=Paper=
{{Paper
|id=Vol-1621/paper2
|storemode=property
|title=A Field Evaluation of an Intelligent Interaction Between People and a Territory and its Cultural Heritage
|pdfUrl=https://ceur-ws.org/Vol-1621/paper2.pdf
|volume=Vol-1621
|authors=Amon Rapp,Federica Cena,Luca Console,Cristina Gena,Alessandro Marcengo
|dblpUrl=https://dblp.org/rec/conf/avi/RappCCGM16
}}
==A Field Evaluation of an Intelligent Interaction Between People and a Territory and its Cultural Heritage==
https://ceur-ws.org/Vol-1621/paper2.pdf
A Field Evaluation of an Intelligent Interaction Between People
and a Territory and its Cultural Heritage
Federica Cena Luca Console Cristina Gena
Department of Computer Science Department of Computer Science Department of Computer Science
University of Turin, Italy University of Turin, Italy University of Turin, Italy
cena@di.unito.it lconsole@di.unito.it cgena@di.unito.it
Alessandro Marcengo Amon Rapp
Telecom Italia Department of Computer Science
Research & Prototyping, Italy University of Turin, Italy
alessandro.marcengo@telecomitalia.it rapp@di.unito.it
people and other objects and which evolve along time, given the
ABSTRACT social activities of the objects.
In order to achieve these goals, we devised an intelligent
In this paper we present a reward-based field evaluation of the
interaction model that enables a personalized, social and
interaction model developed for Wanteat, designed to support the
serendipitous interaction with networked things, allowing a
visualization and the exploration of identifiable objects of the real
continuous transition between real and digital world. We therefore
world and their connections with other objects. The interaction
exploited novel forms of information visualization and interaction
model proposes a paradigm that enables a personalized, social and
technologies to design an innovative human-object-interaction
serendipitous interaction with networked things, allowing a
model.
continuous transition between real and digital world. We will
illustrate the procedure and the results of such evaluation, carried We decided to conduct a field trial, which is used to evaluate
out with a prototype application without an active users applications in a context of use that is quite close to that of the real
community. In particular, we would like to discover if the life. Kjeldskov et al. [2], evaluating MobileWARD, a context-
interaction model stimulates the exploration of the objects in the aware mobile system in a field study, highlighted the limitations
system and their networks, and if it promotes the interactive caused by the lack of control, as there were no predefined tasks to
features of the application, in particular social actions. drive users’ behaviors. Rogers et al. [5] conducted an evaluation in
the field of LillyPad, an ubicomp application for learning, pointing
CCS Concepts that the process was costly in terms of time and effort. Since
Human computer interaction (HCI) ➝ HCI design and evaluation WantEat, at the time of the evaluation, was still in a prototypical
methods stage, we needed a way for creating a meaningful context for users
interacting with such a multifaceted application in a natural way.
Keywords We needed also a way to encourage users to perform a set of
Interaction model; social web of things; field studies; actions and to interact with other users via the social features of
cultural heritage. the system, even in absence of an active users community. Thus,
we decided to use a field trial, conducted in a fair, and enhanced
1. INTRODUCTION by rewards, to push users to use all the features of our app and to
WantEat [2] is an intelligent mobile application in food domain, provide the social context for using the app’s social features. For
which puts together real and virtual words. By means of WantEat more description about the reward-based methodology of
evaluation see [4].
it is possible to make everyday objects smart and able to
communicate with users and to create social relationships with 2. AN INTELLIGENT MOBILE
users and other objects. Objects are gastronomic items, such as
food products, market stalls, restaurants, shops, recipes but also APPLICATION
geographic places and actors such as cooks, producers, shop WantEat [2] is a smartphone application that introduces a novel
owners, etc. WantEat is based on the idea that socially smart paradigm for supporting the user interaction with social networks
objects could play the role of gateways for enhancing the of smart objects. This interaction is made of two main phases: (i)
interaction between people and a territory and its cultural heritage. getting in touch and (ii) sharing information with the object and
If objects could speak they could tell people about the world exploring its social network.
around them, the place in which they stay and its history and Getting in touch. A basic assumption of our approach is that
traditions. This world is made of relationships which involve infrastructuring should be minimized. We aimed at supporting
interaction with everyday objects, with no embedded electronics
or tags. Thus, we developed a number of ways of creating the
contact between a user and an object (Fig. 1): (i) Taking a picture
Copyright © 2016 for this paper by its authors. Copying permitted for of the label of a product with the camera (Fig. 1(b)); (ii)
private and academic purposes. Geopositioning the user in a specific place and thus with the
objects related to the place, i.e., the objects around him; (iii)
Getting a recommendation; (iv) Searching or (v) Exploring information to the object in focus and (ii) influencing the social
bookmarks. relations between objects, as discussed in the following.
