=Paper=
{{Paper
|id=Vol-2855/preface
|storemode=property
|title=None
|pdfUrl=https://ceur-ws.org/Vol-2855/preface.pdf
|volume=Vol-2855
}}
==None==
https://ceur-ws.org/Vol-2855/preface.pdf
WebTour 2021
ACM WSDM Workshop on Web Tourism
Jerusalem, Israel, March 12th, 2021
Proceedings
Edited by
Catalin-Mihai Barbu, Ludovik Coba, Amra Delić,
Dmitri Goldenberg, Tsvi Kuflik, Julia Neidhardt &
Markus Zanker
Co-located with the 14th ACM International WSDM
Conference (WSDM 2021)
Copyright and Bibliographical Information
Copyright © 2021 for the individual papers by the papers’ authors. Use
permitted under Creative Commons License Attribution 4.0 International (CC
BY 4.0). This volume is published and copyrighted by its editors. The
copyright for papers appearing in these proceedings belongs to the papers’
authors.
This volume is published by Catalin-Mihai Barbu, Ludovik Coba, Amra
Delić, Dmitri Goldenberg, Tsvi Kuflik, Julia Neidhardt and Markus Zanker.
Published online at CEUR-WS.org.
Proceedings of the Workshop on Web Tourism (WebTour 2021), held in
conjunction with the 14th ACM Conference on Web Search and Data Mining
(WSDM 2021), March 8th - 12th, 2021, Jerusalem, Israel,
http://www.wsdm-conference.org/2021/.
Further information about the workshop can be found at:
https://web.ec.tuwien.ac.at/webtour21
Preface
Web has become a premier source of information in almost every area, including tourism.
When a user is planning a vacation or a trip, she searches the Web for information about
destinations, accommodations, attractions, means of transportation, in short, everything
related to her future vacation/trip. Nowadays, when the search is complete, it is possible
to reserve almost everything online: flight tickets, train tickets, reserve accommodations,
attractions tickets or car rentals. The blessing of the easily accessible information comes
with the curse of information overload, that brought information filtering and
recommendation techniques into play. This is especially true recently given the wide
spread of COVID-19 and the uncertainty and transformative power it brings to travelling.
WebTour 2021 was the first workshop focusing on the specific role of the Web in tourism.
It brought together researchers and practitioners working on developing and improving
tools and techniques for improving users’ ability to better find relevant information that
matches their needs.
WebTour 2021 had two parts, a traditional workshop papers’ track, where traditional
papers were submitted and presented and a challenge track, where a challenging task +
a dataset were published and teams registered and competed in addressing the
challenge.
Five research papers and eight challenge papers were accepted to the proceedings. The
research papers covered a diverse set of topics, including traditional tour planning to
tourists’ paths analysis as well as novel ideas of evaluating 360 virtual tour applications
and considering diversity and social cohesion in content recommendations.
The challenge attracted more than 800 participants. The accepted papers (of the best
performing teams) presented a diversity of deep-learning based approached for finding
the best recommendation of an additional trip destination.
The workshop itself took place virtually due to COVID-19 pandemic, but nevertheless,
triggered interesting discussion.
The rapid development of information and communication technologies (ICT) and the
Web transformed the tourism domain. Nowadays travelers no longer rely on travel
agents/agencies. Indeed, recent studies indicate that they are now active in searching for
information and composing their vacation packages according to their specific
preferences.
When onsite, they search for freely available information about the site itself rather than
buying a visitor guide, renting a mobile guide or hiring even a tour guide that may be
available, but would be considered expensive or sometimes outdated. However, like in
many other cases, the blessing of the Web comes with a curse – the curse of information
overload. Recommender systems are a practical tool for overcoming this information
overload.
