=Paper=
{{Paper
|id=Vol-1533/paper1
|storemode=property
|title=Spontaneous Event Recommendations on the Go
|pdfUrl=https://ceur-ws.org/Vol-1533/paper1.pdf
|volume=Vol-1533
|authors=Daniel Herzog,Wolfgang Wörndl
|dblpUrl=https://dblp.org/rec/conf/dmrs/HerzogW15
}}
==Spontaneous Event Recommendations on the Go==
https://ceur-ws.org/Vol-1533/paper1.pdf
Spontaneous Event Recommendations on the Go
Daniel Herzog and Wolfgang Wörndl
Department of Informatics,
Technische Universität München, Germany
{herzogd,woerndl}@in.tum.de
Abstract. In this paper, we summarize our previous work in the field
of event recommendations and give an outlook on future work. We de-
veloped a recommender system which implements a hybrid recommen-
dation technique to provide accurate recommendations. A two-week user
study showed that our system delivers promising results. Nevertheless,
we believe that this approach mainly supports users who are looking
for recommendations a long time in advance. Other possible situations
in which people could be open for recommendations are more sponta-
neous, for example, when they are already out exploring the city. We
give an overview of aspects which have to be considered fur such sponta-
neous recommendations on the go and the role of social context in this
scenario.
Keywords: Event Recommendations, Collaborative Filtering, Context-
Awareness, Mobile Application.
1 Introduction and Motivation
Recommending future events is more difficult than recommending items of other
domains such as movies or points of interest. Events are often unique because
they take place only one-time under the exact same conditions. Visitors cannot
rate the event before it takes place and their ratings are no longer of importance
for other potential visitors when the event is over [4]. These characteristics are
the reason why more sophisticated techniques have to be identified and evaluated
to ensure accurate event recommendations.
Our previous work presented first approaches to recommend events but these
systems mainly support users who want to receive recommendations a long time
in advance, before the actual event takes place. Nevertheless, when talking to
selected experts from the event and ticketing industry, we found out that espe-
cially young people often decide spontaneously to join events they might like.
One important factor in their decision making are the opinions of other impor-
tant persons like close friends.
During our research in the field of event recommendations, we developed a
mobile, context-aware event recommender system. In this paper, we present the
results of our previous research which are the basis for our future work. Our goal
is to find out under which circumstances (e.g., while driving a car or during a
2 Spontaneous Event Recommendations on the Go
sightseeing trip) users are open for joining recommended events spontaneously.
After identifying the context for such spontaneous recommendations, we want
to optimize them collaboratively, for example, by taking other people nearby or
friends’ opinions into account.
2 Previous Research Focus and Results
After conducting expert interviews with four selected representatives from the
German event and ticketing industry, we developed our first event recommender
system. In order to provide accurate recommendations, we implemented a hy-
brid recommendation algorithm based on Content-boosted Collaborative Filter-
ing (CBCF). CBCF is a recommendation technique which uses the output from
a content-based (CB) prediction to generate recommendations in the subsequent
collaborative filtering (CF) phase. Studies show that this combination promises
better recommendations than a pure CB or CF recommender [3]. Furthermore,
we extended the traditional CBCF approach by contextual pre-filtering of events.
Contextual pre-filtering is one paradigm for incorporating context into a recom-
mendation process and allows to immediately exclude events which are impos-
sible to recommend [1]. For example, an event taking place too far away from
the user’s location does not have to be considered for recommendation. Conse-
quently, the final algorithm is composed of three phases:
1. Contextual pre-filtering
2. Content-based prediction
3. Collaborative filtering
The contextual pre-filtering reduces the number of possible recommendations
before the actual recommendation process takes place. Events are filtered by a set
of context factors we evaluated during the expert interviews like the geographical
context, temporal factors and temporarily wanted or unwanted genres. The user
can set thresholds like the maximum distance to a venue and if the context of a
potential recommendation exceeds this threshold, the corresponding event will
not be considered for recommendation.
After excluding events which do not satisfy the context constraints, the CB
prediction phase takes place. For this, we adapt the classical CBCF approach
to the special case of event recommendations. We analyze event attributes rated
by the user in the past in order to estimate ratings for events comprising these
attributes. Based on the expert interviews we conducted, events are mainly char-
acterized by structured data. This is the reason why we propose a case-based
approach for the CB prediction of ratings, as presented by [6]. For each event
attribute (e.g., the venue), we count how often the user gave positive or negative
feedback to previous recommendations comprising this attribute. If the user’s
history provides feedback for a sufficient number of attributes of an event, a
prediction is called accurate. Similarity assessments can be used to calculate the
similarity between the item and the query, in this case the user history. The
output corresponds to the value of the recommended item for the user.
Spontaneous Event Recommendations on the Go 3
The calculated value is stored in the pseudo user-item rating matrix and used
for the upcoming CF phase. Its goal is to extend the matrix by taking ratings
of other users with similar preferences into account. For this purpose, we apply
a User-Based Nearest Neighbor algorithm [5].
