=Paper=
{{Paper
|id=Vol-1280/paper3
|storemode=property
|title=A Case Study of Active, Continuous and Predictive Social Media Analytics for Smart City
|pdfUrl=https://ceur-ws.org/Vol-1280/paper3.pdf
|volume=Vol-1280
|dblpUrl=https://dblp.org/rec/conf/semweb/BalduiniBBVHOPT14
}}
==A Case Study of Active, Continuous and Predictive Social Media Analytics for Smart City==
https://ceur-ws.org/Vol-1280/paper3.pdf
A Case Study of Active, Continuous and
Predictive Social Media Analytics for Smart City
Marco Balduini1 , Stefano Bocconi2 , Alessandro Bozzon2 ,
Emanuele Della Valle1 , Yi Huang3 , Jasper Oosterman2 , Themis Palpanas4 , and
Mikalai Tsytsarau5
1
Politecnico di Milano - DEIB, Milano, Italy
2
Delft University of Technology - WIS, Delft, the Netherlands
3
Siemens - Corporate Technology, Munich, Germany
4
Paris Decartes University - Paris, France
5
University of Trento - DISI, Trento, Italy
Abstract. Imagine you are in Milano for the Design Week. You have
just spent a couple of days attending few nice events in Brera district.
Which of the other hundreds of events spread around in Milano shall you
attend now? This paper presents a system able to recommend venues to
the visitors of such a city-scale event based on the digital footprints
they left on Social Media. By combining deductive and inductive stream
reasoning techniques with visitor-modeling functionality, this system se-
mantically analyses and links visitors’ social network activities to pro-
duce high-quality recommendations even when information about visi-
tors’ preferences for venues and events is sparse.
Keywords: Social Media Analytics, User Modeling, Stream Reasoning,
Link Prediction, Recommendation, User Engagement
1 Introduction
Thanks to the widespread adoption of smart phones, location-based Social Media
capture an increasingly accurate and up-to-date digital reflection of our cities. In
particular, they allow to observe a constantly reshaping network of people that
interacts with places around the city, while talking about a variety of topics.
Being able to predict in real time changes in such a network is of major inter-
est for many applications supporting multiple city stakeholders. Short-term pre-
dictions may be of interest for tourists and citizens, while medium-term predic-
tions may be useful for city-scale service managers. Tourists may receive precise
and timely recommendations to explore places of their interest while sightseeing.
Citizens may be informed to avoid means of public transport that are predicted
to be crowded. Bike-sharing managers may plan for the availability and the re-
balancing of bikes in the stalls based on the predictions of people moving from
one neighbourhood to another.
To reach these goals, a system has to fulfil the following requirements:
R.1 build from one or more social media sources a network whose nodes represent
people, places and topics while edges represent the presence of people in
places, and the interest of people in topics
R.2 track the evolution of such network in real time to detect changes, both in
terms of nodes in the graph and in terms of edges
R.3 predict the possible changes in the graph
R.4 use the prediction to address specific needs, such as resource planning
In a previous work [3], we proposed a Continuous Predictive Social Media
Analytics (CP-SMA) solution that addressed the four requirements above. The
key innovation of CP-SMA is its ability to predict the appearance of edges in the
graph when little or no training information about existing edges is available.
Such conditions are typical for city-scale events (CSE) like the Milano Design
Week (MDW). Geographically limited to the city of Milano, the MDW featured
thousands of events attended by half a million visitors in half a thousand venues
that serve as temporary exhibition centres. Large part of the visitors come from
abroad. The venues hosting the events are temporary. Even associations between
visitors and venues are not applicable across different editions of the event,
because visitors, venues and events change every year.
CP-SMA was shown in the lab to accurately predict associations between
visitors of MDW 2013 and its venues after only 3 days of observations [3]. In
this paper, we report a real-time case study of CP-SMA deployed for MDW 2014,
in collaboration with fuorisalone.it6 , with the purpose of recommending venues
to visitors who were detected to talk about MDW on Twitter. We evaluate the
quality of the prediction by checking if the predicted associations are observed
after the prediction is made. Our evaluation provides evidence that visitor-venue
links can be discovered with a good balance between precision and recall, and
sentiment annotations can be added to micro-posts with good accuracy. The
evaluation also implicitly demonstrates the ability to build historical and event-
related topical profiles of visitors by semantically analysing their social network
activities.
