Each to his own: how different users call for different interaction methods in recommender systems

B.P. Knijnenburg; N.J.M. Reijmer; M.C. Willemsen

doi:10.1145/2043932.2043960

Each to his own: how different users call for different interaction methods in recommender systems

B.P. Knijnenburg, N.J.M. Reijmer, M.C. Willemsen

Human Technology Interaction

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

109 Citations (Scopus)

1 Downloads (Pure)

Abstract

This paper compares five different ways of interacting with an attribute-based recommender system and shows that different types of users prefer different interaction methods. In an online experiment with an energy-saving recommender system the interaction methods are compared in terms of perceived control, understandability, trust in the system, user interface satisfaction, system effectiveness and choice satisfaction. The comparison takes into account several user characteristics, namely domain knowledge, trusting propensity and persistence. The results show that most users (and particularly domain experts) are most satisfied with a hybrid recommender that combines implicit and explicit preference elicitation, but that novices and maximizers seem to benefit more from a non-personalized recommender that just displays the most popular items.

Original language	English
Title of host publication	RecSys '11 Proceedings of the fifth ACM International Conference on Recommender Systems, 23-27 October 2011, Chicago, Il., USA
Editors	B. Mobasher, R. Burke
Place of Publication	New York
Publisher	Association for Computing Machinery, Inc
Pages	141-148
ISBN (Print)	978-1-4503-0689-6
DOIs	https://doi.org/10.1145/2043932.2043960
Publication status	Published - 2011
Event	5th ACM Conference on Recommender Systems (RecSys 2011) - Chicago, United States Duration: 23 Oct 2011 → 27 Oct 2011 Conference number: 5 https://recsys.acm.org/recsys11

Conference

Conference	5th ACM Conference on Recommender Systems (RecSys 2011)
Abbreviated title	RecSys 2011
Country/Territory	United States
City	Chicago
Period	23/10/11 → 27/10/11
Internet address	https://recsys.acm.org/recsys11

Access to Document

10.1145/2043932.2043960

Cite this

Knijnenburg, B. P., Reijmer, N. J. M., & Willemsen, M. C. (2011). Each to his own: how different users call for different interaction methods in recommender systems. In B. Mobasher, & R. Burke (Eds.), RecSys '11 Proceedings of the fifth ACM International Conference on Recommender Systems, 23-27 October 2011, Chicago, Il., USA (pp. 141-148). Association for Computing Machinery, Inc. https://doi.org/10.1145/2043932.2043960

Knijnenburg, B.P. ; Reijmer, N.J.M. ; Willemsen, M.C. / Each to his own: how different users call for different interaction methods in recommender systems. RecSys '11 Proceedings of the fifth ACM International Conference on Recommender Systems, 23-27 October 2011, Chicago, Il., USA. editor / B. Mobasher ; R. Burke. New York : Association for Computing Machinery, Inc, 2011. pp. 141-148

@inproceedings{4f71921b67ab4ef5b1a9d1981b419a3f,

title = "Each to his own: how different users call for different interaction methods in recommender systems",

abstract = "This paper compares five different ways of interacting with an attribute-based recommender system and shows that different types of users prefer different interaction methods. In an online experiment with an energy-saving recommender system the interaction methods are compared in terms of perceived control, understandability, trust in the system, user interface satisfaction, system effectiveness and choice satisfaction. The comparison takes into account several user characteristics, namely domain knowledge, trusting propensity and persistence. The results show that most users (and particularly domain experts) are most satisfied with a hybrid recommender that combines implicit and explicit preference elicitation, but that novices and maximizers seem to benefit more from a non-personalized recommender that just displays the most popular items.",

author = "B.P. Knijnenburg and N.J.M. Reijmer and M.C. Willemsen",

year = "2011",

doi = "10.1145/2043932.2043960",

language = "English",

isbn = "978-1-4503-0689-6",

pages = "141--148",

editor = "B. Mobasher and R. Burke",

booktitle = "RecSys '11 Proceedings of the fifth ACM International Conference on Recommender Systems, 23-27 October 2011, Chicago, Il., USA",