In the end, the events with the highest value for the user are recommended.
Only recommendation with a value of at least 0.5 on a scale from 0 to 1 are
considered. Furthermore, we limit the maximum number of recommendations at
one request to 10 to avoid overwhelming the user with events.
We implemented the presented algorithm in a real working Android appli-
cation we developed. A Munich based event and ticketing company provided
a dataset with approximately 3700 real events which were used to conduct a
two-week user study. During this study, 16 participants tested and rated the
recommender system. Overall, they were satisfied with our solution (∅: 3.75, σ:
0.83, on a scale from 1 to 5 with 5 representing the best possible rating). The
recommendations met their expectations slightly above average (∅: 3.38, σ: 0.60)
and the study shows that they can be called sufficiently diversified (∅: 3.63, σ:
1.05). A majority of the participants, 87.5%, mentioned that they would like to
continue using the system to find interesting events in the future. In general,
they were satisfied with the choice of settings which allowed them to modify the
context-awareness, for example by defining thresholds like a radius or possible
time slots. Nevertheless, the participants requested further options to modify
the context-awareness, for example, the user’s current budget for events which
was not taken into account as this information was not available in our dataset.
3 Requirements for Spontaneous Event Recommendations
on the Go
Even though the presented algorithm takes context into account, we believe that
the recommender system mainly supports users in receiving recommendations
a certain time before the actual event takes place. The developed application
can be used at home and the geographical and temporal context settings allow
to adapt the recommendations to future conditions. This approach covers a big
share of potential visitors but it does not deliver further support for people who
are open towards spontaneous event visits. Examples are tourists who visit a
city for a few days and have some time left or young people going out in the
evening without having any concrete plans.
As a next step in our event recommendation research, we want to focus on
recommendations for events which take place in the same conditions as the cur-
rent user context. We call these recommendations spontaneous recommendations
on the go because the events take place shortly after the recommendation is gen-
erated and the venues have to be located in a reasonable distance to the user’s
current position. These kinds of recommendations demand the consideration of
additional context factors which were less important in our previous work. For
example, the current weather plays a critical role as bad weather may exclude
some outdoor activities. In addition, the duration of events is critical as, for ex-
4 Spontaneous Event Recommendations on the Go
ample, tourists usually have only a little time for visiting events. The fact that
the user is driving a car or taking the subway could have a significant influence
on the acceptance of recommendations. Sensors in mobile phones area already
precisely enough to determine which means of transportation the user is using
[2]. We also want to try other solutions of context incorporation and compare
the results to this work.
Social context is another relevant context factor which should be considered
in future work. For example, the user’s companions might influence her or his
decisions in regard to spontaneous event visits. Furthermore, our solution could
be improved by taking more sophisticated, collaborative methods into account.
Instead of regarding all users in the user-item rating matrix, only friends or
people nearby could be considered in some situations.
The goal of our research now is to identify all relevant context factors for
spontaneous recommendations on the go and to understand which kinds of event
recommendations are desirable under which circumstances. We want to imple-
ment the new algorithm in another prototype and test it again in a larger user
study. The results of this study then can be compared to our previous results in
order to measure the algorithm’s performance.
References
1. Adomavicius, G., Tuzhilin, A.: Context-aware recommender systems. In Ricci, F.,
Rokach, L., Shapira, B., Kantor, P. B. (eds.) Recommender Systems Handbook, pp.
217–253. Springer US (2011).
2. Kuramoto, I., Ishibashi, T., Yamamoto, K., Tsujino, Y.: Stand Up, Heroes! : Gam-
ification for Standing People on Crowded Public Transportation. In Marcus, A.
(eds.) Design, User Experience, and Usability. Health, Learning, Playing, Cultural,
and Cross-Cultural User Experience 2013. LNCS, vol. 8013, pp. 538–547. Springer
Berlin Heidelberg (2013)
3. Melville, P., Mooney, R.J., Nagarajan, R.: Content-Boosted Collaborative Filtering
for Improved Recommendations. In: Eighteenth National Conference on Artificial
Intelligence, pp. 187–192. American Association for Artificial Intelligence, Menlo
Park, CA, USA (2002)
4. Minkov, E., Charrow, B., Ledlie, J., Teller, S., Jaakkola, T.: Collaborative future
event recommendation. In: Proceedings of the 19th ACM International Conference
on Information and Knowledge Management, CIKM ’10, pp. 819–828. ACM, New
York, NY, USA (2010)
5. Schafer, J.B., Frankowski, D., Herlocker, J., Sen, S.: Collaborative Filtering Rec-
ommender Systems. In: Brusilovsky, P., Kobsa, A., Nejdl, W. (eds.) The Adaptive
Web 2007. LNCS, vol. 4321, pp. 291–324. Springer, Berlin Heidelberg (2007)
6. Smyth, B.: Case-based Recommendation. In: Brusilovsky, P., Kobsa, A., Nejdl, W.
(eds.) The Adaptive Web 2007. LNCS, vol. 4321, pp. 342–376. Springer, Berlin
Heidelberg (2007)