The remainder of the paper is organised as follows. Section 2 presents the
architecture of the solution deployed for MDW 2014. Section 3 illustrates the
middleware, which we used to connect the components. Section 4 addresses R.1
and R.2, describing the solution used to identify visitors and to track the evo-
lution of their associations with places (see also [4]). Section 5 describes the
solution used to address R.1 and R.2 with regards to discovering links between
visitors and topics. Section 6 details the robust machine learning based predic-
tive model that addresses R.3 by predicting new visitor-venue links (see also [3]).
Section 7 describes the strategy we adopted to engages visitors directly through
social media (addressing R.4). Section 8 briefly compares our contribution with
related work. Finally, Section 9 discusses the results obtained and the lessons
learnt in this case study, concluding with future work.
6
Fuorisalone.it is the official Web portal of Milano Design Week.
2 Architecture
For this case study we designed a loosely-coupled architecture based on Stream-
ing Linked Data principles [6] and provenance ontology [20], so that different
components could communicate and scale independently from each other. Fig-
ure 1 illustrates the architecture. The gray looping arrow illustrates the overall
flow of information from Twitter, throughout the components of our solution and
back to Twitter. The flow starts from the Twitter Streaming API7 that continu-
ously sends to our Social Listener (SL) all the tweets posted from a given area (in
this case the Milano urban area), in order to detect visitor-venue links and the
most active users. It loops back to the Twitter REST API8 , from which the Vis-
itor Modeller (VM) fetches more tweets of visitors in order to build their profiles.
The data flow then goes through the Visitor-Venue Recommender (VVR), which
predicts visitor-venues links, and it heads back to the REST API of Twitter that
is used by the Visitor Engager (VE) to send recommendations to visitors.
Fig. 1. The architecture of the Continuous and Predictive Social Media Analytics sys-
tem used for the Smart City case study
More specifically, the SL component registers geo-bound queries in the Twit-
ter Streaming API. This starts pushing to the SL tweets posted within those
geographical areas. The SL analyzes the tweets, links those with positive senti-
ment to the venues of the CSE, identifies the most active users and stores the
results in the Blackboard, using the APIs exposed by the Blackboard Mediator
(BM). The Blackboard is the central component of our solution, which decou-
ples in space and time the intercommunication of all our components. The VM
periodically looks up visitors recently recorded by the SL in the blackboard. It
subsequently checks if such visitors have been previously observed and, if this is
7
https://dev.twitter.com/docs/api/streaming
8
https://dev.twitter.com/docs/api/1.1
not the case, it fetches all their tweets from the Twitter REST API. This compo-
nent then extracts the semantic entities (from DBpedia) contained in each tweet,
computes a profile of the user as weighted links between visitors and entities, and
adds this profile to the Blackboard. The profile is periodically updated with the
most recent tweets and added to the Blackboard. The VVR periodically fetches
the most recent visitor-venue links and visitor profiles from the Blackboard. Then
for each visitor, the VVR predicts the top 10 most probable visitor-venue links
not previously observed and adds them to the Blackboard. The VE periodically
looks up the most recently predicted links and use them as recommendations for
each visitor. If a recommendation concerns a visitor that has not received any
message yet, the VE invites through Twitter such a visitor to follow its Twitter
account. If the visitor is already a follower, the VE sends them a Direct Message
with the computed recommendations.
3 Blackboard and Blackboard Mediator
The heterogeneity of the components and of the data they produce requires
an integration middleware. Moreover, since the components are distributed, the
data needs to be remotely managed, in a scalable and robust way. Last but not
least, data elements are produced over time and, in this specific scenario, the
more recent they are, the more frequently they will be accessed. As a conse-
quence, after a long enough period of time they can be archived preventing the
data management system to require infinite memory.
These requirements can be addressed by a blackboard-based communica-
tion approach [17]: a flexible communication model that does not require any
prior restriction on who can place what information on the blackboard and
when they do so. RDF represents a suitable data model to be used with black-
boards since it poses no restriction on the type of information that can be ex-
changed. The Streaming Linked Data Format, proposed in a previous work [4],
can be used to deal with data that is produced by distributed components, and
changes frequently over time. This format has two main elements: the graphs
that are continuously published by the components (named instantaneous graphs
or, shortly, iGraphs), and a graph (called stream graph or, shortly, sGraph)
that lists the iGraphs and annotates them with who produces each iGraph
(using the PROV ontology [20] property prove:wasAttributedTo) and when
(prove:generatedAtTime).
