Estimating a latent-class user model for travel recommender systems

Research output: Contribution to journalArticleAcademicpeer-review

28 Downloads (Pure)

Abstract

In determining the selection of sites to visit on a trip tourists have to trade-off attraction values against routing and time-use characteristics of points of interest (POIs). For recommending optimal personalized travel plans an accurate assessment of how users make these trade-offs is important. In this paper we report the results of a study conducted to estimate a user model for travel recommender systems. The proposed model is part of c-Space—a tour-recommender system for tourists on a city trip which uses the LATUS algorithm to find personalized optimal tours. The model takes into account a multi-attribute utility function of POIs as well as dynamic needs of persons on a trip. A stated choice experiment is designed where the current need is manipulated as a context variable and activity choice alternatives are varied. A random sample of 316 individuals participated in the on-line survey. A latent-class analysis shows that significant differences exist between tourists in terms of how they make the trade-offs between the factors and respond to needs. The estimation results provide the parameters of a multi-class user model that can be used for travel recommender systems.

Original languageEnglish
Pages (from-to)61-82
Number of pages22
JournalInformation Technology & Tourism
Volume19
Issue number1-4
DOIs
Publication statusPublished - 1 Jun 2018

Fingerprint

Recommender systems
travel
tourist
online survey
random sample
human being
experiment
Values
Experiments

Keywords

  • City trip
  • Latent class model
  • Stated choice experiment
  • Travel recommender systems
  • User model

Cite this

@article{30042670fd4d4889a6330f6beeb51875,
title = "Estimating a latent-class user model for travel recommender systems",
abstract = "In determining the selection of sites to visit on a trip tourists have to trade-off attraction values against routing and time-use characteristics of points of interest (POIs). For recommending optimal personalized travel plans an accurate assessment of how users make these trade-offs is important. In this paper we report the results of a study conducted to estimate a user model for travel recommender systems. The proposed model is part of c-Space—a tour-recommender system for tourists on a city trip which uses the LATUS algorithm to find personalized optimal tours. The model takes into account a multi-attribute utility function of POIs as well as dynamic needs of persons on a trip. A stated choice experiment is designed where the current need is manipulated as a context variable and activity choice alternatives are varied. A random sample of 316 individuals participated in the on-line survey. A latent-class analysis shows that significant differences exist between tourists in terms of how they make the trade-offs between the factors and respond to needs. The estimation results provide the parameters of a multi-class user model that can be used for travel recommender systems.",
keywords = "City trip, Latent class model, Stated choice experiment, Travel recommender systems, User model",
author = "Theo Arentze and Astrid Kemperman and Petr Aksenov",
year = "2018",
month = "6",
day = "1",
doi = "10.1007/s40558-018-0105-z",
language = "English",
volume = "19",
pages = "61--82",
journal = "Information Technology & Tourism",
issn = "1098-3058",
publisher = "Springer",
number = "1-4",

}

Estimating a latent-class user model for travel recommender systems. / Arentze, Theo; Kemperman, Astrid; Aksenov, Petr.

In: Information Technology & Tourism, Vol. 19, No. 1-4, 01.06.2018, p. 61-82.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Estimating a latent-class user model for travel recommender systems

AU - Arentze, Theo

AU - Kemperman, Astrid

AU - Aksenov, Petr

PY - 2018/6/1

Y1 - 2018/6/1

N2 - In determining the selection of sites to visit on a trip tourists have to trade-off attraction values against routing and time-use characteristics of points of interest (POIs). For recommending optimal personalized travel plans an accurate assessment of how users make these trade-offs is important. In this paper we report the results of a study conducted to estimate a user model for travel recommender systems. The proposed model is part of c-Space—a tour-recommender system for tourists on a city trip which uses the LATUS algorithm to find personalized optimal tours. The model takes into account a multi-attribute utility function of POIs as well as dynamic needs of persons on a trip. A stated choice experiment is designed where the current need is manipulated as a context variable and activity choice alternatives are varied. A random sample of 316 individuals participated in the on-line survey. A latent-class analysis shows that significant differences exist between tourists in terms of how they make the trade-offs between the factors and respond to needs. The estimation results provide the parameters of a multi-class user model that can be used for travel recommender systems.

AB - In determining the selection of sites to visit on a trip tourists have to trade-off attraction values against routing and time-use characteristics of points of interest (POIs). For recommending optimal personalized travel plans an accurate assessment of how users make these trade-offs is important. In this paper we report the results of a study conducted to estimate a user model for travel recommender systems. The proposed model is part of c-Space—a tour-recommender system for tourists on a city trip which uses the LATUS algorithm to find personalized optimal tours. The model takes into account a multi-attribute utility function of POIs as well as dynamic needs of persons on a trip. A stated choice experiment is designed where the current need is manipulated as a context variable and activity choice alternatives are varied. A random sample of 316 individuals participated in the on-line survey. A latent-class analysis shows that significant differences exist between tourists in terms of how they make the trade-offs between the factors and respond to needs. The estimation results provide the parameters of a multi-class user model that can be used for travel recommender systems.

KW - City trip

KW - Latent class model

KW - Stated choice experiment

KW - Travel recommender systems

KW - User model

UR - http://www.scopus.com/inward/record.url?scp=85048079291&partnerID=8YFLogxK

U2 - 10.1007/s40558-018-0105-z

DO - 10.1007/s40558-018-0105-z

M3 - Article

AN - SCOPUS:85048079291

VL - 19

SP - 61

EP - 82

JO - Information Technology & Tourism

JF - Information Technology & Tourism

SN - 1098-3058

IS - 1-4

ER -