=Paper=
{{Paper
|id=None
|storemode=property
|title= Context-Aware Places of Interest Recommendations and Explanations
|pdfUrl=https://ceur-ws.org/Vol-740/DEMRA2011_paper3.pdf
|volume=Vol-740
}}
== Context-Aware Places of Interest Recommendations and Explanations==
https://ceur-ws.org/Vol-740/DEMRA2011_paper3.pdf
Context-Aware Places of Interest
Recommendations and Explanations
Linas Baltrunas, Bernd Ludwig, Stefan Peer, and Francesco Ricci
Free University of Bozen-Bolzano
Piazza Domenicani 3, 39100 Bolzano, Italy
lbaltrunas,bernd.ludwig,fricci@unibz.it
Abstract. Contextual knowledge has been traditionally used in Rec-
ommender Systems (RSs) to improve the recommendation accuracy of
the core recommendation algorithm. Beyond this advantage, in this pa-
per we argue that there is an additional benefit of context management;
making more convincing recommendations because the system can use
the contextual situation of the user to explain why an item has been
recommended, i.e., the RS can pinpoint the relationships between the
contextual situation and the recommended items to justify the sugges-
tions. The results of a user study indicate that context management and
this type of explanations increase the user satisfaction with the recom-
mender system.
1 Introduction
Recommender Systems (RSs) are software tools and techniques providing sug-
gestions for items to be of use to a user [8]. It is a matter of fact that more
compelling and useful recommendations can be identified if the context of the
user is known [1]. Here we adopt the definition of context provided by [5]: context
is “any information that can be used to characterize the situation of an entity.
An entity is a person, place, or object that is considered relevant to the inter-
action between a user and an application, including the user and applications
themselves”. For instance, in a travel recommender, the season and the dura-
tion of the travel are important contextual conditions that should be considered
before suggesting a holiday.
For this reason, context-aware recommender systems (CARSs) have attracted
a lot of attention, and in particular in the tourism domain [4, 3, 7]. But, in order
to adapt the recommendations to the user’s context one must first identify all
the potential contextual factors that may influence the acceptance of a recom-
mendation, e.g., distance to a target place of interest, motivations for the travel,
etc. This knowledge can be obtained by referring to the vast consumer behavior
literature, especially in tourism [9]. But this knowledge can only be used as a
starting point. In a necessary second step the quantitative dependency of the
user preferences (ratings for items) from each single contextual factor must be
modeled. This dependency model can be built, in collaborative filtering RSs, by
acquiring explicit ratings for some of the items to be recommended under several
possible contextual conditions. So for instance, in our application domain, one
should acquire the ratings of a museum (place of interest – POI) when the user
is traveling with or without children or when she is alone.
In this paper, we briefly illustrate ReRex, a recommender system for places
of interest (POIs), that exploits a context-aware rating prediction model to gen-
erate more useful recommendations and can explain the recommendations by
referring to some selected factors describing the contextual situation of the tar-
get user [10]. We illustrate the evaluation methodology, based on the comparison
of ReRex with a variant obtained by removing its context-awareness capability
and recommendation explanations, showing that these two features of the system
increase the user satisfaction with the recommender system.
2 Ratings in Context
Our working hypothesis is that a recommendation can be explained plausibly if
at least the most important criteria that lead to the recommendation are com-
municated to the user. In our context-aware recommendation model, besides the
user-item-matrix of ratings, the context, i.e., the set of conditions that hold when
the recommendation is made, is of major importance for the recommendation.
Evidence that context matters for good recommendations is taken from a user
study that we conducted. In this study subjects were asked to rate a selection of
places of interest in Bolzano imagining that certain contextual conditions hold
[2]. Table 1 lists some of the contextual factors that change the average ratings
of particular categories of points of interest significantly (for lack of space only
a selection of these categories is considered). For instance, “walking paths” are
rated worse at “night time” or if the user is “far away” from that path. Note
that in the table MCY, is the mean rating for items in that category when that
contextual condition was considered, while MCN is the mean rating for the same
selection of items when context was not considered.
This difference in the rating means is significant (p < 0.001: ∗ ∗ ∗; 0.001 ≤
p < 0.01: ∗∗; 0.01 ≤ p < 0.05: ∗). From this results we can conclude, for instance,
that the rating prediction for a walking path should decrease if the user is far
from it. Moreover, the distance to a walking path could be used as an argument
for not suggesting that item even if based on other elements, e.g., the previous
ratings of the user for similar items, it may seem a good recommendation. In
contrast to this example, the mean rating of a walking path grows significantly if
the user is with friends or she is in a lazy mood. Consequently, in that contextual
conditions, the recommender could argue for its recommendation of a walking
path by pointing out that since the user is with friends (or is in a lazy mood)
then that particular walking path is a suitable activity.