Our Blackboard is built on Jena TDB (as RDF triple store), Jena Fuseki
(as SPARQL server for querying, updating and managing RDF graphs over
HTTP protocol) and a Java API (namely Blackboard Mediator) that hides the
complexity to invoke Fuseki and provides a single access point to the blackboard.
The Blackboard Mediator (BM) abstracts the communication between the
components and the blackboard by offering a Java API to the data producers
and consumers. The three main methods are: add new graph, retrieve the list
of graphs inserted in a given time period by a given agent (i.e. the component),
and fetch a graph. In particular, the BM exposes a service to add a new iGraph
Fig. 2. Results of the evaluation on the blackboard
g by encapsulating two steps: 1) the creation of a tracking sGraph for g in the
default graph, and 2) the insertion of g. The unique identifier of g consists of the
base URI, the agent and the arrival timestamp. The uniqueness of the agent-
timestamp pair is enforced by the API.
We ran two different evaluation experiments accessing the blackboard using
the BM component. The first experiment measured the time needed to randomly
access a single graph by URI, varying the number of iGraphs in the blackboard.
The second one measured the time for retrieving the list of iGraphs in three dif-
ferent time windows (3 minutes, 30 minutes and 180 minutes wide, respectively)
varying the number of iGraphs in the blackboard.
As illustrated in Figure 2, the time taken for randomly accessing a single
iGraph is independent from the number of iGraph stored in the blackboard
(Figure 2 A) and the time required to retrieve a list of iGraphs URI increases
linearly with the number of iGraph in the blackboard (the number of iGraph in
the system is presented using different symbols in the diagram) (Figure 2 B.1),
but is not sensitive to the timespan of the window requested (Figure 2 B.2). The
efficacy of the blackboard mediator as an integration middleware is empirically
demonstrated by this evaluation. The linear growth of the access time with the
amount of iGraph is not problematic because in our system iGraphs can be
deleted from the blackboard when they are older than a predefined threshold,
thus preventing an infinite growth.
4 Social Listener
The SL is the container of a pipeline of components devoted to collecting, trans-
lating, decorating and analysing a generic data stream from social sources (see
Figure 3). It addresses Requirements R.1 and R.2.
The Twitter Adapter represents the entry point of the pipeline, it establishes
a connection with the Twitter Streaming API to collect the raw tweets and
to transform them in a structured data format, using RDF as a common data
model. The structured representation of a single tweet include the hashtags, the
Fig. 3. The diagram of the Social Listener
URLs, the creator, etc. in a structured way that eases the operations in the
blocks downstream.
The next element in the pipeline is the CSE Entities Decorator [5]. This
component links tweets to venues of the CSE. It uses an aggregation of four
lexical similarity metrics that compares content and hashtags of each tweet to
the names of the venues and the titles of the events hosted in each venue (thus
also exploiting the semantic relationship between venues and events). As shown
in the table below, the manual assessment of the correctness of the discovered
links provides experimental evidence of the effectiveness of our CSE Entities
Decorator.
Type of Link Number of Links Correctness
Visitor-Venue 761 72%
Visitor-CSE 3723 94%
The decoration phase is concluded by the Sentiment Decorator [22] that adds
the sentiment information to the tweet. It relies on a dictionary-based classifica-
tion method, and applies the same processing for tweets written in English and in
Italian. More specifically, our method uses English and Italian sentiment dictio-
naries derived from SentiWordNet [13] and MultiWordNet [19] semantic lexicons,
where words are attributed with positive, negative and objective scores. These
scores are combined into a single sentiment score for each tweet, by considering
negation and modifier keywords, and also taking into account positive and nega-
tive emoticons. Within a specific domain (as the one of CSEs) simple sentiment
expression, even including irony and idioms can be captured. Still, complex sen-
timent expressions (rarely encountered in tweets mentioning venues) go beyond
pattern-based analysis and require more robust methods that are not optimised
for fast text processing because they need more than one-pass.
To evaluate the performance of our method, we randomly selected a third of
the tweets liked to a venue, and asked two human experts to label their opinion
polarities, obtaining 187 tweets with verified annotations. The annotated sub-
set contained approximately equal amounts of positive, negative and objective
(neutral) tweets, making the baseline classifier accuracy 0.37, when labeling all
tweets as objective. We compared our method using various dictionaries, and also
included the results obtained by SentiStrength [21] method for English, however
equipped with Italian dictionaries (provided by the authors). The results of our
experiments are reported in the table below, where we measured the overall clas-
sification accuracy, and the recall for individual classes, while utilizing polarity
thresholds that yield the best accuracy.