When an object is in focus (Figure 1(c)), the wheel provides
access to the social network of its friends (both people and
objects). Each friend belongs to one of four sectors; the partition
into sectors depends on the object in the center. In the example in
Figure 1(c), the object in focus is a cheese; the first sector
“Territorio” (Territory) contains the friends related to the territory,
the production and supply chain (e.g. producers, shops, production
places, etc.). The sector “Persone” (People) contains people that
are friends of the object in focus (e.g. people who bookmarked it
or who wrote a comment on it); the sector “Prodotti” (Products)
contains other food products that are friends of the object in focus
(e.g. a wine that goes well with a cheese); the sector “Cucina”
(Cuisine) contains entities related to cuisine, such as restaurants,
recipes, and so on.
Each sector can be expanded by touching it. The expanded sector
fills the screen and the items in the sector are displayed as small
circles in a ring (see Figure 1(e), where the “Territorio” sector is
expanded), similar to the dialer in an old style telephone. The
order of the items is based on the user model and on item type
(maintaining items of different types and preferring those more
suitable for the user). The items can be explored by rotating the
ring, in the same way as dialing on the old style telephone. One
item at a time is enlarged and the relation it has with the object in
focus is highlighted in a small box. See again Figure 1(e), which
shows that the object in the center of the wheel (miniaturized in
the bottom right corner of the screen) is produced in (“prodotto
in”) the place (“Valle di Lanzo”, i.e. Lanzo valley) enlarged in the
sector. Information about the enlarged item can be displayed by
touching it. The user can continue the exploration by changing the
object in focus. This can be done by simply dragging the enlarged
item toward the wheel miniature in one of the corners (Figure
1(f)). At this point the whole wheel is recomputed and displayed
to the user. For more details on system architecture and the
involved software components see [2].
3. A REWARD-BASED EVALUTAION
A good occasion to test WantEat interaction model and its
features, has been the international food fair Cheese. This biennial
Figure 1. Example of the wheel on an iPhone exhibition, held in the streets of the town of Bra in Piedmont
(Italy) attracts about 300,000 visitors. The objective of this round
Interacting with the object and its world: The wheel. Once a
of test was to stimulate the spontaneous usage of the application in
contact with an object has been established, the user can interact
all its aspects and in a context as close as possible to real use. Thus
with it and access its social network. Since we aimed at using
during the four days of the fair, the application has been installed
objects as gateways for accessing the cultural heritage of a
directly on the users iPhones. Participants could use it whatever
territory, we designed an intelligent interaction model that allows
they would like and for as long as they desired (even for the whole
users to explore the world starting from a contacted object. We
four days duration of the event). The high degree of freedom given
developed a “wheel” model (Fig. 1(c)), where the wheel can be
to users has been balanced by means of “game missions”, which
seen as the square of a village, the traditional place for meeting; in
substituted the formal tasks of the laboratory evaluation. Each
this place the user can interact with the object and its friends,
participant received a leaflet with instructions and a map of the fair
exchanging information and knowledge, being introduced to and
highlighting the areas in which the application was working.
exploring their social networks. The object the user is interacting
Inside the exhibition 10 items (cheeses), were selected as the focus
with is in the center of the wheel. The user can get in touch with it
of the evaluation. They were located in different areas of the fair,
by simply touching it, which is an appealing and natural way of
and were marked as recognizable by the application. The main
performing selective actions with a touch sensitive interface. The
objective given to users was to recognize at least 5 cheeses by
selected object tells the user about itself, providing both general
taking a picture taste them and perform some social actions on the
knowledge and information synthesized from the interaction with
application. Users received a prize when they returned to the
other people (including tags, comments, ratings) (Figure 1(d)).
installation point: a T-shirt with the Application logo. A live
The user can, in turn, tell something to the object: in particular,
leaderboard at the installation point maintained all participants
she can add her tags, comments and ratings or can bookmark the
informed of their current score.
