Supporting a Group Member to Make a Group Choice
Hanif Emamgholizadeh
hemamgholizadeh@unibz.it
Free University of Bozen Bolzano
Bolzano, Bolzano, Italy
Amra Delic
adelic@etf.unsa.ba
University of Sarajevo
Sarajevo, Bosnia and Herzegovina
Francesco Ricci
francesco.ricci@unibz.it
Free University of Bozen Bolzano
Bolzano, Bolzano, Italy
Abstract
We often make choices that involve a group of people, such as
selecting a movie to watch with friends or choosing a travel desti-
nation to visit with the family. Sometimes, a single member of the
group may be in charge of making the decision for the group, by
playing the role of łorganizerž. Although some tools for supporting
Group Decision-Making have been proposed, none of them have
considered the case where a single group member is autonomously
making such a decision, hence entering the preferences of the group
members, interacting with the system, and fnally selecting a proper
recommendation. In this paper, we introduce MyFoodGRS, a web
application for a single user to fnd a proper restaurant for their
group, that supports the previously mentioned tasks. We introduce
an interaction design to follow the Attribute and Socially-based
group decision patterns, and we report the positive result of the
conducted system usability evaluation.
Keywords
Recommender Systems, Group Recommender Systems, Decision
Making, Group Decision Making
ACM Reference Format:
Hanif Emamgholizadeh, Amra Delic, and Francesco Ricci. 2023. Supporting
a Group Member to Make a Group Choice. In UMAP ’23 Adjunct: Adjunct
Proceedings of the 31st ACM Conference on User Modeling, Adaptation and
Personalization (UMAP ’23 Adjunct), June 26ś29, 2023, Limassol, Cyprus.
ACM, New York, NY, USA, 4 pages. https://doi.org/10.1145/3563359.3597414
1 Introduction
There are some circumstances in which a group of users may need to
fnd a proper product or service to be consumed jointly by the group.
For instance, when a group of close friends wants to go on a trip
and they need to assemble a travel plan to satisfy the preferences
of all of them, or when a person wants to invite their colleagues
to a restaurant. To address these needs, Group Recommender sys-
tems (GRS) have been employed [7]. GRS leverage techniques that
aid a group in their decision-making activities by suggesting perti-
nent items or facilitating them in a joint Group Decision Making
(GDM) process [7]. In the majority of the cases where a GRS is
employed, either all or some of the group members are actively
involved, e.g., in eliciting preferences and negotiating. However,
there are certain scenarios where a single member of the group
Permission to make digital or hard copies of part or all 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 third-party components of this work must be honored.
For all other uses, contact the owner/author(s).
UMAP ’23 Adjunct, June 26ś29, 2023, Limassol, Cyprus
© 2023 Copyright held by the owner/author(s).
ACM ISBN 978-1-4503-9891-6/23/06.
https://doi.org/10.1145/3563359.3597414
makes a decision on behalf of the entire group. In such cases,
this individual (henceforth referred to as the organizer) is uniquely
responsible for making the decision. For instance, if someone wants
to invite their colleagues to a restaurant, they may try to search for
a venue that fts all the group members, and make a surprise. This
type of decision-making is a particular case of GDM that, despite
the absence of the preference elicitation and options’ discussion
steps, is not necessarily simpler. Remembering each invitee’s food
preferences and possible dietary restrictions, striving to balance the
satisfaction level of all participants, and maximizing the group’s
overall satisfaction are some of the challenges that the organizer
will encounter.
Since the frst GRS application was introduced [9], a number of
follow up techniques have been proposed to support groups in their
Decision Making (DM) process [1, 10, 12]. Of particular interest for
this work are INTRIGUE [2] and REMPAD [3], which were properly
designed to aid the organizer of an event. INTRIGUE is a GRS that
allows the tour leader to input the group members’ information.
On the base of those preferences, recommendations are generated,
specifcally tailored to satisfy a number of homogeneous subgroups
in the larger and heterogeneous group of people. REMPAD facili-
tates the organizer of a group of a reminiscence therapy session in
selecting appropriate multimedia content.
Providing assistance to an event organizer in selecting an ap-
propriate restaurant involves diferent domain-dependent function-
alities. For instance, in contrast to an itinerary recommendation
problem, where there are various points of interest (POIs) that
can be suggested to a group to ensure that each group member is
enough satisfed, it can be challenging to fnd a single restaurant
that is suitable for groups with diverse preferences. Additionally,
unlike in the reminiscence therapy application [3], the organizer
may only have limited knowledge about the favorite dishes of each
member in the group. We note that while most of the commercial
restaurant fnders, like TripAdvisor (https://www.tripadvisor.com/),
are meant to be used by a single person, eventually on behalf of a
group, they do not ofer explicit support for GDM.
As a solution to these problems, we propose MyFoodGRS
(http://myfoodgrs.inf.unibz.it:8080/), an application that can assist
event organizers in fnding a suitable restaurant for a group. In this
paper, we introduce MyFoodGRS that we developed in collabora-
tion with okkam.it. MyFoodGRS provides a set of group-oriented
functionalities that enable organizers to assess the relative qual-
ity of restaurants, reconcile the diverse preferences of the group
members, and make informed decisions by using the attribute- and
the socially-based choice patterns. We have evaluated MyFoodGRS
by using the SUS usability questionnaire [4] and obtained a score
higher than the benchmark. The usability study also indicated that
organizers more often adopt the attribute-based choice pattern,
when they are making a restaurant decision for the group.
96