Approach Accuracy Recall Pos. Recall Neg. Recall Obj.
Baseline 0.37 0.00 0.00 1.00
IT SentiStrength 0.52 0.50 0.25 0.77
IT Only 0.58 0.34 0.51 0.87
IT + EN 0.66 0.55 0.63 0.78
IT + EN + Stem 0.67 0.59 0.73 0.68
Accordingly, the best performance is reached when our method utilizes both
English and Italian sentiment dictionaries together with stemming. The accu-
racy in this case reaches 0.67, being 30% above the baseline and 15% above Sen-
tiStrength. What is more important, our method reached 0.73 for the recall of
negative sentiments, reducing their misclassification as talksAboutPositively
relation, which is of the main interest for the venue recommender.
In the Analyze phase two different continuous queries are performed over
the decorated data: the first one extracts the visitor-venue links for the VVR
component and the second one extracts the visitor ids for the VM component.
Sentiment plays an important role in this phase, only the tweets with a positive
sentiment are passed to the VVR and VM components. In this way the rec-
ommendation and the visitor analysis is performed only on satisfied visitorsThe
Blackboard Translator performs the last step of the process writing the results
of the Social Listener on the blackboard using the Blackboard Mediator APIs.
5 Visitor Modeller
The VM performs monitoring and profiling of visitors based on their social me-
dia activities. The VM monitors selected visitors (the visitors that have been
detected by the SL) by crawling their social media posts, and subsequently anal-
yses them with different techniques to obtain a profile. It complements the SL
in addressing Requirements R.1 and R.2.
The VM is composed by the following modules (see also Figure 4): a Front-end
that reads visitor ids from the blackboard; a Scheduler that schedules the analysis
of the ids; a Crawler that crawls visitors’ tweets; an Analyzer that extracts entities
from the tweets; and a Profiler that generates a profile for each visitor.
To guarantee high scalability, all components (except for the Profiler) have
been designed to be replicable, and connected by a load balancing mechanism im-
plemented by a message queuing sub-system9 . Once a visitor id has been read by
the Front-end and scheduled for analysis by the Scheduler, the Crawler collects all
visitor’s tweets, using Twitter’s public REST APIs. The Analyser then extracts
the entities contained in the tweets. For example, from the tweet “Temperley
9
We use ActiveMQ http://activemq.apache.org/
Fig. 4. The architecture of the Visitor Modeller. White modules represent its com-
ponents, grey modules indicate other components described in the paper, while blue
modules indicate existing services and software.
London at London Fashion Week Spring 2014 http://t.co/mXFdvmCWXR”, the
VM detects that London Fashion Week refers to the entity http://dbpedia.
org/resource/London_Fashion_Week.
The Analyser can use different Named Entity (NE) extractors. For this case
study we used the probabilistic version of DBpedia-Spotlight10 . This tool ana-
lyses the text by “spotting” possible candidates for entities, and disambiguating
each candidate. NE tools usually provide also some values related to the likeli-
hood that the result is correct. In Spotlight’s case, this is not really a confidence
value, but more an indication of how well the entity was disambiguated from
alternative entities in DBpedia; the candidate could still be wrongly spotted (e.
g. not be an entity). In particular, Spotlight provides two values for each found
entities: assuming that there is an entity in the text, how likely this is the entity
ranked first by Spotlight, normalized with respect to all possible entities (the
similarityScore), and how likely the second ranked entity is with respect to the
first ranked one (the percentageOfSecondRank ).
The Analyser filters extracted entities below a certain threshold. To obtain
a single value from Spotlight, we adopted the following score for each entity:
(1 − 0.5 ∗ percentageof secondrank) ∗ similarityscore, the rationale being that
if an entity is very likely (similarityscore=1) but a second one is equally likely,
both score 0.5. Since we observed that almost 80% of the entities had a score
≥ 0.9, we filtered out entities with lower score to have relatively high quality
without losing too much in recall (1.090.237 entities were left).
To evaluate the quality of the extraction, we estimated the proportion of
entities correctly extracted by manually verifying their presence in the tweets.
