in HA Proper , S Strecker & C Huemer (eds), Research Papers. vol. 1, 8452660, Institute of Electrical and Electronics Engineers (IEEE), pp. 70-78, 20th IEEE International Conference on Business Informatics, CBI 2018, Vienna, Austria, 11/07/18. https://doi.org/10.1109/CBI.2018.00017

Exploring users' perception of collaborative explanation styles. / Coba, Ludovik; Zanker, Markus; Rook, Laurens et al.
Research Papers. ed. / H.A. Proper ; S. Strecker; C. Huemer . Vol. 1 Institute of Electrical and Electronics Engineers (IEEE), 2018. p. 70-78 8452660.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Exploring users' perception of collaborative explanation styles

AU - Coba, Ludovik

AU - Zanker, Markus

AU - Rook, Laurens

AU - Symeonidis, Panagiotis

PY - 2018

Y1 - 2018

N2 - Collaborative filtering systems heavily depend on user feedback expressed in product ratings to select and rank items to recommend. In this study we explore how users value different collaborative explanation styles following the user-based or item-based paradigm. Furthermore, we explore how the characteristics of these rating summarizations, like the total number of ratings and the mean rating value, influence the decisions of online users. Results, based on a choice-based conjoint experimental design, show that the mean indicator has a higher impact compared to the total number of ratings. Finally, we discuss how these empirical results can serve as an input to developing algorithms that foster items with a, consequently, higher probability of choice based on their rating summarizations or their explainability due to these ratings when ranking recommendations.

AB - Collaborative filtering systems heavily depend on user feedback expressed in product ratings to select and rank items to recommend. In this study we explore how users value different collaborative explanation styles following the user-based or item-based paradigm. Furthermore, we explore how the characteristics of these rating summarizations, like the total number of ratings and the mean rating value, influence the decisions of online users. Results, based on a choice-based conjoint experimental design, show that the mean indicator has a higher impact compared to the total number of ratings. Finally, we discuss how these empirical results can serve as an input to developing algorithms that foster items with a, consequently, higher probability of choice based on their rating summarizations or their explainability due to these ratings when ranking recommendations.

KW - Collaborative filtering

KW - Conjoint experiment

KW - Explanations

KW - Recommender systems

UR - http://www.scopus.com/inward/record.url?scp=85054078609&partnerID=8YFLogxK

U2 - 10.1109/CBI.2018.00017

DO - 10.1109/CBI.2018.00017

M3 - Conference contribution

AN - SCOPUS:85054078609

SN - 978-153867016-3

VL - 1

SP - 70

EP - 78

BT - Research Papers

A2 - Proper , H.A.

A2 - Strecker, S.

A2 - Huemer , C.

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 20th IEEE International Conference on Business Informatics, CBI 2018

Y2 - 11 July 2018 through 13 July 2018

ER -

Exploring users' perception of collaborative explanation styles

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this