publisher = "Association for Computing Machinery, Inc",

address = "United States",

note = "5th ACM Conference on Recommender Systems (RecSys 2011), RecSys 2011 ; Conference date: 23-10-2011 Through 27-10-2011",

url = "https://recsys.acm.org/recsys11",

}

Knijnenburg, BP, Reijmer, NJM & Willemsen, MC 2011, Each to his own: how different users call for different interaction methods in recommender systems. in B Mobasher & R Burke (eds), RecSys '11 Proceedings of the fifth ACM International Conference on Recommender Systems, 23-27 October 2011, Chicago, Il., USA. Association for Computing Machinery, Inc, New York, pp. 141-148, 5th ACM Conference on Recommender Systems (RecSys 2011), Chicago, Illinois, United States, 23/10/11. https://doi.org/10.1145/2043932.2043960

Each to his own: how different users call for different interaction methods in recommender systems. / Knijnenburg, B.P.; Reijmer, N.J.M.; Willemsen, M.C.
RecSys '11 Proceedings of the fifth ACM International Conference on Recommender Systems, 23-27 October 2011, Chicago, Il., USA. ed. / B. Mobasher; R. Burke. New York: Association for Computing Machinery, Inc, 2011. p. 141-148.

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

TY - GEN

T1 - Each to his own: how different users call for different interaction methods in recommender systems

AU - Knijnenburg, B.P.

AU - Reijmer, N.J.M.

AU - Willemsen, M.C.

N1 - Conference code: 5

PY - 2011

Y1 - 2011

N2 - This paper compares five different ways of interacting with an attribute-based recommender system and shows that different types of users prefer different interaction methods. In an online experiment with an energy-saving recommender system the interaction methods are compared in terms of perceived control, understandability, trust in the system, user interface satisfaction, system effectiveness and choice satisfaction. The comparison takes into account several user characteristics, namely domain knowledge, trusting propensity and persistence. The results show that most users (and particularly domain experts) are most satisfied with a hybrid recommender that combines implicit and explicit preference elicitation, but that novices and maximizers seem to benefit more from a non-personalized recommender that just displays the most popular items.

AB - This paper compares five different ways of interacting with an attribute-based recommender system and shows that different types of users prefer different interaction methods. In an online experiment with an energy-saving recommender system the interaction methods are compared in terms of perceived control, understandability, trust in the system, user interface satisfaction, system effectiveness and choice satisfaction. The comparison takes into account several user characteristics, namely domain knowledge, trusting propensity and persistence. The results show that most users (and particularly domain experts) are most satisfied with a hybrid recommender that combines implicit and explicit preference elicitation, but that novices and maximizers seem to benefit more from a non-personalized recommender that just displays the most popular items.

U2 - 10.1145/2043932.2043960

DO - 10.1145/2043932.2043960

M3 - Conference contribution

SN - 978-1-4503-0689-6

SP - 141

EP - 148

BT - RecSys '11 Proceedings of the fifth ACM International Conference on Recommender Systems, 23-27 October 2011, Chicago, Il., USA

A2 - Mobasher, B.

A2 - Burke, R.

PB - Association for Computing Machinery, Inc

CY - New York

T2 - 5th ACM Conference on Recommender Systems (RecSys 2011)

Y2 - 23 October 2011 through 27 October 2011

ER -

Knijnenburg BP, Reijmer NJM, Willemsen MC. Each to his own: how different users call for different interaction methods in recommender systems. In Mobasher B, Burke R, editors, RecSys '11 Proceedings of the fifth ACM International Conference on Recommender Systems, 23-27 October 2011, Chicago, Il., USA. New York: Association for Computing Machinery, Inc. 2011. p. 141-148 doi: 10.1145/2043932.2043960

Each to his own: how different users call for different interaction methods in recommender systems

Abstract

Conference

Access to Document

Fingerprint

Cite this