Conference PaperPDF Available

Context Incorporation in Cultural Path Recommendation Using Topic Modelling

Authors:

Abstract and Figures

Even though path recommendation is a subject that has been vigorously studied, the majority of related work has been predominantly focused on travel and routing topics, with relatively minimal incorporation of cultural context. The latter issue is addressed in the current contribution through the proposition of a personalized, context-aware cultural path recommendation system, aiming at achieving an enhanced cultural experience for its users. More specifically, topic modelling is used to represent the landmarks, where each location is modeled as a distribution of latent topics that eventually describe its characteristics. The initial approach is subsequently extended through the fusion of contextual aspects that include visitor profile, their behavior during the visit and other environmental parameters that might affect the cultural experience. In this work, a subset of contextual aspects, consisting of the type of visited location and the time the visit occurred, is considered. The overall system is evaluated on a benchmark dataset in order to assess the effect of the contextual dimension in the produced recommendations.
Content may be subject to copyright.
Context Incorporation in Cultural Path
Recommendation Using Topic Modelling
Konstantinos Michalakis1[0000000259436613], Georgios
Alexandridis1,2[0000000236118292] , George Caridakis1[000000019884935X],
and Phivos Mylonas3[0000000269163129]
1Cultural Technology Department, University of the Aegean, Mytilene, Greece
{kmichalak, gealexandri, gcari}@aegean.gr,
2School of Electrical & Computer Engineering, National Technical University of
Athens, Zografou, Greece,
3Department of Informatics, Ionian University, Corfu, Greece
fmylonas@ionio.gr
Abstract. Even though path recommendation is a subject that has been
vigorously studied, the majority of related work has been predominantly
focused on travel and routing topics, with relatively minimal incorpo-
ration of cultural context. The latter issue is addressed in the current
contribution through the proposition of a personalized, context-aware
cultural path recommendation system, aiming at achieving an enhanced
cultural experience for its users. More specifically, topic modelling is used
to represent the landmarks, where each location is modeled as a distri-
bution of latent topics that eventually describe its characteristics. The
initial approach is subsequently extended through the fusion of contex-
tual aspects that include visitor profile, their behavior during the visit
and other environmental parameters that might aect the cultural ex-
perience. In this work, a subset of contextual aspects, consisting of the
type of visited location and the time the visit occurred, is considered.
The overall system is evaluated on a benchmark dataset in order to assess
the eect of the contextual dimension in the produced recommendations.
Keywords: Personalized cultural user experience ·Cultural path rec-
ommendation ·Context-aware recommendation ·Topic m o dell ing.
1 Introduction
Cultural user experience is a subject that has recently gained enough popular-
ity, despite requiring complex procedures of formalization and evaluation [15].
Apart from the standard complexity incurred by the delivery of a personalized
experience, the content of cultural spaces is often enriched with characteristics
associated with its origin and whose correlation to the experience itself is very
tight. The extraction of those underlying aspects has not been adequately ex-
plored and while some route recommendation systems have been adapted for
cultural visits, the cultural aspects are usually not integrated into the process.
K. Michalakis et al.
Context integration, on the other hand, results in an enhanced perception of
the current situation by the system, with data not directly related to the objects
of interest. Typical contextual parameters include location,time,type of recom-
mended object and environmental conditions, allowing for a more insightful in-
terpretation of the surrounding environment. Most context-aware recommender
systems apply context-driven querying and search approaches that require the
matching of contextual data with resource metadata. On the contrary, contextual
filtering and modeling are sparsely used [26].
This work addresses the aforementioned issues by introducing a personalized,
context-aware and topic sensitive cultural path recommendation system. The
proposed architecture combines content modeling and context-awareness into a
unified approach that analyzes user behavior and enhances the recommendation
process with the contextual parameters of time and location. At the core of
the presented methodology lies topic modeling; a theoretical abstraction that
conceptualizes the aspects of user visits to Points of Interest (POIs). Context-
awareness is introduced into the model by formulating the relationship between
POIs and time as one contextual parameter and the correlation between user
and POI category as another.
2 Related Work
Recommender Systems (RSs) process user preference data in order to propose
items ranging from products to paths or actions. RSs have been applied to a
variety of domains and incorporate additional information sources, when avail-
able (e.g. from social networks [4]). In this sense, a popular extension is the
inclusion of contextual data, usually in the form of spatial, environmental and
behavioral parameters. This process adds context-awareness to RSs, resulting
in a further optimized and personalized user experience, based on the current
situation. Context-awareness may be combined in route RSs in location-aware
environments, where a path of actions or sites to be visited is proposed. Research
on such spatiotemporal modeling and prediction has been performed for both
travelers [5, 27] and drivers [16].
