Interpreting user inaction in recommender systems

Qian Zhao, Martijn C. Willemsen, Gediminas Adomavicius, F. Maxwell Harper, Joseph A Konstan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Temporally, users browse and interact with items in recommender systems. However, for most systems, the majority of the displayed items do not elicit any action from users. In other words, the user-system interaction process includes three aspects: browsing, action, and inaction. Prior recommender systems literature has focused more on actions than on browsing or inaction. In this work, we deployed a ield survey in a live movie recommender system to interpret what inaction means from both the user's and the system's perspective, guided by psychological theories of human decision making. We further systematically study factors to infer the reasons of user inaction and demonstrate with oline data sets that this descriptive and predictive inaction model can provide beneits for recommender systems in terms of both action prediction and recommendation timing.

Original languageEnglish (US)
Title of host publicationRecSys 2018 - 12th ACM Conference on Recommender Systems
PublisherAssociation for Computing Machinery, Inc
Pages40-48
Number of pages9
ISBN (Electronic)9781450359016
DOIs
StatePublished - Sep 27 2018
Event12th ACM Conference on Recommender Systems, RecSys 2018 - Vancouver, Canada
Duration: Oct 2 2018Oct 7 2018

Publication series

NameRecSys 2018 - 12th ACM Conference on Recommender Systems

Other

Other12th ACM Conference on Recommender Systems, RecSys 2018
CountryCanada
CityVancouver
Period10/2/1810/7/18

Fingerprint

Recommender systems
Decision making

Keywords

  • Decision ield theory
  • Decision making
  • User inaction

Cite this

Zhao, Q., Willemsen, M. C., Adomavicius, G., Maxwell Harper, F., & Konstan, J. A. (2018). Interpreting user inaction in recommender systems. In RecSys 2018 - 12th ACM Conference on Recommender Systems (pp. 40-48). (RecSys 2018 - 12th ACM Conference on Recommender Systems). Association for Computing Machinery, Inc. https://doi.org/10.1145/3240323.3240366

Interpreting user inaction in recommender systems. / Zhao, Qian; Willemsen, Martijn C.; Adomavicius, Gediminas; Maxwell Harper, F.; Konstan, Joseph A.

RecSys 2018 - 12th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2018. p. 40-48 (RecSys 2018 - 12th ACM Conference on Recommender Systems).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zhao, Q, Willemsen, MC, Adomavicius, G, Maxwell Harper, F & Konstan, JA 2018, Interpreting user inaction in recommender systems. in RecSys 2018 - 12th ACM Conference on Recommender Systems. RecSys 2018 - 12th ACM Conference on Recommender Systems, Association for Computing Machinery, Inc, pp. 40-48, 12th ACM Conference on Recommender Systems, RecSys 2018, Vancouver, Canada, 10/2/18. https://doi.org/10.1145/3240323.3240366
Zhao Q, Willemsen MC, Adomavicius G, Maxwell Harper F, Konstan JA. Interpreting user inaction in recommender systems. In RecSys 2018 - 12th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc. 2018. p. 40-48. (RecSys 2018 - 12th ACM Conference on Recommender Systems). https://doi.org/10.1145/3240323.3240366
Zhao, Qian ; Willemsen, Martijn C. ; Adomavicius, Gediminas ; Maxwell Harper, F. ; Konstan, Joseph A. / Interpreting user inaction in recommender systems. RecSys 2018 - 12th ACM Conference on Recommender Systems. Association for Computing Machinery, Inc, 2018. pp. 40-48 (RecSys 2018 - 12th ACM Conference on Recommender Systems).
@inproceedings{2a52a97a23794c7e9941f2a03e527152,
title = "Interpreting user inaction in recommender systems",
abstract = "Temporally, users browse and interact with items in recommender systems. However, for most systems, the majority of the displayed items do not elicit any action from users. In other words, the user-system interaction process includes three aspects: browsing, action, and inaction. Prior recommender systems literature has focused more on actions than on browsing or inaction. In this work, we deployed a ield survey in a live movie recommender system to interpret what inaction means from both the user's and the system's perspective, guided by psychological theories of human decision making. We further systematically study factors to infer the reasons of user inaction and demonstrate with oline data sets that this descriptive and predictive inaction model can provide beneits for recommender systems in terms of both action prediction and recommendation timing.",
keywords = "Decision ield theory, Decision making, User inaction",
author = "Qian Zhao and Willemsen, {Martijn C.} and Gediminas Adomavicius and {Maxwell Harper}, F. and Konstan, {Joseph A}",
year = "2018",
month = "9",
day = "27",
doi = "10.1145/3240323.3240366",
language = "English (US)",
series = "RecSys 2018 - 12th ACM Conference on Recommender Systems",
publisher = "Association for Computing Machinery, Inc",
pages = "40--48",
booktitle = "RecSys 2018 - 12th ACM Conference on Recommender Systems",

}

TY - GEN

T1 - Interpreting user inaction in recommender systems

AU - Zhao, Qian

AU - Willemsen, Martijn C.

AU - Adomavicius, Gediminas

AU - Maxwell Harper, F.

AU - Konstan, Joseph A

PY - 2018/9/27

Y1 - 2018/9/27

N2 - Temporally, users browse and interact with items in recommender systems. However, for most systems, the majority of the displayed items do not elicit any action from users. In other words, the user-system interaction process includes three aspects: browsing, action, and inaction. Prior recommender systems literature has focused more on actions than on browsing or inaction. In this work, we deployed a ield survey in a live movie recommender system to interpret what inaction means from both the user's and the system's perspective, guided by psychological theories of human decision making. We further systematically study factors to infer the reasons of user inaction and demonstrate with oline data sets that this descriptive and predictive inaction model can provide beneits for recommender systems in terms of both action prediction and recommendation timing.

AB - Temporally, users browse and interact with items in recommender systems. However, for most systems, the majority of the displayed items do not elicit any action from users. In other words, the user-system interaction process includes three aspects: browsing, action, and inaction. Prior recommender systems literature has focused more on actions than on browsing or inaction. In this work, we deployed a ield survey in a live movie recommender system to interpret what inaction means from both the user's and the system's perspective, guided by psychological theories of human decision making. We further systematically study factors to infer the reasons of user inaction and demonstrate with oline data sets that this descriptive and predictive inaction model can provide beneits for recommender systems in terms of both action prediction and recommendation timing.

KW - Decision ield theory

KW - Decision making

KW - User inaction

UR - http://www.scopus.com/inward/record.url?scp=85056793254&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056793254&partnerID=8YFLogxK

U2 - 10.1145/3240323.3240366

DO - 10.1145/3240323.3240366

M3 - Conference contribution

T3 - RecSys 2018 - 12th ACM Conference on Recommender Systems

SP - 40

EP - 48

BT - RecSys 2018 - 12th ACM Conference on Recommender Systems

PB - Association for Computing Machinery, Inc

ER -