The collected context-dependent ratings have been used to train a novel
context-aware rating prediction model that extends and adapts the approach
presented in [6]. We have introduced one model parameter for each contextual
condition and item pair. To keep our approach tractable, we have modeled con-
text as a set of independent contextual factors. The model then learns how the
Table 1. Effects of context on the mean rating for items. MCY is the mean of the
ratings when that context is considered, while MCN is the mean of the ratings for the
same items when context is not considered.
contextual condition factor p-value MCN MCY Effect
Castle
far away distance ∗ ∗∗ 3.80 2.47 ↓
winter season ∗∗ 3.81 2.63 ↓
Museum
sad mood ∗ ∗∗ 2.79 1.64 ↓
activity/sport travel-goal ∗ ∗∗ 2.64 1.33 ↓
active mood ∗ ∗∗ 2.64 1.44 ↓
far away distance ∗∗ 2.78 1.92 ↓
Walking Path
night time day-time ∗ ∗∗ 3.78 1 ↓
far away distance ∗ ∗∗ 3.86 2.38 ↓
cold temperature ∗ ∗ ∗ 3.8 1.88 ↓
winter season ∗ ∗∗ 3.91 2.33 ↓
with friends or colleagues companion ∗ ∗∗ 3.85 4.83 ⇑
crowded crowdedness ∗ ∗ 3.88 2.75 ↓
working day day-week ∗∗ 3.94 2.75 ↓
half day time-available ∗ ∗ 4.01 1.6 ↓
more than a day time-available ∗ ∗ 3.89 4.8 ⇑
lazy mood ∗∗ 4.03 4.71 ⇑
ratings deviate from classical personalized predictions as effect of one selected
contextual factor, for each possible value of the factor, i.e., contextual condition.
This deviation is the baseline for that contextual condition and item combina-
tion. Broadly speaking, the system computes a rating prediction for a user-item
pair and then adapts that prediction to the current contextual situation, i.e., a
combinations of contextual conditions (values for contextual factors) using the
learned context-dependent baselines.
More precisely, in our data set of context-aware ratings, a rating ruic1 ...ck in-
dicates the evaluation of the user u for the item i made in the context c1 , . . . , ck ,
where cj = 0, 1, . . . , zj , and cj = 0 means that the j-th contextual factor is un-
known, while the other index values refer to possible values for the j-th contextual
factor. The tuples (u, i, c1 , . . . , ck ), for which rating the ruic1 ...ck is known, are
stored in the data set R = {(u, i, c1 , . . . , ck )|ruic1 ...ck is known}. Note, that in
our collected data set, only one contextual condition is known and all the others
are unknown, hence in R there are ratings for which only one among the indices
c1 , . . . , ck is different from 0.
The proposed model computes a personalized context-dependent rating esti-
mation using the following equation:
k
X
r̂uic1 ...ck = v u · q i + ı̄ + bu + Bijcj (1)
j=1
where v u and q i are d dimensional real valued vectors representing the user
u and the item i. ı̄ is the mean of the item i ratings in the data set R, bu is
the baseline parameter for user u, and Bijcj are the parameters modeling the
interaction of the contextual conditions and the items. The parameters v u , q i ,
bu , and Bijcj are learned using stochastic gradient descent; this has been proved
to be an efficient approach for similar learning problems [6].
In order to generate the explanation for a recommendation for item i in the
contextual situation c1 . . . ck we identified j = arg maxj Bijcj , i.e., the factor that
in the predictive model has the largest positive effect on the rating prediction
for item i. Using one single factor in the generated explanation has the benefit
of creating a simple, easy to grasp motivation, and to not overload the user. The
implementation of a concrete recommender system, which is using this model,
is discussed in the next section.