Route RSs usually rely on mining techniques in order to discover usable in-
formation, such as user behavior and trajectory patterns [11], fastest path and
route optimization based on user-specified destinations [20] and personalized
route recommendation extracted from big trajectory data [9]. The recommenda-
tion process often requires the dynamic modelling of users (e.g. normal schedule,
activity recognition); such functionality is incorporated in [22], where interactive
multi-criteria techniques are adopted on personalized tours that combine user
profile, preference and area characteristics. Multimodal information fusion may
also be used in RS in order to enrich the acquired knowledge; e.g. a route rec-
ommendation utilizing geotagged images in an eort to probabilistically model
user behavior is adopted in [17]. Research on the integration of social and crowd-
sourcing techniques for the improvement of recommendation performance has
been conducted in [10, 24].
63
Context-awareness may be introduced to RSs either in a pre-filtering or a
post-filtering fashion, depending on whether contextual processing occurs before
or after the application of the recommendation algorithm. The two approaches
are compared in [3], where it is concluded that no method outperforms the
other and that their suitability is highly dependent on the application domain.
A further classification of contextual information in RSs is proposed in [21],
where the lack of studies in the non-representational views of context is also
illustrated. Recent advances on computational intelligence have also fueled more
ecient and more complex RSs that apply context-awareness with the use of
neural networks,fuzzy sets and other similar machine learning techniques [1].
In general, context-aware RSs in the cultural heritage domain have found
little applications so far and context is usually limited to spatial characteristics.
In [6], a framework that manages heterogeneous multimedia data gathered from
various web sources is suggested, which results in a context-aware recommenda-
tion process. SmartMusem [23] is a mobile RS that uses ontology-based reason-
ing, query expansion and context knowledge, achieving optimized performance.
Finally, an ontology based pre-filtering and contextual processing post-filtering
hybrid technique is used to provide optimized tour recommendations in [7].
3 User Modeling
Auser model is a theoretical concept that tries to formulate a person’s in-
terests (motion patterns in-between POIs or landmarks in this case). Various
approaches to user modeling exist, with some of them having already been pre-
sented in Section 2. In sites of cultural interest (museums, archaeological sites,
cities, etc), the userbase and the available options are usually constrained and
as a result the collected data tend to be of relatively small volume, especially
when compared with the massive userbase and itemsets of other domains (movie
or music recommendation). In the former cases, statistical models seem to be a
good starting point for user modeling and this approach has been followed in
this work. More specifically, topic modelling, a statistical approach to user mod-
elling is presented in Section 3.1, while the aforementioned technique is extended
through the fusion of contextual information in Section 3.2.
3.1 Topic Modeling
Atopic model is a hierarchical probabilistic model that quantifies the relation-
ship between users (visitors) and items (landmarks they have visited) through
the notion of topics [8]. In this setting, visitor interest is expressed as mixture of
topics, while each topic is modelled as a probability distribution over the land-
marks. Of course, topics are not known in advance; in fact their estimation is
the objective of the algorithm and for this reason they are considered to be the
latent features of the model. In general, topic models have been used in the area
of information retrieval [13] and in preference modelling and personalization [14,
2]. The most notable topic modelling techniques are Latent Dirichlet Allocation
Context Incorporation in Cultural Path Recommendation using TM 64
K. Michalakis et al.
(LDA) [8], Latent Semantic Analysis (LSA) and Probabilistic LSA (PLSA) [12],
which is also the technique of choice in this contribution.
More formally, let Lbe the set of points of interest (POIs) of a cultural
location, which can be of any type; constrained withing a building (e.g. museum),
an open space (e.g. cultural site) or even a broader place (e.g. the historical center
of a city). In either of these cases, POIs could be exhibits, landmarks or distinct
places.
The set of visitors (users) is denoted as Uand every visitor u2Uis primarily
characterized by a record hu(l0,l
1,...,l
t1), which is the sequence of POIs
visited by uup until time t1. Therefore, the objective of the model and the
RS in general, is to predict the POIs the user is going to visit next.