object (Figure 1(g)). These actions contribute to (i) adding the
This reward-based field evaluation (extensively described in [4])
was aimed at evaluating: 1) The interaction model, and in We have organized the collected data in a simple taxonomy,
particular if it stimulated the exploration of objects and their (Figure 2) where CTPRVS means “all the user actions”, which is
network, and if it promoted the serendipitous discovery of new the taxonomy top level class, while VS is the sub-class that
recommended items; 2) The interactive features of the application, contains browsing actions, namely the observable symbols V and
and in particular how users communicate with objects by taking S, which correspond to the actions “display the object and its
advantage of the social features of the application, even in absence network”, namely the thing the user is interacting with and its
of an active users community. network, and “more info about the object” of the object. CTPR is
the sub-class that contains social actions, namely the observable
3.1 RESULTS symbols “commenting”, “tagging”, “(adding) preferred items
In the four-days event 157 people attended the trial and installed (bookmarks)”, “rating”.
the system on their smartphones. 110 users out of 157 (70.06%)
have actively participated in the evaluation. In total they have We have calculated the transitional probabilities for each pair of
interacted with 102 objects. In particular, 72 users out of 110 states “x, y” that determine the probability that the next state will
(65.45%) interacted with more than the required 5 objects be y given that the current state is x. In TAXOMO the sequences
(AVG=28.08 objects per user, STD=28.08), and around 51.8% of are modeled with Markov models whose states correspond to
users (namely 57) interacted with more than the 10 selected nodes in the provided taxonomy, and each state represents the
cheeses (AVG=28.08 objects per user, STD=28.08). As the events in the sub-tree under the corresponding node. In our model
evaluation instructions directly required interacting with at least 5 the valid states are V, S, C, T, P, R that correspond to display the
objects out of 10 selected in the fair, this result means that the object and its network (Fig. 1(c)), more info about the objects
interaction model quite well supported the free exploration of the (Fig. 1(d)), comment, tag, add bookmark, and rate (Fig. 1(g)) and
application contents. Moreover excluding the 10 cheeses that have are respectively grouped in VS (browsing actions) and CTPR
to be photographed, 51.8% of users browsed the other 92 objects (social actions). The transition from x to y is calculated as the ratio
contained in the app (other cheeses, producers linked to the between the number of times they occur together and the number
cheeses, etc.). This is a first index that the wheel model supported of time x occurs.
quite well the serendipitous discovery of new contents present in Considering the so grouped states we have collected the following
the application, helping users to follow their own path on the transition probabilities:
application, for more details see [4].
We classified 70 users (63.64%) out of 110 as contributing users, (1) VS 0.9904761904761905
(2) CTPR 0.0095238095238095
since they made some sort of social actions (rating, commenting,
(3) VS VS 0.578697421981004
sharing bookmarks, tagging) that bring contributions to the (4) VS CTPR 0.35345997286295794
application contents (for details see [4]). This shows a positive (5) VS $ 0.06784260515603799
result in terms of social engagement in the context of the reward- (6) CTPR VS 0.9451553930530164
based evaluation, although there was not an already active user (7) CTPR CTPR 0.04570383912248629
community before the beginning of the evaluation. As an example (8) CTPR $ 0.00914076782449725
of the results regarding the social features rating and bookmarking
actions have been very frequent, as less time-consuming than From the above transition probabilities we can observe that users
other actions. always start the interaction with browsing actions (1), then it is
more likely that they see other objects present in the object’s
network (3) before doing a social action (4). It is unlikely that
users soon stop ($) the interaction after browsing actions (5).
After one social action, it is very likely that they perform a
browsing action (6) instead of making another social action (7) or
terminating the interaction (8). Thus they put another object in
focus of the wheel belonging to the object’s network.
From this representation we can conclude that interaction with the
wheel promotes the discovery of the object’s social network, since
after having viewed an object and its related information the user
is likely to explore some other object present in its social network.
Thus, the wheel interaction model tends to promote the
exploration of objects linked through the object network. From our
analysis it is also probable that the user will perform a social
action however, as observed above, the evaluation condition has
forced the execution of social actions, which obtain frequencies,
thus transition probabilities, higher than usual
Figure 2. The taxonomy of actions in WantEat
We have also calculated emission probabilities (also known as
For analyzing the action sequences the users made while using the output probabilities) for every symbol belonging to a class in our
application we have exploited TAXOMO [1], a taxonomy-driven taxonomy. In particular the emission probability shows the
modeler, which given a taxonomy of events and a dataset of probability of emission of the X symbol when the system state is
sequences of these events produces a compact representation of xy, and is calculated as the ratio between the number of times x
the sequences. The representation adopted in TAXOMO is a occurs and the number of times x and y occurs together.