In total we extracted 1.090.237 entities from 1.879.187 tweets. We sampled the
entities extracted to estimate the proportion p̂ of correct entities. Considering
that such a proportion follows a binomial distribution that for large population
can be approximated by a normal distribution, we used Wald’s method to es-
tablish the sample size given the confidence interval conf and the error range
err, such as that for the real estimate p we have that p ∈ (p̂ − err, p̂ + err) in
10
https://github.com/dbpedia-spotlight/dbpedia-spotlight/wiki
conf% of the times:
qnorm(conf )2 p̂(1 − p̂)
n= (1)
err2
where qnorm is the quantile function of the normal distribution. We chose
err=0.025 (i. e. 2.5%) and conf=95%. From an initial exploratory evaluation with
sample size of 300 entities we obtained an initial estimate for p̂ to be around
0.74, which gives a sample size of 833. We therefore sampled (with replacement)
the data set and carried out the evaluation presented in the table below.
Entities Samples Correct Precision Range Sup Range Inf Confidence
1090237 833 615 73.83% 71.33% 76.33% 95.00%
To be noted that this evaluation only measures the precision of the extraction,
and not the recall. Evaluating recall on our data set is much harder since it
requires the evaluator to define the set of the entities that are contained in a
tweet, while verifying that an entity is contained in a tweet is much easier.
Finally, the Profiler creates a visitor profile. For each visitor the Profiler builds
both an historical and an event profile. Historical profiles are based on tweets
posted before the monitored event, while event profiles are based on tweets
during the event. A visitor profile is defined as a set of pairs (e, w(u, e)), where e
is an entity and w(u, e) is the weight of e in u’s profile. Initially our strategy has
been to select the most common entities (we set the limit at max 10 entities)
for each visitor and weighting them based on the number of occurrences. We are
planning to evaluate alternative strategies, such as filtering out entities that are
not discriminative (e. g. because they are too common, such as Milano), and use
the class of entities to have more overlapping among visitor profiles.
6 Visitor-Venue Recommender
This section addresses the requirement R.3: predict the possible changes in the
graph (see Section 1). We briefly describe the component Visitor-Venue Recom-
mender (VVR) and evaluate it on the MDW data.
The VVR predicts visitor-venue links that are very likely to occur in the
future. A statistical machine learning approach named SUNS [15] is applied in
the VVR. SUNS can be viewed as a regularized matrix factorization approach11 .
This approach is robust with respect to sparsity of data and can incrementally
improve predictions when more data become available. The regularization can
reduce the model’s sensitivity to its parameters. The model of the VVR is trained
using visitors’ profiles generated by the VM and visitor-venue links detected
by the SL. It is then applied to recommending venues that will be potentially
visited by visitors in the upcoming days. In the following updates, when new
visitor-venue links or new or updated visitors’ profiles are available, the model is
retrained taking new information into account. This capability enables the VVR
to cope with social media stream dynamics.
11
In recent years matrix factorization based approaches have been using in many
recommendation systems, e.g. Netflix Prize.
The evaluation of the VVR in this paper is focused on the capability of
capturing changes of social media stream over time. During the MDW the VVR
processed 842 unique links between 512 visitors and 198 venues. This data is
summarized in the table below. It is important to clarify what the training data
is and what the test data is. Considering the update on April 8th at 4pm, the
VVR fetched from the Blackboard 105 new unique links and 65 new visitors were
observed. Until that time 100 visitors had 154 links associated with venues they
talked about.12 This was the training data exploited at this update time. In
subsequent updates until the end of MDW, 22 visitors had 42 more links to
venues.
Update Time New Unique Links New Visitors Links to Predict User to Predict
2014-04-08T04:00:00 49 35 10 6
2014-04-08T16:00:00 105 65 42 22
2014-04-09T04:00:00 49 30 54 27
2014-04-09T16:00:00 62 41 53 31
2014-04-10T04:00:00 62 33 46 27
2014-04-10T16:00:00 158 91 46 31
2014-04-11T04:00:00 49 24 33 23
2014-04-11T16:00:00 81 55 27 19
2014-04-12T04:00:00 23 17 26 19
2014-04-12T16:00:00 80 51 16 11
2014-04-13T04:00:00 50 31 16 9
2014-04-13T16:00:00 74 39 - -
sum 842 512 - -
In order to evaluate the quality of the predictions in the VVR, we compared
SUNS with random guessing (Random), Pearson correlation coefficient (Pearson)
and most talked venues (MostTalked). Random assigns randomly a likelihood to
every venue not talked yet by a visitor; Pearson makes recommendations based on
the visitors’ similarity; and MostTalked encodes the popularity of venues in the
community observed by counting how frequent the venues were mentioned and
recommending the venues ordered by the frequency to all visitors. In addition, we
combined SUNS with MostTalked (SUNS+MostTalked), which intends to model
both venue popularity and visitor preferences. The evaluation measures used
were:
precision@topN = T rueP ositive/N and
recall@topN = T rueP ositive/(T rueP ositive + F alseN egative).