Topic models address this issue by making the basic assumption that visits
to future POIs are conditionally independent from the current record (history)
huof u. Consequently, the probability P(lt|hu) of uvisiting POI ltat time t,
given hu, is approximated according to Equation 1
P(lt|hu)=X
z2Z
P(lt|z)P(z|hu) (1)
where P(z|hu) expresses the extend to which the “hidden” topic zis of interest
to uwhile P(lt|z) quantifies how much POI ltis described by topic z. In more
simple words, P(z|hu) models visitor interest in this topic and P(lt|z)represents
the coverage (“trend”) of topic z.
As both probabilities of the right-hand side of Equation 1 cannot be deter-
mined analytically, they are approximated through Expectation-Maximization
(EM). EM is an iterative procedure particularly useful in determining the max-
imum likelihood in statistical models dependent upon “latent” parameters, like
this one. A typical EM iteration consists of two steps, the Expectation Step,
where the posterior probability of each latent topic zis computed, given the
parameters lt,h
uof the model (Equation 2)
P(z|l, hu)= P(z|hu)P(l|z)
P
z02Z
P(z0|hu)P(l|z0)(2)
and a Maximization Step, where model parameters are updated (Equations 3-4)
in order to maximize the likelihood (Equation 2)
P(z|hu)/X
l2L
N(l, hu)P(z|l, hu) (3)
P(l|z)/X
u2U
N(l, hu)P(z|l, hu) (4)
where N(l, hu) designates the number of times POI l occurs in the history
(record) of u. P(z|hu) and P(l|z) are initialized to some random values.
Finally, the steps described in Equations 2-4 are repeated until convergence
(that is, when P(z|hu) and P(l|z) reach an equilibrium).
65
3.2 Context Modelling
The most straightforward way of fusing spatial attributes in RS is to model
them as an extra multiplicative term in Equation 1, yielding Equation 5 below
Ps(lt|hu)=P(lt|hu)N(x|u)
C(hu)(5)
In a similar fashion, Equation 5 may be further extended by yet another
multiplicative term that models temporal attributes, as in Equation 6 below
Ps,t(lt|hu)=Ps(lt|hu)P(f|l)
C(l)(6)
where Ps(lt|hu)wis the adjusted posterior probability of context-aware model
of Equation 5, Ps,t(lt|hu) is the posterior probability of the new context-aware
model combining spatial and temporal features, P(f|l) is the probability of lo-
cation lto be visited at time fby all users and C(l) is a normalization factor
with a similar role to C(hu).
4 Experiments & Results
4.1 Dataset
4https://flickr.com/
Context Incorporation in Cultural Path Recommendation using TM
Context modelling is the inclusion of contextual information in the recommenda-
tion process. Context, in a RS framework, is predominantly linked to the location
of the users (e.g. home, workplace, public place) and the time the recommenda-
tions are either requested or produced, ranging from hours (morning, evening),
to days (workdays, weekends) and beyond (holiday periods) [3]. This represen-
tation of location and time implies that both quantities are described by a set
of characteristic attributes; therefore let X be the set of spatial attributes and
Y the set of temporal attributes, respectively.
where P(lt|hu) is the posterior probability of the contextless model, Psp(lt|hu)
is the adjusted posterior probability of the context-aware model, N(x|u) is the
frequency of spatial attribute x X associated with location l being visited by
user u at time t and finally C(hu) is a normalization factor that ensures Equation
5 remains a probability distribution.
The aforementioned models, contextless and context-aware, have been evaluated
on the Flickr User-POI Visits Dataset [25], which is comprised of user visits
to various Points of Interest (POIs) in eight cities. Table 1 summarizes the
dataset characteristics
Entries in the dataset correspond to geotagged photos uploaded by users
on Flickr4, an image and video hosting service. Apart from the photo and user
ids, each entry contains other useful metadata, such as the photo timestamp,
the id and theme (category) of the photographed POI, the frequency this spe-
cific location has been photographed (visited) by other users in the dataset and
66
K. Michalakis et al.
Tabl e 1 . General dataset characteristics
Characteristic Value
Number of cities 8
Number of visits 153,208
Number of paths 21,186
Number of users 5,595
Average user-based path length 27.38
Average sequence-based path length 7.23
POI Categories (themes) 18
finally a sequence id. Sequence ids group photographs uploaded by the same
user together, based on their timestamp; more specifically, photographs taken
by a single user within a time frame of 8 hours are considered to belong to the
same sequence. In addition to the metadata presented above, each POI is also
characterized by its name, its coordinates (latitude and longitude) and a matrix
containing the distances in-between POIs of the same city.
