Single User Group Recommendations
Hanif Emamgholizadeh
hemamgholizadeh@unibz.it
Free University of Bozen-Bolzano
Bozen-Bolzano, Italy
Barbara Bazzanella
OKKAM s.r.l.
Trento, Italy
bazzanella@okkam.it
Andrea Molinari
University of Trento
Trento, Italy
andrea.molinari@unitn.it
Francesco Ricci
francesco.ricci@unibz.it
Free University of Bozen-Bolzano
Bozen-Bolzano, Italy
ABSTRACT
Going to restaurants is also a social activity; people often go to
restaurants with family, friends, or colleagues. However, most
restaurant fnder systems, such as TripAdvisor, allow users to search
for restaurants matching only one user’s preferences. We present
here a system GUI aiming at extending such systems to support the
organizer of an event in fnding a proper restaurant for her group.
The organizer is responsible for expressing the group members’
preferences, analyzing the recommendations, and fnally selecting
a restaurant. We have identifed three recommendation techniques
(popularity-based, relevance-based, and critiquing-based) to sup-
port such a task. These techniques make diferent assumptions on
the amount of information about the group members’ preferences
available to the organizer, and they support alternative choice pat-
terns. Moreover, the proposed system supports in the fnal decision-
making stage by: a) indicating the extent to which a recommended
restaurant is attractive to each group member, w.r.t. the entered
preferences, b) suggesting a good choice for the group, and c) il-
lustrating the similarity of other groups which have previously
bookmarked one of the recommended restaurants.
KEYWORDS
Recommender Systems, Group Recommender Systems, Restaurant
Recommendation
ACM Reference Format:
Hanif Emamgholizadeh, Barbara Bazzanella, Andrea Molinari, and Francesco
Ricci. 2022. Single User Group Recommendations. In Adjunct Proceedings of
the 30th ACM Conference on User Modeling, Adaptation and Personalization
(UMAP ’22 Adjunct), July 4ś7, 2022, Barcelona, Spain. ACM, New York, NY,
USA, 6 pages. https://doi.org/10.1145/3511047.3537663
1 INTRODUCTION
Current restaurant fnder applications let the user search for restau-
rants only on the base of their individual preferences. For instance,
TripAdvisor is an application for online searching hotels, fights,
Permission to make digital or hard copies of all or part of this work for personal or
classroom use is granted without fee provided that copies are not made or distributed
for proft or commercial advantage and that copies bear this notice and the full citation
on the frst page. Copyrights for components of this work owned by others than ACM
must be honored. Abstracting with credit is permitted. To copy otherwise, or republish,
to post on servers or to redistribute to lists, requires prior specifc permission and/or a
fee. Request permissions from permissions@acm.org.
UMAP ’22 Adjunct, July 4ś7, 2022, Barcelona, Spain
© 2022 Association for Computing Machinery.
ACM ISBN 978-1-4503-9232-7/22/07. . . $15.00
https://doi.org/10.1145/3511047.3537663
attractions, and restaurants. When looking for a restaurant, users
insert their (preferred) location, price range, and type of restau-
rant. As a result, the system lists relevant options on the base of
the stated preferences. MyFood (myfood.okkam.it) is a similar ap-
plication, specifcally dedicated to restaurant fnding. In MyFood,
individual users can insert personal food preferences, such as the
type of cuisine they are interested in. The system returns relevant
restaurants that are also compatible with dietary restrictions of
the user. However, people often go to restaurants in groups; there-
fore, it is common that users of these applications are looking for
restaurants tailored for a group of users, such as a family, a group
of colleagues, or friends.
In this paper, we present the design of a necessary and minimal
interaction to let MyFood to support users to fnd restaurants suit-
able for the group they belong to. We are working in partnership
with the developers of MyFood to extend their restaurant fnder to
a group recommender system (GRS) called MyFoodGRS. Precisely,
in this paper, we deal with the situation in which the organizer
of a group is making a choice on behalf of the group. This is a
frequent scenario as organising a group discussion for choosing
a good restaurant may not always be possible. Therefore, we are
interested in understanding how GRS techniques can be efectively
used to support the organizer in fnding a proper restaurant for her
group.
Group Recommender Systems (GRSs) are techniques and tools
that can be used to suggest relevant items to a group of people [8]
and support the group in making a proper decision. The concept
that we are addressing here, namely to support a single user to
make a choice for a group, is rather diferent from previously tar-
geted scenarios for GRSs. For example, Where2eat [5] is a GRS that
lets two users to negotiate their proposals for a suitable restaurant.
MUSICFX [9] is a GRS aimed at supporting a group in selecting a
radio station to play music in the gym. This application makes a
decision on behalf of the groups after acquiring the users’ prefer-
ences. STSGroup [11] is a chat-based environment that lets group
members discuss recommended items and fnally suggests an item
as a group choice.
Hence, state-of-the-art GRSs have not exactly targeted our appli-
cation scenario. The unique GRS, to the best of our knowledge, that
is tackling a similar scenario is REMPAD [2]. Here, the group orga-
nizer uses the system recommendations to select and suggest one
of the recommended videos to the group. Hence, in these systems,
except for REMPAD, either the whole group or, more autonomously,
the system is in charge of making the group choice. Conversely,
308