Figures 5 (a) and (b) show the recall@5 and @10 recommendations in 11
updates from April 8th at 4am to April 13th at 4am, 2014. The random rank-
ing failed in most cases to recommend correct venues. Pearson performed better
than Random and its recall value increased slowly over time. The performance of
SUNS kept increasing too, especially in the last update. Surprisingly, MostTalked
outperformed all other approaches and it was clearly overtaken by SUNS only
in a few updates, when considering the top 5 recommendations. The combined
approach SUNS+MostTalked performed in most updates better than both ap-
proaches. Figures 5 (c) and (d) show the precision@5 and @10 recommenda-
tions. In contrast to the recall, the precision decreased against the top number
12
Note that a visitor can talk about the same venue several times and that we report
here the distinct count.
(a) (b)
(c) (d)
Fig. 5. Precision and recall values at top 5 (a,c) and top 10 (b,d) at each update time
of recommendations and it was lower than the recall. That is because the av-
erage number of the ground truth links per visitor is not greater than 2, i.e.
T rueP ositive + F alseN egative <= 2 (see the right two columns in the table
above), whereas precision is calculated by dividing the top number 5 resp. 10.
Our evaluation uncovered several interesting findings. First, the VVR reaches,
on average for all visitors, recall over 20% at top 5 and more than 30% at top
10 (applying SUNS+MostTalked). If we consider the fact that many events were
held for several days at the same venue so that the venues which had been talked
by visitors in the past could be recommended again and again, the resulting VVR
models performed fairly well. Second, in many updates, the more information
is available, the higher quality of recommendations are provided. However, this
increase is not observed at all updates. That is because the difficulty degree of
making recommendation does not only depend on the available data, but also
on many other aspects in a particular update, such as the sparsity of the links
regarding the number of visitors and the number of venues and the community
structure (e.g. active users, user clusters). Last, but not the least, the popularity
of venues dominates the performance of the VVR. The visitor similarity, explored
by both SUNS and Pearson, did not contribute as much as it usually does in social
networks.
7 Visitor Engager
The purpose of the VE is to automatically contact relevant Twitter users and
provide them with the possibility to view and rate their personalized recom-
mendations (addressing Requirement R.4). The VE is a Java enterprise ap-
plication build on top of Errai framework and is publicly available at https:
//github.com/WISDelft/AttendeeEngager. It consists of four main compo-
nents: 1) The Front-end consisting of an informative landing page of the VE and
a personal dashboard, 2) The TwitterManager that handles sending of Twitter
messages and monitoring of followers of the designated account, 3) The Recom-
mendationManager which uses the Blackboard Mediator to retrieve recommenda-
tions calculated by the VVR, and 4) The QueueManager which reliably handles
all communication between the components using the same underlying queue
technology as for the Visitor Modeller.
Fig. 6. Engagement process of Twitter users
The engagement process (see Figure 6) is started by receiving the Twitter
user IDs of new users, as detected by the Social Listener. Using the @fuorisa-
lonetips Twitter account, which was officially supported by the organization, the
VE sent each user only a welcome and (if necessary) a reminder message via a
Tweet mentioning the user, a so-called mention. The welcome mention looked
like: @joosterman Welcome to #fuorisalone Milano Design Week <. . . >. If the
user started following the account, they would be considered opted-in and re-
ceived the link to their personal dashboard. To minimize the amount of unso-
licited tweets, we chose to send recommendations only to users who had actively
opted in. At any time a user could opt-out via the personal dashboard or stop fol-
lowing the designated account to become opted-out, after which they would not
receive any further messages. Opted-in users received direct messages (a private
Fig. 7. Personal dashboard showing the recommended venues
message) containing recommendations and the information that their dashboard
was updated.