4.2 Data Preprocessing
Path types and length According to the description of the dataset above,
visitor paths may be determined in two ways; on a user basis or on a sequence
basis. The latter option seems to be more natural, as sequences incorporate the
temporal dimension of each visit, in the sense that geotagged photos of a certain
user may span several days. However, sequence-based paths in the dataset are
extremely short. This is evident both in Table 1, where the average sequence-
based path length is just above 7 and in Figure 1, which depicts the number
of paths of a given path-length; the overwhelming majority of sequence-based
paths has a length between 1 and 3.
The same observation holds true for user-based path lengths as well (Figure
2). In this case, however, there exists a certain fraction of users whose path
lengths are well above the short-path margins of the previous case. Therefore,
in our analysis we considered user-based paths.
It could be argued that in considering user-based paths, the temporal context
of the recommendations is overlooked. While there is a certain validity in this
argument, it should also be stressed out that such an assumption does not hurt
This specific dataset has been previously used in [18], where a tour recom-
mendation framework is implemented and the PersTour algorithm is introduced
(exhibiting better performance than the baseline algorithms of Greedy Near-
est and Greedy Most Popular). The described system recommends a complete
route to the visitor based on his/her previous sequences, while also
exploiting the cost/benefit of each proposed route. Expanding on this idea, the
authors in [19] group visitors of similar POIs, recommending tour itineraries
for groups rather than isolated users. To the best of our knowledge, our
approach is among the first to explore the contextual dimensions of this
dataset.
67
0
1
2
3
4
5
6
7
8
9
10
0 5 10 15 20 25 30 35 40 45 50
Number of paths (in thousands)
Path length
Fig. 1. Distribution of sequence-based paths in the dataset
0
200
400
600
800
1000
1200
1400
0 5 10 15 20 25 30 35 40 45 50
Number of paths
Path length
Fig. 2. Distribution of user-based paths in the dataset
the performance of the RS, as it is still able to predict new places that the users
might have not visited in their previous visits.
Having fixed the way paths are determined (user-based instead of visitor-
based paths), a decision should be made on the minimum path length. It is
obvious that paths of short length are of no practical use to a RS and therefore
need to be filtered out. This is achieved by defining a threshold on the minimum
path length. Based on the reasoning above and after some experimentation, the
optimal value of the minimum path length has been set to 5.
Context Incorporation in Cultural Path Recommendation using TM
Number of latent features The number of latent features (parameter z) of
the models described in Equations 1, 5-6 (Section 3) aects the performance of
the respective RSs. Figure 3 depicts the performance of the topic model-based
approach (Equation 1) on the visitors of the city of Budapest, Hungary.
68
K. Michalakis et al.
30 %
31 %
32 %
33 %
34 %
35 %
36 %
2 4 6 8 10 12 14 16
Accuracy
Number of latent features
Fig. 3. The influence of the number of latent features on the performance of the topic
modelling approach on the Budapest, Hungary subset of the dataset
It can be seen that the performance gradually rises, along with the dimen-
sionality of the latent feature space, until it reaches a climax. Increasing zbeyond
that point is of no benefit to the model, as it cannot generalize. Therefore, de-
termining the optimum value for zis a hyperparameter of the overall approach,
dependent on the specific technique used and the data. By definition, the latent
feature space is smaller than the quantities it models (users and number of POIs
in this case). As the number of POIs per city ranges between 26 (in Perth, Aus-
tralia) and 40 (in Budapest, Hungary), the optimum value for zhas been sought
in the range of [2,20] and it was found to be between 8 and 12 for all cities in
the dataset.
4.3 Experiments
The experimentation protocol followed has been the leave-one-out cross-
validation. At each iteration of the protocol one user is picked as the test user and
the path s/he follows is split into two parts; the training part and the test part.
This step is necessary for the models in order to approximate the distribution
of the test user’s interest in the latent topics (Equation 3). After experimenting
with various train and test set sizes, we ended up using the first 25% of the
path as the training set and the rest 75% as the test set. Consequently, when
Having fixed the parameters and the hyperparameters of the proposed approach,
the specifics of the experimental procedure need to be addressed. Since there is
no connection (geographical or otherwise semantic) in-between the 8 cities of
the dataset, 8 distinct sub-experiments were performed, pertaining to the
data of each city. For each sub-experiment, four dierent approaches were
considered; the contextless topic model of Equation 1, the inclusion of either
the spatial or the temporal contextual information (Equation 5) and finally the
incorporation of both contextual dimensions (Equation 6).
69
training was over, the RS proposed POIs to the test user and those recommen-
dations were compared with the POIs in the test set in order to estimate system
performance.
