There has been a growing interest in recommending trips for tourists using location-based social networks. The challenge of trip recommendation not only lies in searching for relevant points-of-interest (POIs) to form a personalized trip, but also selecting the best time of day to visit the POIs. Popular POIs can be too crowded during peak times, resulting in long queues and delays. In this work, we propose the Personalized Crowd-aware Trip Recommendation (PersCT) algorithm to recommend personalized trips that also avoid the most crowded times of the POIs. We model the problem as an extension of the Orienteering Problem with multiple constraints. We extract user interests by collaborative filtering and we propose an extension of the Ant Colony Optimisation algorithm to merge user interests with POI popularity and crowdedness data to recommend trips. We evaluate our algorithm using foot traffic information obtained from a real-life pedestrian sensor dataset and user travel histories extracted from a Flickr photo dataset. We show that our algorithm out-performs several benchmarks in achieving a balance between conflicting objectives by satisfying user interests while reducing the crowdedness of the trips.
Description
Improving Personalized Trip Recommendation by Avoiding Crowds
%0 Conference Paper
%1 Wang:2016:IPT:2983323.2983749
%A Wang, Xiaoting
%A Leckie, Christopher
%A Chan, Jeffrey
%A Lim, Kwan Hui
%A Vaithianathan, Tharshan
%B Proceedings of the 25th ACM International on Conference on Information and Knowledge Management
%C New York, NY, USA
%D 2016
%I ACM
%K personalized-trip-recommendation social-information-access
%P 25--34
%R 10.1145/2983323.2983749
%T Improving Personalized Trip Recommendation by Avoiding Crowds
%U http://doi.acm.org/10.1145/2983323.2983749
%X There has been a growing interest in recommending trips for tourists using location-based social networks. The challenge of trip recommendation not only lies in searching for relevant points-of-interest (POIs) to form a personalized trip, but also selecting the best time of day to visit the POIs. Popular POIs can be too crowded during peak times, resulting in long queues and delays. In this work, we propose the Personalized Crowd-aware Trip Recommendation (PersCT) algorithm to recommend personalized trips that also avoid the most crowded times of the POIs. We model the problem as an extension of the Orienteering Problem with multiple constraints. We extract user interests by collaborative filtering and we propose an extension of the Ant Colony Optimisation algorithm to merge user interests with POI popularity and crowdedness data to recommend trips. We evaluate our algorithm using foot traffic information obtained from a real-life pedestrian sensor dataset and user travel histories extracted from a Flickr photo dataset. We show that our algorithm out-performs several benchmarks in achieving a balance between conflicting objectives by satisfying user interests while reducing the crowdedness of the trips.
%@ 978-1-4503-4073-1
@inproceedings{Wang:2016:IPT:2983323.2983749,
abstract = {There has been a growing interest in recommending trips for tourists using location-based social networks. The challenge of trip recommendation not only lies in searching for relevant points-of-interest (POIs) to form a personalized trip, but also selecting the best time of day to visit the POIs. Popular POIs can be too crowded during peak times, resulting in long queues and delays. In this work, we propose the Personalized Crowd-aware Trip Recommendation (PersCT) algorithm to recommend personalized trips that also avoid the most crowded times of the POIs. We model the problem as an extension of the Orienteering Problem with multiple constraints. We extract user interests by collaborative filtering and we propose an extension of the Ant Colony Optimisation algorithm to merge user interests with POI popularity and crowdedness data to recommend trips. We evaluate our algorithm using foot traffic information obtained from a real-life pedestrian sensor dataset and user travel histories extracted from a Flickr photo dataset. We show that our algorithm out-performs several benchmarks in achieving a balance between conflicting objectives by satisfying user interests while reducing the crowdedness of the trips.},
acmid = {2983749},
added-at = {2017-02-08T21:23:27.000+0100},
address = {New York, NY, USA},
author = {Wang, Xiaoting and Leckie, Christopher and Chan, Jeffrey and Lim, Kwan Hui and Vaithianathan, Tharshan},
biburl = {https://www.bibsonomy.org/bibtex/274bf3767dd3da205cff692b7a154c921/xianteng},
booktitle = {Proceedings of the 25th ACM International on Conference on Information and Knowledge Management},
description = {Improving Personalized Trip Recommendation by Avoiding Crowds},
doi = {10.1145/2983323.2983749},
interhash = {2bf1b03f507e2b6ad6aefed861a1b2c2},
intrahash = {74bf3767dd3da205cff692b7a154c921},
isbn = {978-1-4503-4073-1},
keywords = {personalized-trip-recommendation social-information-access},
location = {Indianapolis, Indiana, USA},
numpages = {10},
pages = {25--34},
publisher = {ACM},
series = {CIKM '16},
timestamp = {2017-02-08T21:23:27.000+0100},
title = {Improving Personalized Trip Recommendation by Avoiding Crowds},
url = {http://doi.acm.org/10.1145/2983323.2983749},
year = 2016
}