Using their Twitter account or dashboard link users could visit their personal
dashboard (see Figure 7). The dashboard showed recommended venues grouped
by day, and each venue could be expanded to see events taking place there.
Thumb-up and thumb-down buttons were shown next to each venue. To assess
the quality of the recommendations, in terms of users perception of usefulness
and interest in the item recommended, we defined two ratings: a user expanding
a venue (implicit rating) and clicking on a thumb button (explicit rating).
There are two Twitter policies that apply to the VE: firstly, the harassment
policy, that prevents an account to send large numbers of unsolicited mentions,
and secondly the spam policy, that prevents an account to send many messages
of duplicate content. Trying to comply to these policies we implemented a timer
for sending messages such that messages were sent with an interval of 5 minutes.
We also created 5 different versions of each message.
However, despite our efforts, the account was temporary suspended for vio-
lating the harassment policy. After the suspension we were able to again send
messages but at a much slower pace. The system managed to send welcome
messages to 179 users of which only 2 opted in and only 5 opted out resulting
in a response rate of 3.9%. These results are in line with previous empirical
studies [16] reporting a 4% response rate. The system did not send reminder
messages because, due to the limitations imposed by Twitter, we gave higher
priority to sending messages to new users. Two users visited the dashboard of
which one used it to opt-out. Neither user used the dashboard to rate the rec-
ommended venues. As a result, it was clear that visitors did not appreciate to
be contacted on Twitter, even when using an official Twitter account supported
by the organization of the event (Fuorisalone). Therefore, in the future we need
to devise alternative ways for visitor engagement.
8 Related Work
Several efforts in literature are related to the solution we adopted for this case
study, although there are clear differences with our approach.
City venues and their categories have been used in order to characterise a
city’s districts, also with the goal of recommending particular areas to visitors.
[18] uses Foursquare checkins and Foursquare venue categories to classify differ-
ent areas of the city, and to profile users based on the categories of the venues
that they visit. A similar work is [11], which clusters together areas in a city
based on similar users checking in the venues of that area, based on the assump-
tion that both people and places define the character of an area (what they call
Livehoods). Both the venue and the visitor profile are based on Foursquare venue
categories. A step further is represented by [12], where the authors define venues
also based on the profile of the visitors visiting those venues, using Facebook data
to profile visitors. They claim that using semantics extracted both from places
and from the online profiles of people who frequent those places improves city
areas and venues classification. Differently from our solution, these approaches
rely on the availability of data about the categories of venues. Moreover, venues
are considered as having a static “character”, i.e. a fixed category. In our case,
during a City Scale Event venues change their character and this data is not
available from Location Based Social Networks such as Facebook or Foursquare.
Other efforts have tried to relate tweets to the geographical location from
where they were posted. [14] predicts location of a tweet, using a generative
model based on location-dependent language models. Similarly, also [9] propose
a probabilistic framework for estimating a Twitter user’s city-level location based
on the content of the user’s tweets. Such approaches do not achieve the precision
needed in our approach, considering that they are able to place users within 100
miles of their actual location. Also using the geolocation information of social
streams, but for a different purpose, [10] analyses check-ins as a way to study
user mobilities with a large scale perspective (millions of check-ins).
Related to the problem of linking a tweet to a venue, [8] uses entity extraction
from tweets in order to enrich the static description of Point of Interests with
dynamic information contained in the tweets. Again, this approach operates at
city scale, while we operate at venue scale. Moreover, our problem is not to
characterise an event, but to know who exactly is attending it.
A similar approach to ours, [1] also uses social streams and other user-
generated sources such as GPS information to understand the urban context
and generate recommendations, using a semantic approach based on Semantic
Web technologies (Pellet, OWL and SWRL). Different from our work, their user
modeling is not based on user interests but on user preferences for mobility (such
as avoid crowded place to go to work), since their recommendations are related to
route planning. Therefore, their user models have a different content. Similarly,
in the field of Smart Cities and mobility, the CityPulse project13 aims to create
a distributed framework for semantic discovery, processing and interpretation of
13
http://www.ict-citypulse.eu/
large-scale real-time Internet of Things and relevant social data streams, with the
goal of knowledge extraction in a city environment [7]. In particular,“Extracting
City Traffic Events from Social Stream’ deals with extracting traffic events from
twitter streams [2].