The second parameter is a temporal one, namely the time the visit took
place. The time is deduced from the timestamps of the photographs and it can
be exploited to add contextual information about the periods within the day
that each specific POI is accessed (for example, park visits usually occur during
the day time). In the proposed approach, the time period corresponding to a day
is split into time windows and then the frequency of the visits within each time
window is measured for each POI. Then the posterior probability of uvisiting
landmark ltnext is adjusted according to the current time window and the
aforementioned frequency. After experimenting with various time window sizes,
the optimal value has been determined to be 8 hours. Finally, the two contextual
parameters discussed above are integrated in the unified procedure of Equation
6.
5 Conclusions
In this work, a methodology of integrating contextual elements in cultural path
recommendation has been outlined and experimentally evaluated on a dataset
Context Incorporation in Cultural Path Recommendation using TM
Context integration The dataset included two contextual parameters that
could be exploited by the context-aware methodologies proposed in this
work. The first one is a spatial parameter, the category or “theme” of the
visited POI. It is a categorical variable that can take 18 distinct values, which
are related to the cultural aspect of the visited POI (e.g. “Museum”, “Histori-
cal”, “Cultural”). Themes are indicative of the type of POIs each visitor prefers
and therefore their modelling can be used to provide more personalized cultural
recommendations. In this approach, and according to Equation 5, the frequency
of the visited theme is initially calculated, adjusting the posterior probability
Ps(lt|hu) of u visiting landmark lt next. After this adjustment, the model rec-
ommends the next POI to be visited, hopefully having gained some insight on
the user’s cultural preferences and achieving better performance.
Results Figure 4 summarizes the results of the experimental procedure for all
4 models and for the 8 cities. An initial observation is that the addition of the
contextual information increases the accuracy of the recommendations in all
cases by a margin of at least 5%. This is especially evident in the case of Perth,
Australia, Glasgow, Scotland and Osaka, Japan and it is a clear indication that
the incorporation of context is a process that enhances the overall quality of
the recommendations. Additionally, a qualitative analysis on the cities where
the RSs exhibited better results reveals that the visitors in these cases were
associated with longer paths, which permitted the context-aware process to more
thoroughly aect the functionality of the model.
70
K. Michalakis et al.
20 %
25 %
30 %
35 %
40 %
45 %
50 %
55 %
60 %
Budapest
Delhi
Perth
Vienna
Edinburgh
Glasgow
Toronto
Osaka
Fig. 4. Performance results of all models on all cities
References
1. Abbas, A., Zhang, L., Khan, S.U.: A survey on context-aware recommender systems
based on computational intelligence techniques. Computing 97(7), 667–690 (2015)
2. Abel, F., Gao, Q., Houben, G.J., Tao, K.: Analyzing user modeling on twitter for
personalized news recommendations. In: International Conference on User Model-
ing, Adaptation, and Personalization. pp. 1–12. Springer (2011)
3. Adomavicius, G., Tuzhilin, A.: Context-aware recommender systems. In: Recom-
mender systems handbook, pp. 217–253. Springer (2011)
Contextless
Context (theme)
Context (time)
Context (theme time)
of geotagged photos taken by visitors in eight cities. More specifically, the POIs
visited by the users were modeled according to topic modeling, enabling the
enhancement of the recommendation process with cultural location awareness.
Furthermore, implicitly inferred context has been extracted from the dataset
(POI theme and the time window within the day that each POI is visited).
The measured performance demonstrated an increase of accuracy, when the
contextual parameters were integrated.
The experimental results indicate that the inclusion of context-awareness into
the recommendation process enhances the ability of the system to optimize its
predictions. The achieved increase in accuracy is a promising result, pointing out
that measuring and incorporating contextual data can greatly impact the overall
system accuracy. Adding further and more explicit contextual data, such as user
profile information (age, educational level, etc.) or environmental parameters
(weather conditions, crowd density, etc.) is expected to result in even better
recommendations.
71
4. Alexandridis, G., Siolas, G., Stafylopatis, A.: Accuracy Versus Novelty and Diver-
sity in Recommender Systems: A Nonuniform Random Walk Approach, pp. 41–57.