3 The ReRex Mobile Application
In a typical interaction with ReRex the user initially establishes the context of
the visit. Using the system GUI the user can enable and/or set the values of
important contextual factors. The user can switch on/off some of these factors,
e.g., the “Temperature” or “Weather” (see Figure 1, left). When one of these
factors is switched on the recommender system will take into account its cur-
rent value in the recommendation generation process. The full set of contextual
factors considered in ReRex, their values (contextual conditions), and whether
they are automatically collected, using an external service, or manually entered
by the user, is provided in the following:
– Distance to POI (automatic): far away, near by;
– Temperature (automatic): hot, warm, cold;
– Weather (automatic): sunny, cloudy, clear sky, rainy, snowing;
– Season (automatic): spring, summer, autumn, winter;
– Companion (manual): alone, friends, family, partner, children;
– Time day (automatic): morning, afternoon, night;
– Weekday (automatic): working day, weekend;
– Crowdedness (manual): crowded, not crowded, empty;
– Familiarity (manual): new to city, returning visitor, citizen of the city;
– Mood (manual): happy, sad, active, lazy;
– Budget (manual): budget traveler, price for quality, high spender;
– Travel length (manual): half day, one day, more than a day;
– Means of transport (manual): car, bicycle, pedestrian, public transport;
Fig. 1. ReRex context management (left); display for recommendations (right).
– Travel goal (manual): visiting friends, business, religion, health care, social
event, education, cultural, scenic/landscape, hedonistic/fun, activity/sport.
After the user has entered the specification of the contextual situation (see
Figure 1, left) the system can be requested to provide some recommendations. A
short number of suggestions, namely six, are provided (see Figure 1, right). The
recommendations are ordered according to their predicted rating. If the user
is not happy with these suggestions she can request more recommendations.
In the suggestion list the user can touch any of these suggestions to access a
more detailed description of the POI (see Figure 2). It is worth noting that
some of these suggestions are marked with an icon showing a small clock and
a green arrow. This means that these recommendations are particularly suited
for the current context of the request as it was previously acquired. For these
recommendations (Figure 2) there is an explanation sentence like “This place
is good to visit with family”. This refers to the contextual condition that was
largely responsible for predicting an high ranking for this item. Note, that “with
family” condition could even decrease the rank of some items, i.e., their relevance
for the current context. However, some items become more attractive than others
(this specific museum in our case) if the group is a family. The other items, i.e.,
those not marked with the clock icon, are suited as well for the current contextual
situation. But we decided not to explain their relationship with the context to
highlight and better differentiate those marked with the clock icon from the rest.
This can be considered as a persuasive usage of the contextual information.
We have identified custom explanation messages for all the possible 54 con-
textual conditions listed previously. We note that even if more than one contex-
tual condition holds in the current recommendation session, and all of them are
actually used in the computation of the predicted score of each recommenda-
Fig. 2. ReRex screen for explaining recommendations.
tion, nevertheless the system exploits only one of them for the explanation. The
contextual condition that is used in the explanation is the most influential one
as estimated by the predictive model used by the recommender to predict the
relevance (rating) of items in the current context. This design choice is moti-
vated by a simplicity reason; we hypothesized that a single statement would be
easily understood by the users and ultimately would produce the best effect on
them. Naturally this issue, and more in general a better explanation function-
ality could be implemented in a future version of the system. In fact, as it will
be illustrated in the next section, the quality of these canned explanations were
not perceived by the users as strikingly good, indicating that better explanation
messages could be generated.
Some additional functions have been implemented to enable the user to better
exploit the system. The user can add a recommendation to her wish list, rate
an item, show the position of an item on the map. We also note that ReRex
recommendations are updated when a relevant contextual condition is changed
either by the user manually or is automatically acquired.
4 Experimental Evaluation
In order to measure the effectiveness of this approach we developed two variants
of our ReRex mobile recommender system. The first one is that described previ-
ously, the second variant is not context-aware, i.e., there is no possibility for the
user to specify the current context, the UI screen shown in Figure 1 (left), has
been removed, and no recommendation is marked with any icon, or explained
to stress the appropriateness for the current contextual situation. The predic-
tion model described in Equation 1 is simplified in this second variant, and the
parameters Bijcj are not learned. This variant does not offer any explanation
for the recommendation. Hence, comparing these two variants we could check
if context management in the prediction model and the proposed explanation
technique have a joint effect on user satisfaction compared to a system that does
not exploit context at all.