However, the tourism domain is substantially more complicated, and as such, creates
huge challenges for those designing tourism focused on recommender systems. Planning
a vacation usually involves searching for a set of products that are interconnected (e.g.
means of transportation, lodging, attractions etc.), with a rather limited availability, and
where contextual aspects may have a major impact (timing, social context, environmental
context). In addition, and most importantly, products are emotionally “loaded” and
considered “experience goods”. Therefore, decision taking is not only based on rational
and objective criteria (i.e., system 2 thinking). As such, providing the right information to
visitors of a tourism site at the right time about the site itself and various services nearby
is challenging. Thus, all of this makes building effective recommendation systems within
tourism extremely difficult. The workshop focuses on the specific challenges for tourism-
related information search and recommendations. This workshop focus on tourism
provides an opportunity for WSDM participants working in this area to discuss specific
issues of interest that are unique to this complex and attractive domain. We are confident
that this workshop will be a start for focused discussions at WSDM for years to come.
WebTour is the first workshop focusing on the specific role of the Web in tourism.
Traditionally, the RecTour workshop series has been associated with the RecSys
conference since 2015, focusing on applying recommendation techniques for helping
users cope with information overload of tourism-related information. However, as the
Web is the main (if not the only) source of information for travelers that are planning their
trips, a WSDM workshop is a natural choice. Tourism-related information is available all
over the Web. This workshop therefore brings together researchers and practitioners
from different fields (e.g., tourism, recommender systems, user modeling, user
interaction, mobile, ubiquitous and ambient technologies, artificial intelligence and web
information systems) working in the tourism recommendation domain. The workshop
aims at providing a forum for these people to discuss novel ideas for addressing the
specific challenges for recommender systems in tourism with the goal to advance the
current state-of-the-art in this field. Another goal of the workshop is to identify practical
applications of these technologies within tourism settings from the point of view of
individual users and user groups, service providers, as well as additional stakeholders
(e.g., destination management organizations).
WORKSHOP TOPICS
The key interest topics of the workshop are:
• Systems, applications and novel techniques
– Information search in travel and tourism
– Recommendation systems for travel and tourism
– Route planning and trip recommendation
– Data integration methods
– Case studies and evaluation
• User modeling in tourism
– Travelers preference elicitation
– Context and mobility
– Information needs, information access and search patterns
– Cold-start problem in tourist information search
– Interaction concepts with personal and group displays
– Personalized explanations and feedback of recommendation systems
– Digital storytelling and narratives
• Networks, governance and policy
– Analysis of networks in tourism
– Novel ICT and its impact on travel and tourism
– Sustainability of the tourism ecosystem
– Travel and tourism in the COVID-19 and post-covid era
CHALLENGE
As part of the workshop, the WebTour 2021 Challenge organized by Booking.com is taking
place. It focuses on a multi-destinations trip planning problem, which is a popular scenario
in the travel domain. The goal of this challenge is to make the best recommendation of
an additional in-trip destination. To do so, Booking.com provides a unique dataset based
on millions of real anonymized bookings. Top performing teams are invited to present
short papers describing their solution approach and receiving prizes. For a more detailed
description of the challenge dataset see https://www.bookingchallenge.com/
SUMMARY
The WebTour 2021 workshop draws special attention to the various challenges of tourism
in the Web context and brings together scientists from diverse fields such as e-tourism,
recommender systems, user modeling or adaptive hypermedia. Therefore, this first
instance of a workshop topic constitutes an important step for establishing e-tourism
research at the WSDM conference series. The workshop proceedings can be found on the
website of the workshop at https://web.ec.tuwien.ac.at/webtour21/.
Organizers and Program Committee
Catalin-Mihai Barbu, University of Duisburg-Essen, Germany
Ludovik Coba, Free University of Bozen-Bolzano, Italy
Amra Delić, University of Sarajevo, Bosnia & Herzegovina
Dmitri Goldenberg, Booking.com, Tel Aviv, Israel
Tsvi Kuflik, The University of Haifa, Israel
Julia Neidhardt, TU Wien, Austria
Markus Zanker, Free University of Bozen-Bolzano, Italy
Program
The workshop will take place on March 12, 2021. The schedule is provided in Jerusalem
time (GMT+2).