Springer International Publishing, Cham (2015). https://doi.org/10.1007/978-3-
319-14379-8 3, https://doi.org/10.1007/978-3- 319-14379- 8_3
5. Ashbrook, D., Starner, T.: Using gps to learn significant locations and predict
movement across multiple users. Personal and Ubiquitous computing 7(5), 275–
286 (2003)
6. Bartolini, I., Moscato, V., Pensa, R.G., Penta, A., Picariello, A., Sansone, C.,
Sapino, M.L.: Recommending multimedia visiting paths in cultural heritage appli-
cations. Multimedia Tools and Applications 75(7), 3813–3842 (2016)
7. Benouaret, I., Lenne, D.: Personalizing the museum experience through context-
aware recommendations. In: Systems, Man, and Cybernetics (SMC), 2015 IEEE
International Conference on. pp. 743–748. IEEE (2015)
8. Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. Journal of machine
Learning research 3(Jan), 993–1022 (2003)
9. Dai, J., Yang, B., Guo, C., Ding, Z.: Personalized route recommendation using
big trajectory data. In: Data Engineering (ICDE), 2015 IEEE 31st International
Conference on. pp. 543–554. IEEE (2015)
10. Doytsher, Y., Galon, B., Kanza, Y.: Storing routes in socio-spatial networks and
supporting social-based route recommendation. In: Proceedings of the 3rd ACM
SIGSPATIAL International Workshop on Location-Based Social Networks. pp. 49–
56. ACM (2011)
11. Giannotti, F., Nanni, M., Pinelli, F., Pedreschi, D.: Trajectory pattern mining. In:
Proceedings of the 13th ACM SIGKDD International Conference on Knowledge
Discovery and Data Mining. pp. 330–339. ACM (2007)
12. Hofmann, T.: Probabilistic latent semantic indexing. In: Proceedings of the
22Nd Annual International ACM SIGIR Conference on Research and Develop-
ment in Information Retrieval. pp. 50–57. SIGIR ’99, ACM, New York, NY,
USA (1999). https://doi.org/10.1145/312624.312649, http://doi.acm.org/10.
1145/312624.312649
13. Hofmann, T.: Collaborative filtering via gaussian probabilistic latent semantic anal-
ysis. In: Proceedings of the 26th annual international ACM SIGIR conference on
Research and development in informaion retrieval. pp. 259–266. ACM (2003)
14. Iwata, T., Watanabe, S., Yamada, T., Ueda, N.: Topic tracking model for analyzing
consumer purchase behavior. In: IJCAI. vol. 9, pp. 1427–1432 (2009)
15. Konstantakis, M., Michalakis, K., Aliprantis, J., Kalatha, E., Caridakis, G.: For-
malising and evaluating cultural user experience. In: Semantic and Social Media
Adaptation and Personalization (SMAP), 2017 12th International Workshop on.
pp. 90–94. IEEE (2017)
16. Krumm, J., Horvitz, E.: Predestination: Inferring destinations from partial tra-
jectories. In: International Conference on Ubiquitous Computing. pp. 243–260.
Springer (2006)
17. Kurashima, T., Iwata, T., Irie, G., Fujimura, K.: Travel route recommendation
using geotagged photos. Knowledge and Information Systems 37(1), 37–60 (Oct
2013). https://doi.org/10.1007/s10115-012-0580-z
18. Lim, K.H., Chan, J., Leckie, C., Karunasekera, S.: Personalized tour recommen-
dation based on user interests and points of interest visit durations. In: IJCAI.
vol. 15, pp. 1778–1784 (2015)
19. Lim, K.H., Chan, J., Leckie, C., Karunasekera, S.: Towards next generation touring:
Personalized group tours. In: ICAPS. pp. 412–420 (2016)
Context Incorporation in Cultural Path Recommendation using TM 72
K. Michalakis et al.
20. Lu, E.H.C., Lee, W.C., Tseng, V.S.: Mining fastest path from trajectories with
multiple destinations in road networks. Knowledge and information systems 29(1),
25–53 (2011)
21. Panniello, U., Tuzhilin, A., Gorgoglione, M., Palmisano, C., Pedone, A.: Exper-
imental comparison of pre-vs. post-filtering approaches in context-aware recom-
mender systems. In: Proceedings of the third ACM conference on Recommender
systems. pp. 265–268. ACM (2009)
22. Rodriguez, B., Molina, J., Perez, F., Caballero, R.: Interactive design of
personalised tourism routes. Tourism Management 33(4), 926 – 940 (2012).
