Relevance Models for Multi-Contextual Appropriateness in Point-of-Interest Recommendation

Anirban Chakraborty; Debasis Ganguly; Owen Conlan

doi:10.1145/3397271.3401197

Relevance Models for Multi-Contextual Appropriateness in Point-of-Interest Recommendation

Anirban Chakraborty, Debasis Ganguly, Owen Conlan

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Trip-qualifiers, such as 'trip-type' (vacation, work etc.), 'accompanied-by' (e.g., solo, friends, family etc.) are potentially useful sources of information that could be used to improve the effectiveness of POI recommendation in a current context (with a given set of these constraints). Using such information is not straight forward because a user's text reviews about the POIs visited in the past do not explicitly contain such annotations (e.g., a positive review about a pub visit does not contain the information on whether the user was with friends or alone, on a business trip or vacation). We propose to use a small set of manually compiled knowledge resource to predict the associations between the review texts in a user profile and the likely trip contexts. We demonstrate that incorporating this information within an IR-based relevance modeling framework significantly improves POI recommendation.

Original language	English
Title of host publication	Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
Place of Publication	New York, NY, USA
Publisher	Association for Computing Machinery, Inc
Pages	1981–1984
ISBN (Print)	9781450380164
DOIs	https://doi.org/10.1145/3397271.3401197
Publication status	Published - 25 Jul 2020
Event	43rd International ACM SIGIR Conference on Research and Development in Information Retrieval - Online Conference Duration: 25 Jul 2020 → 30 Jul 2020 Conference number: 43 https://sigir.org/sigir2020/

Publication series

Name	SIGIR '20
Publisher	Association for Computing Machinery

Conference

Conference	43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
Abbreviated title	SIGIR 2020
Period	25/07/20 → 30/07/20
Internet address	https://sigir.org/sigir2020/

Keywords / Materials (for Non-textual outputs)

joint context modeling
weak supervision
point-of-interest recommendation

Access to Document

10.1145/3397271.3401197Licence: All Rights Reserved

https://dl.acm.org/doi/10.1145/3397271.3401197Licence: All Rights Reserved

Cite this

Chakraborty, A., Ganguly, D., & Conlan, O. (2020). Relevance Models for Multi-Contextual Appropriateness in Point-of-Interest Recommendation. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 1981–1984). (SIGIR '20). Association for Computing Machinery, Inc. https://doi.org/10.1145/3397271.3401197

@inproceedings{ad4a146754b5412ba816b760d73041cf,

title = "Relevance Models for Multi-Contextual Appropriateness in Point-of-Interest Recommendation",

abstract = "Trip-qualifiers, such as 'trip-type' (vacation, work etc.), 'accompanied-by' (e.g., solo, friends, family etc.) are potentially useful sources of information that could be used to improve the effectiveness of POI recommendation in a current context (with a given set of these constraints). Using such information is not straight forward because a user's text reviews about the POIs visited in the past do not explicitly contain such annotations (e.g., a positive review about a pub visit does not contain the information on whether the user was with friends or alone, on a business trip or vacation). We propose to use a small set of manually compiled knowledge resource to predict the associations between the review texts in a user profile and the likely trip contexts. We demonstrate that incorporating this information within an IR-based relevance modeling framework significantly improves POI recommendation.",

keywords = "joint context modeling, weak supervision, point-of-interest recommendation",

author = "Anirban Chakraborty and Debasis Ganguly and Owen Conlan",

year = "2020",

month = jul,

day = "25",

doi = "10.1145/3397271.3401197",

language = "English",

isbn = "9781450380164",

series = "SIGIR '20",

publisher = "Association for Computing Machinery, Inc",

pages = "1981–1984",

booktitle = "Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval",

note = "43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020 ; Conference date: 25-07-2020 Through 30-07-2020",

url = "https://sigir.org/sigir2020/",

}

Chakraborty, A, Ganguly, D & Conlan, O 2020, Relevance Models for Multi-Contextual Appropriateness in Point-of-Interest Recommendation. in Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR '20, Association for Computing Machinery, Inc, New York, NY, USA, pp. 1981–1984, 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 25/07/20. https://doi.org/10.1145/3397271.3401197

Relevance Models for Multi-Contextual Appropriateness in Point-of-Interest Recommendation. / Chakraborty, Anirban; Ganguly, Debasis; Conlan, Owen.
Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, NY, USA: Association for Computing Machinery, Inc, 2020. p. 1981–1984 (SIGIR '20).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Relevance Models for Multi-Contextual Appropriateness in Point-of-Interest Recommendation

AU - Chakraborty, Anirban

AU - Ganguly, Debasis

AU - Conlan, Owen

N1 - Conference code: 43

PY - 2020/7/25

Y1 - 2020/7/25

N2 - Trip-qualifiers, such as 'trip-type' (vacation, work etc.), 'accompanied-by' (e.g., solo, friends, family etc.) are potentially useful sources of information that could be used to improve the effectiveness of POI recommendation in a current context (with a given set of these constraints). Using such information is not straight forward because a user's text reviews about the POIs visited in the past do not explicitly contain such annotations (e.g., a positive review about a pub visit does not contain the information on whether the user was with friends or alone, on a business trip or vacation). We propose to use a small set of manually compiled knowledge resource to predict the associations between the review texts in a user profile and the likely trip contexts. We demonstrate that incorporating this information within an IR-based relevance modeling framework significantly improves POI recommendation.

AB - Trip-qualifiers, such as 'trip-type' (vacation, work etc.), 'accompanied-by' (e.g., solo, friends, family etc.) are potentially useful sources of information that could be used to improve the effectiveness of POI recommendation in a current context (with a given set of these constraints). Using such information is not straight forward because a user's text reviews about the POIs visited in the past do not explicitly contain such annotations (e.g., a positive review about a pub visit does not contain the information on whether the user was with friends or alone, on a business trip or vacation). We propose to use a small set of manually compiled knowledge resource to predict the associations between the review texts in a user profile and the likely trip contexts. We demonstrate that incorporating this information within an IR-based relevance modeling framework significantly improves POI recommendation.

KW - joint context modeling

KW - weak supervision

KW - point-of-interest recommendation

U2 - 10.1145/3397271.3401197

DO - 10.1145/3397271.3401197

M3 - Conference contribution

SN - 9781450380164

T3 - SIGIR '20

SP - 1981

EP - 1984

BT - Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

PB - Association for Computing Machinery, Inc

CY - New York, NY, USA

T2 - 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

Y2 - 25 July 2020 through 30 July 2020

ER -

Relevance Models for Multi-Contextual Appropriateness in Point-of-Interest Recommendation

Abstract

Publication series

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this