To achieve this goal the test participants, 20 in total, tried out both vari-
ants of the system (within groups experimental model), in a random order, and
executed, supported by each system, two similar but different tasks, related to
travel planning. After the user completed the assigned task using one system,
she was requested to fill out a usability questionnaire. These questions were ex-
tracted, and slightly adapted to the scope of our investigation, from the IBM
Computer System Usability Questionnaire. Then finally the subjects were re-
quested to compare the two systems. The full set of results of this evaluation
are reported in detail elsewhere and are beyond the scope of this paper [2]. In
summary, we can report that when the users were requested to directly compare
the two variants, 85% of the users preferred the context-aware version, and 95%
of the users considered the context-aware recommendations more appropriate.
with respect to the explanation functionality, the subjects rated their agree-
ments to the following two statements: (Q14) I am satisfied with the provided
contextual explanations; and (Q15) I believe that the contextual explanations
are useful. We observed a score of 1.05 for (Q14), and a higher score of 1.5 for
(Q15) (scores range from -2, strongly disagree, to 2, strongly agree). This shows
that the quality of the explanations is not yet optimal but the users clearly per-
ceived the importance of such feature. Summarizing the evaluation results we
observe that, even if this conclusion is supported by a limited number of testers,
the context-aware recommendations were considered more effective than those
produced by the non context-aware version. Moreover, the users largely agreed
on the importance of explanations even if they complained about the quality
of them. This indicates that the explanation is a very important component, it
strongly influenced the system acceptance, but the user is particularly sensible
to the quality of these explanation; and the formulation of these explanations
can be surely improved.
5 Conclusions and Future Work
In this paper we have illustrated the importance of exploiting a traveler con-
textual conditions when recommending POIs. The proposed mobile application
offers to the user context-aware recommendations that are justified and explained
by referring explicitly to the contextual situation in which the user will experi-
ence them. We have shown that the proposed system can offer effective context-
aware explanations that are generated by identifying the contextual conditions
that show the largest influence on the predicted relevance score (rating) of the
recommended items. In a live user study we have compared a context-aware ver-
sion to a non context-aware one. We have shown that the user acceptance and
satisfaction is larger for the context-aware version and that the users prefer this
version compared to another, with a very similar user interface, which does not
consider the request context and does not provide any explanations.
In a future work we want to better understand the individual role of per-
sonalization, contextualization, and explanations. In fact, in the study described
in this paper we have compared a system offering contextualization of the rec-
ommendations and explanations with a variant that misses both features. We
need to perform new experiments where the individual features are considered
independently: for instance, comparing two context-aware systems: with and
without explanations. A second issue was mentioned already in the paper and
refers to the measured low user satisfaction for the generated explanations. We
want to improve the quality of the explanations exploiting advanced natural
language processing techniques to better adapt the explanation to the type of
recommended item and using more information extracted from the predictive
model.
References
1. G. Adomavicius and A. Tuzhilin. Context-aware recommender systems. In F. Ricci,
L. Rokach, B. Shapira, and P. Kantor, editors, Recommender Systems Handbook,
pages 217–256. Springer Verlag, 2011.
2. L. Baltrunas, B. Ludwig, S. Peer, and F. Ricci. Context relevance assessment and
exploitation in mobile recommender systems. (to appear) Personal and Ubiquitous
Computing, 2011.
3. V. Bellotti, J. Begole, E. Chi, N. Ducheneaut, J. Fang, E. Isaacs, T. King, M. New-
man, K. Partridge, B. Price, P. Rasmussen, M. Roberts, D. Schiano, and A. Wal-
endowski. Activity-based serendipitous recommendations with the magitti mobile
leisure guide. In Proceedings of the 2008 Conference on Human Factors in Com-
puting Systems, CHI 2008, pages 1157–1166. ACM Press, 2008.
4. F. Cena, L. Console, C. Gena, A. Goy, G. Levi, S. Modeo, and I. Torre. Integrating
heterogeneous adaptation techniques to build a flexible and usable mobile tourist
guide. AI Communication, 19(4):369–384, 2006.
5. A. Dey. Understanding and using context. Personal and Ubiquitous Computing,
5(1):4–7, 2001.
6. Y. Koren. Collaborative filtering with temporal dynamics. In Proceedings of the
15th ACM SIGKDD international conference on Knowledge Discovery and Data
mining, KDD ’09, pages 447–456, New York, NY, USA, 2009. ACM.
7. F. Ricci. Mobile recommender systems. Journal of Information Technology and
Tourism, 12(3):205–231, 2011.
8. F. Ricci, L. Rokach, and B. Shapira. Introduction to recommender systems hand-
book. In F. Ricci, L. Rokach, B. Shapira, and P. Kantor, editors, Recommender
Systems Handbook, pages 1–35. Springer Verlag, 2011.
9. J. Swarbrooke and S. Horner. Consumer Behaviour in Tourism. Butterworth-
Heinemann, 2 edition, 2006.
10. N. Tintarev and J. Masthoff. Designing and evaluating explanations for recom-
mender systems. In F. Ricci, L. Rokach, B. Shapira, and V. Kantor, editors,
Recommender Systems Handbook, pages 479–510. Springer Verlag, 2011.