Just in time recommendations - Modeling the dynamics of boredom in activity streams

Komal Kapoor, Karthik Subbian, Jaideep Srivastava, Paul Schrater

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

26 Citations (Scopus)

Abstract

Recommendation methods have mainly dealt with the problem of recommending new items to the user while user visitation be-havior to the familiar items (items which have been consumed before) are little understood. In this paper, we analyze user ac-tivity streams and show that user's temporal consumption of fa-miliar items is driven by boredom. Specifically, users move on to a different item when bored and return to the same item when their interest is restored. To model this behavior we include two latent psychological states of preference for items - sensitization and boredom. In the sensitization state the user is highly engaged with the item, while in the boredom state the user is disinterested. We model this behavior using a Hidden Semi-Markov Model for the gaps between user consumption activities. We show that our model performs much better than the state-of-the-art temporal recommendation models at predicting the revisit time to the item. Moreover, we attribute two main reasons for this: (1) recom-mending items that are not in the bored state for the user, (2)recommending items where user has restored her interests.

Original languageEnglish
Title of host publicationWSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining
PublisherAssociation for Computing Machinery, Inc
Pages233-242
Number of pages10
ISBN (Print)9781450333177
DOIs
Publication statusPublished - 2 Feb 2015
Externally publishedYes
Event8th ACM International Conference on Web Search and Data Mining, WSDM 2015 - Shanghai, China
Duration: 31 Jan 20156 Feb 2015

Other

Other8th ACM International Conference on Web Search and Data Mining, WSDM 2015
CountryChina
CityShanghai
Period31/1/156/2/15

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Kapoor, K., Subbian, K., Srivastava, J., & Schrater, P. (2015). Just in time recommendations - Modeling the dynamics of boredom in activity streams. In WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining (pp. 233-242). Association for Computing Machinery, Inc. https://doi.org/10.1145/2684822.2685306

Just in time recommendations - Modeling the dynamics of boredom in activity streams. / Kapoor, Komal; Subbian, Karthik; Srivastava, Jaideep; Schrater, Paul.

WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc, 2015. p. 233-242.

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

Kapoor, K, Subbian, K, Srivastava, J & Schrater, P 2015, Just in time recommendations - Modeling the dynamics of boredom in activity streams. in WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc, pp. 233-242, 8th ACM International Conference on Web Search and Data Mining, WSDM 2015, Shanghai, China, 31/1/15. https://doi.org/10.1145/2684822.2685306
Kapoor K, Subbian K, Srivastava J, Schrater P. Just in time recommendations - Modeling the dynamics of boredom in activity streams. In WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc. 2015. p. 233-242 https://doi.org/10.1145/2684822.2685306
Kapoor, Komal ; Subbian, Karthik ; Srivastava, Jaideep ; Schrater, Paul. / Just in time recommendations - Modeling the dynamics of boredom in activity streams. WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, Inc, 2015. pp. 233-242
@inproceedings{0c2060f5e3f4400c9f8a9e90f0b6ee06,
title = "Just in time recommendations - Modeling the dynamics of boredom in activity streams",
abstract = "Recommendation methods have mainly dealt with the problem of recommending new items to the user while user visitation be-havior to the familiar items (items which have been consumed before) are little understood. In this paper, we analyze user ac-tivity streams and show that user's temporal consumption of fa-miliar items is driven by boredom. Specifically, users move on to a different item when bored and return to the same item when their interest is restored. To model this behavior we include two latent psychological states of preference for items - sensitization and boredom. In the sensitization state the user is highly engaged with the item, while in the boredom state the user is disinterested. We model this behavior using a Hidden Semi-Markov Model for the gaps between user consumption activities. We show that our model performs much better than the state-of-the-art temporal recommendation models at predicting the revisit time to the item. Moreover, we attribute two main reasons for this: (1) recom-mending items that are not in the bored state for the user, (2)recommending items where user has restored her interests.",
author = "Komal Kapoor and Karthik Subbian and Jaideep Srivastava and Paul Schrater",
year = "2015",
month = "2",
day = "2",
doi = "10.1145/2684822.2685306",
language = "English",
isbn = "9781450333177",
pages = "233--242",
booktitle = "WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Just in time recommendations - Modeling the dynamics of boredom in activity streams

AU - Kapoor, Komal

AU - Subbian, Karthik

AU - Srivastava, Jaideep

AU - Schrater, Paul

PY - 2015/2/2

Y1 - 2015/2/2

N2 - Recommendation methods have mainly dealt with the problem of recommending new items to the user while user visitation be-havior to the familiar items (items which have been consumed before) are little understood. In this paper, we analyze user ac-tivity streams and show that user's temporal consumption of fa-miliar items is driven by boredom. Specifically, users move on to a different item when bored and return to the same item when their interest is restored. To model this behavior we include two latent psychological states of preference for items - sensitization and boredom. In the sensitization state the user is highly engaged with the item, while in the boredom state the user is disinterested. We model this behavior using a Hidden Semi-Markov Model for the gaps between user consumption activities. We show that our model performs much better than the state-of-the-art temporal recommendation models at predicting the revisit time to the item. Moreover, we attribute two main reasons for this: (1) recom-mending items that are not in the bored state for the user, (2)recommending items where user has restored her interests.

AB - Recommendation methods have mainly dealt with the problem of recommending new items to the user while user visitation be-havior to the familiar items (items which have been consumed before) are little understood. In this paper, we analyze user ac-tivity streams and show that user's temporal consumption of fa-miliar items is driven by boredom. Specifically, users move on to a different item when bored and return to the same item when their interest is restored. To model this behavior we include two latent psychological states of preference for items - sensitization and boredom. In the sensitization state the user is highly engaged with the item, while in the boredom state the user is disinterested. We model this behavior using a Hidden Semi-Markov Model for the gaps between user consumption activities. We show that our model performs much better than the state-of-the-art temporal recommendation models at predicting the revisit time to the item. Moreover, we attribute two main reasons for this: (1) recom-mending items that are not in the bored state for the user, (2)recommending items where user has restored her interests.

UR - http://www.scopus.com/inward/record.url?scp=84928712279&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84928712279&partnerID=8YFLogxK

U2 - 10.1145/2684822.2685306

DO - 10.1145/2684822.2685306

M3 - Conference contribution

SN - 9781450333177

SP - 233

EP - 242

BT - WSDM 2015 - Proceedings of the 8th ACM International Conference on Web Search and Data Mining

PB - Association for Computing Machinery, Inc

ER -