https://doi.org/https://doi.org/10.1016/j.tourman.2011.09.014
23. Ruotsalo, T., Haav, K., Stoyanov, A., Roche, S., Fani, E., Deliai, R., M¨akel¨a, E.,
Kauppinen, T., Hyv¨onen, E.: Smartmuseum: A mobile recommender system for
the web of data. Web semantics: Science, services and agents on the world wide
web 20, 50–67 (2013)
24. Su, H., Zheng, K., Huang, J., Jeung, H., Chen, L., Zhou, X.: Crowdplanner: A
crowd-based route recommendation system. In: Data engineering (ICDE), 2014
IEEE 30th International Conference on. pp. 1144–1155. IEEE (2014)
25. Thomee, B., Shamma, D.A., Friedland, G., Elizalde, B., Ni, K., Poland, D., Borth,
D., Li, L.J.: The new data and new challenges in multimedia research. arXiv
preprint arXiv:1503.01817 1(8) (2015)
26. Verbert, K., Manouselis, N., Ochoa, X., Wolpers, M., Drachsler, H., Bosnic, I.,
Duval, E.: Context-aware recommender systems for learning: a survey and future
challenges. IEEE Transactions on Learning Technologies 5(4), 318–335 (2012)
27. Zheng, Y., Zhang, L., Xie, X., Ma, W.Y.: Mining interesting locations and travel se-
quences from gps trajectories. In: Proceedings of the 18th international conference
on World wide web. pp. 791–800. ACM (2009)
73
... Likewise, in [142] designed a travel itinerary recommender based on dimension trees of contextual features, an inferential tourist guide engine, and a recommendation engine. In [143] proposed a recommender of cultural routes based on the geotagged photos' content, the temporal context, and the geographical location. For this, it used a thematic model based on the PLSA of POIs and visitors. ...
Article
Full-text available
Recommendation systems have overcome the overload of irrelevant information by considering users’ preferences and emotional states in the fields of tourism, health, e-commerce, and entertainment. This article reviews the principal recommendation approach documents found in scientific databases (Elsevier’s Scopus and Clarivate Web of Science) through a scientometric analysis in ScientoPy. Research publications related to the recommenders of emotion-based tourism cover the last two decades. The review highlights the collection, processing, and feature extraction of data from sensors and wearables to detect emotions. The study proposes the thematic categories of recommendation systems, emotion recognition, wearable technology, and machine learning. This paper also presents the evolution, trend analysis, theoretical background, and algorithmic approaches used to implement recommenders. Finally, the discussion section provides guidelines for designing emotion-sensitive tourist recommenders.
Article
Full-text available
Tour recommendation and itinerary planning are challenging tasks for tourists, due to their need to select points of interest (POI) to visit in unfamiliar cities and to select POIs that align with their interest preferences and trip constraints. We propose an algorithm called PersTour for recommending personalized tours using POI popularity and user interest preferences, which are automatically derived from real-life travel sequences based on geo-tagged photographs. Our tour recommendation problem is modeled using a formulation of the Orienteering problem and considers user trip constraints such as time limits and the need to start and end at specific POIs. In our work, we also reflect levels of user interest based on visit durations and demonstrate how POI visit duration can be personalized using this time-based user interest. Furthermore, we demonstrate how PersTour can be further enhanced by: (i) a weighted updating of user interests based on the recency of their POI visits and (ii) an automatic weighting between POI popularity and user interests based on the tourist’s activity level. Using a Flickr dataset of ten cities, our experiments show the effectiveness of PersTour against various collaborative filtering and greedy-based baselines, in terms of tour popularity, interest, recall, precision and F(Formula presented.)-score. In particular, our results show the merits of using time-based user interest and personalized POI visit durations, compared to the current practice of using frequency-based user interest and average visit durations.
Conference Paper
Full-text available
Recommending and planning tour itineraries are challenging and time-consuming for tourists, hence they may seek tour operators for help. Traditionally tour operators have offered standard tour packages of popular locations, but these packages may not cater to tourist's interests. In addition, tourists may want to travel in a group, e.g., extended family, and want an operator to help them. We introduce the novel problem of group tour recommendation (GroupTourRec), which involves many challenges: forming tour groups whose members have similar interests; recommending Points-of-Interests (POI) that form the tour itinerary and cater for the group's interests; and assigning guides to lead these tours. For each challenge, we propose solutions involving: clustering for tourist groupings; optimizing a variant of the Orienteering problem for POI recommendations; and integer programming for tour guide assignments. Using a Flickr dataset of seven cities, we compare our proposed approaches against various baselines and observe significant improvements in terms of interest similarity, total/maximum/minimum tour interests and total tour guide expertise.