12:00 – 12:15 – WebTour opening
12:15 – 12:40 – Elif Erbil and Wolfgang Wörndl: Generating Multi-Day Round Trip
Itineraries for Tourists.
12:40 – 12:55 – Rinita Roy and Linus W. Dietz: TripRec – A Recommender System for
Planning Composite City Trips Based on Travel Mobility Analysis.
12:55 – 13:10 – Lukas Vorwerk and Linus W. Dietz: An Interactive Dashboard for Traveler
Mobility Analysis.
13:10 – 13:25 – Roman Shikhri, Joel Lanir and Lev Poretski: Evaluation Framework for
Improving 360 Virtual Tours User Experience.
13:25 – 13:40 – Tsvi Kuflik, Paul Mulholland and Alan Wecker: Tourist recommendations
with a touch of SPICE: A TRS with Deep Cultural Understanding.
13:40 – 13:45 – Wrap up of the paper session
13:45 – 14:45 – Lunch break
14:45 – 15:00 – Dmitri Goldenberg: Booking.com WSDM WebTour 2021 Challenge.
15:00 – 15:20 – Michał Daniluk, Barbara Rychalska, Konrad Gołuchowski and Jacek
Dąbrowski: Modeling Multi-Destination Trips with Sketch-Based Model.
15:20 – 15:40 – Benedikt Schifferer, Chris Deotte, Jean-Francois Puget, Gabriel de Souza
Pereira Moreira, Gilberto Titericz, Jiwei Liu and Ronay Ak: Using Deep Learning to Win
the Booking.com WSDM WebTour21 Challenge on Sequential Recommendations.
15:40 – 16:00 – Closing discussion
Table of Contents
Main Track - Short Papers
• Generating Multi-Day Round Trip Itineraries for Tourists 1-7
Elif Erbil , Wolfgang Wörndl
• TripRec – A Recommender System for Planning Composite City Trips Based on
Travel Mobility Analysis 8-12
Rinita Roy, Linus W. Dietz
• An Interactive Dashboard for Traveler Mobility Analysis 13-15
Lukas Vorwerk, Linus W. Dietz
• Evaluation Framework for Improving 360 Virtual Tours User Experience 16-18
Roman Shikhri, Joel Lanir, Lev Poretski
• Tourist recommendations with a touch of SPICE: A TRS with Deep Cultural
Understanding 19-20
Tsvi Kuflik , Paul Mulholland, Alan Wecker
Challenge Track - Short Papers
• Booking.com WSDM WebTour 2021 Challenge 21-22
Dmitri Goldenberg, Kostia Kofman, Pavel Levin, Sarai Mizrachi, Maayan Kafry ,
Guy Nadav
• Using Deep Learning to Win the Booking.com WSDM WebTour21 Challenge on
Sequential Recommendations 22-28
Benedikt Schifferer, Chris Deotte, Jean-Francois Puget, Gabriel de Souza Pereira
Moreira, Gilberto Titericz, Jiwei Liu, Ronay Ak
• Modeling Multi-Destination Trips with Sketch-Based Model. 29-33
Michał Daniluk, Barbara Rychalska, Konrad Gołuchowski, Jacek Dąbrowski
• Explore next destination prediction 34-35
Yuanzhe Zhou, Shikang Wu, Chenyang Zheng
• Data Augmentation Using Many-To-Many RNNs for Session-Aware
Recommender Systems 36-40
Martín Baigorria Alonso
• Attention-based neural re-ranking approach for next city in trip
recommendations 41-45
Aleksandr Petrov, Yuriy Makarov
• Weighted Averaging of Various LSTM Models for Next Destination
Recommendation. 46-49
Shotaro Ishihara, Shuhei Goda, Yuya Matsumura
• Combining RNN with Transformer for Modeling Multi-Leg Trips 50-52
Yoshihiro Sakatani
• Hybrid Model with Time Modeling for Sequential Recommender Systems. 53-57
Marlesson R. O. Santana, Anderson Soares