Markov model. The states of the model are nodes in the taxonomy,
where the last level (leaves) contains the observable symbols. (1) VS s 0.2976818181818182
(2) VS v 0.7023181818181818 mechanics were not present. During this field trial, 675 users out
(3) CTPR c 0.23217550274223034 of 684 have actively participated in the evaluation (98.67%), while
(4) CTPR t 0.13528336380255943 just 74 contributing users (10.96%) performed 179 (3,84%) social
(5) CTPR p 0.21937842778793418 actions out of 4660 total actions. The reward-based evaluation
(6) CTPR r 0.41316270566727603 described in this paper with 70 (63.64%) contributing users on 110
active users allowed users to perform 547 social actions (25.63%)
In the context of our analysis the emission probability represents on 2134 total actions.
how likely the user is to perform a certain action when the system
state is on the browsing action class (VS, see Figure 2) or on the REFERENCES
social action class (CTPR, see Figure 2). Considering the former 1. Bonchi, F., Castillo, C., Donato, D., Gionis, A. (2009).
class, when the user is on the wheel, it is more likely that he will Taxonomy-driven lumping for sequence mining. Data Min.
perform a “display object” action (1) than a “request for more Knowl. Discov. 19(2): 227-244
info” on it (2). Considering the latter, when the user is given the 2. Luca Console, Fabrizio Antonelli, Giulia Biamino, Francesca
option menu showing the list with all the possible social actions it Carmagnola, Federica Cena, Elisa Chiabrando, Vincenzo Cuciti,
is more likely that she will rate (6), maybe she might comment (3) Matteo Demichelis, Franco Fassio, Fabrizio Franceschi, Roberto
or add a preference (5), while it is quite unlikely that she will tag Furnari, Cristina Gena, Marina Geymonat, Piercarlo Grimaldi,
(3). Notice that he emission probabilities correspond to the Pierluigi Grillo, Silvia Likavec, Ilaria Lombardi, Dario Mana,
observed frequencies of user actions. Alessandro Marcengo, Michele Mioli, Mario Mirabelli, Monica
Perrero, Claudia Picardi, Federica Protti, Amon Rapp, Rossana
4. SUMMARY OF MAIN RESULTS Simeoni, Daniele Theseider Dupré, Ilaria Torre, Andrea Toso,
The main goals of the interaction model were supporting users in Fabio Torta, Fabiana Vernero, Interacting with social networks
exploring the object network, maintaining a strong focus on the of intelligent things and people in the world of gastronomy,
object and at the same time allowing users to interact with its ACM Transactions on Interactive Intelligent Systems (TiiS),
network, discovering new objects in a serendipitous way, and 3(1): 4 (2013)
finally allowing users to perform direct actions to enrich the object 3. Kjeldskov, J., Skov, M., Als, B., Høegh, R.: Is it worth the
with their personal experience. From the evaluation results users hassle? Exploring the added value of evaluating the usability of
seem to use the model according to our expectations, in particular context-aware mobile systems in the field. In: Brewster, S.,
the interaction promotes the serendipitous discovery of new Dunlop, M.D. (eds.) Mobile Human-Computer Interaction –
related items, helping the users to follow their own path. This is MobileHCI 2004. LNCS, vol. 3160, pp. 61–73. Springer,
demonstrated by the analysis of user actions, and by the sequence Heidelberg (2004)
analysis. Thus, we can conclude that the interaction model is quite 4. Amon Rapp, Federica Cena, Cristina Gena, Alessandro
effective in promoting the desired user interaction with the system. Marcengo, Luca Console, Using game mechanics for field
The field evaluation study conducted in a fair, and enhanced by evaluation of prototype social applications: a novel
rewards in a game context, gave us the possibility to provide users methodology, Behaviour & Information Technology, DOI:
with the social context needed for interact with the app in a 10.1080/0144929X.2015.1046931, 2015
situation close with that of the real life. Although the application 5. Rogers, Y., Connelly, K., Tedesco, L., Hazlewood, W., Kurtz,
was in a prototype phase and thus there was not a pre-existent user A., Hall, R.E. Hursey, J., and Toscos, T. (2007). Why it's worth
community, the evaluation context was able to generate a the hassle: the value of in-situ studies when designing Ubicomp.
sufficient amount of interactions useful to evaluate the interaction In Proceedings of the 9th international conference on
model and the social features of WantEat (see [4] for details). Ubiquitous computing (UbiComp '07), John Krumm, Gregory D.
This is especially true if we compare these results with the ones Abowd, Aruna Seneviratne, and Thomas Strang (Eds.).
collected during a previous field trial we conducted at Salone del Springer-Verlag, Berlin, Heidelberg, 336-353
Gusto 2010, the biggest food fair in Italy, where the game