Article
Full-text available
The valorization and promotion of worldwide Cultural Heritage by the adoption of Information and Communication Technologies represent nowadays some of the most important research issues with a large variety of potential applications. This challenge is particularly perceived in the Italian scenario, where the artistic patrimony is one of the most diverse and rich of the world, able to attract millions of visitors every year to monuments, archaeological sites and museums. In this paper, we present a general recommendation framework able to uniformly manage heterogeneous multimedia data coming from several web repositories and to provide context-aware recommendation techniques supporting intelligent multimedia services for the users—i.e. dynamic visiting paths for a given environment. Specific applications of our system within the cultural heritage domain are proposed by means of real case studies in the mobile environment related both to an outdoor and indoor scenario, together with some results on user’s satisfaction and system accuracy.
Chapter
In this chapter, we focus on recommender systems that are enhanced with social information in the form of trust statements between their users. The trust information may be processed in a number of ways, including the random walks in the social graph, where every step in the walk is chosen almost uniformly at random from the available choices. Although this strategy yields satisfactory results in terms of the novelty and the diversity of the produced recommendations, it exhibits poor accuracy because it does not fully exploit the similarity information among users and items. Our work tries to model user-to-user and user-to-item relation as a probability distribution using a novel approach based on Rejection Sampling in order to decide its next step (biased random walk). Some initial results on reference datasets indicate that a satisfying trade-off among accuracy, novelty, and diversity is achieved.
Article
The demand for ubiquitous information processing over the Web has called for the development of context-aware recommender systems capable of dealing with the problems of information overload and information filtering. Contemporary recommender systems harness context-awareness with the personalization to offer the most accurate recommendations about different products, services, and resources. However, such systems come across the issues, such as sparsity, cold start, and scalability that lead to imprecise recommendations. Computational Intelligence (CI) techniques not only improve recommendation accuracy but also substantially mitigate the aforementioned issues. Large numbers of context-aware recommender systems are based on the CI techniques, such as: (a) fuzzy sets, (b) artificial neural networks, (c) evolutionary computing, (d) swarm intelligence, and (e) artificial immune systems. This survey aims to encompass the state-of-the-art context-aware recommender systems based on the CI techniques. Taxonomy of the CI techniques is presented and challenges particular to the context-aware recommender systems are also discussed. Moreover, the ability of each of the CI techniques to deal with the aforesaid challenges is also highlighted. Furthermore, the strengths and weaknesses of each of the CI techniques used in context-aware recommender systems are discussed and a comparison of the techniques is also presented.
Conference Paper
Route recommendation service has become a big business in industry since traveling is now an important part of our daily life. We can travel to unknown places by simply typing in our destination and then following recommendation service's guidance, that a pleasant trip desires them to provide a good route. However, previous research shows that even the routes recommended by the big-thumb service providers can deviate significantly from the routes travelled by experienced drivers since the many latent factors affect drivers' preferences and it is hard for a single route recommendation algorithm to model all of them. In this demo we will present the CrowPlanner system to leverage crowds' knowledge to improve the recommendation quality. It requests human workers to evaluate candidates routes recommended by different sources and methods, and determines the best route based on the feedbacks of these workers. In this demo, we first introduce the core component of our system for smart question generation, and then show several real route recommendation cases and the feedback of users.
Article
We propose a travel route recommendation method that makes use of the photographers’ histories as held by social photo-sharing sites. Assuming that the collection of each photographer’s geotagged photos is a sequence of visited locations, photo-sharing sites are important sources for gathering the location histories of tourists. By following their location sequences, we can find representative and diverse travel routes that link key landmarks. Recommendations are performed by our photographer behavior model, which estimates the probability of a photographer visiting a landmark. We incorporate user preference and present location information into the probabilistic behavior model by combining topic models and Markov models. Based on the photographer behavior model, proposed route recommendation method outputs a set of personalized travel plans that match the user’s preference, present location, spare time and transportation means. We demonstrate the effectiveness of the proposed method using an actual large-scale geotag dataset held by Flickr in terms of the prediction accuracy of travel behavior.
Article
The tourism sector has evolved in recent times, with a transformation in tourists’ preferences and behaviour. They are increasingly abandoning standard tours in favour of more personalised options. New technologies offer easy access to a large amount of tourism information. However, this also means it is difficult for a decision-maker to assess all the possible alternatives for designing a customised trip. Making such decisions may well require the resolution of conflicting objectives. Therefore, in this paper we develop a tool that provides each tourist with the itinerary best suited to their needs. This itinerary can include the desired different activities on an established schedule, bearing in mind the tourist’s wishes and needs, along with the characteristics of the area. This is done by using a mathematical model and interactive multi-criteria techniques. Finally, we will carry out a practical application in the Autonomous Region of Andalusia.