9 Conclusions and Future Work
The growing amount of digital footprints that visitors of city-scale events leave
on social media enables to build a graph of visitors attending events hosted in
venues. This graph is continuously reshaping and the ability to predict in real
time its evolution can foster innovative social media analytics services. In our
previous work [4,3], we showed that our deductive and inductive stream reason-
ing techniques, once combined with visitor-modeling functionalities, can produce
high-quality predictions of links in such a graph even when information about
visitors’ preferences for venues and events is sparse. In this paper, we report on
our first attempt to experimentally offer a real-world service for the visitors of
Milano Design Week 2014. The case study confirms the ability of our system to
semantically analyze and link visitors’ social network activities to venues of a
city-scale event. The case study also confirms the ability to build representative
visitor profiles. The task of predicting links between visitors and venues is as hard
as expected in the lab. The predictions the system produces are in line with our
expectation (i.e. they are better than any base line methods in the state of the
art). Also the integration middleware based on a Streaming Linked Data imple-
mentation of the blackboard paradigm showed satisfactory performances. The
most critical task was engaging the visitors. We monitored visitors in Twitter
and we also tried to engage them by using Twitter. Unfortunately, the task was
much more challenging than expected. Even if we were granted the permission
to use a Twitter account related to MDW and to host the application under a
sub-domain of the official website of MDW, only few users opted to follow us
and, thus, received our recommendations. Moreover, Twitter anti-spam policies
resulted more powerful than our countermeasures.
In our future work, we intend to improve the correctness of the method em-
ployed in semantically analysing and linking social media to venues and topics.
We will investigate the effect of additional meta data (e.g. organizers of events)
on the quality of recommendations. An important challenge we intend to take
on in the future is to predict the appearance or disappearance of nodes from
the people-venues-events graph. Moreover, we intend to deliver our recommen-
dations through an official mobile application of a city-scale event so that we are
perceived as a trustable source of recommendations.
References
1. Alvarez-Napagao, S., Tejeda-Gómez, A., Oliva, L., Garcia-Gasulla, D., Codina, V.,
Vázquez-Salceda, J.: Urban context detection and context-aware recommendation
via networks of humans as sensors. In: CARE (2014)
2. Anantharam, P.: Extracting city traffic events from social streams (2014), https:
//osf.io/b4q2t/wiki/home
3. Balduini, M., Bozzon, A., Della Valle, E., Huang, Y., Houben, G.J.: Recommending
venues using continuous predictive social media analytics. IEEE Internet Comput-
ing 18(5) (2014)
4. Balduini, M., Della Valle, E., Dell’Aglio, D., Tsytsarau, M., Palpanas, T., Con-
falonieri, C.: Social listening of city scale events using the streaming linked data
framework. In: ISWC (2). pp. 1–16 (2013)
5. Balduini, M., Della Valle, E., Nasi, G., Calegari, G.R.: A quest for lightweight
methods to dynamically linking micro-posts to entities of a city-scale event. In:
Proc. of Workshop on Context, Interpretation and Meaning (2014)
6. Barbieri, D.F., Della Valle, E.: A proposal for publishing data streams as linked
data - a position paper. In: LDOW (2010)
7. Bischof, S., Karapantelakis, A., Sheth, A., Mileo, A., Barnaghi, P.: Semantic mod-
elling of smart city data. In: W3C Workshop on the Web of Things Enablers and
services for an open Web of Devices. pp. 1–5. Berlin, Germany (2014)
8. Cano, A.E., Varga, A., Ciravegna, F.: Volatile classification of point of interests
based on social activity streams. In: Proc. Of SDOW (2011)
9. Cheng, Z., Caverlee, J., Lee, K.: You are where you tweet : A content-based ap-
proach to geo-locating twitter users. In: ICKM. pp. 759–768. ACM (2010)
10. Cheng, Z., Caverlee, J., Lee, K., Sui, D.Z.: Exploring millions of footprints in
location sharing services. In: Proc of the 5th Int Conference on Weblogs and Social
Media. pp. 81–88. The AAAI Press (2011)
11. Cranshaw, J., Hong, J.I., Sadeh, N.: The livehoods project : Utilizing social media
to understand the dynamics of a city. In: The 6th Int. AAAI Conf. on Weblogs
and Social Media. AAAI Press, Dublin, Ireland (2012)
12. Del Bimbo, A., Ferracani, A., Pezzatini, D., D’Amato, F., Sereni, M.: Livecities :
Revealing the pulse of cities by location- based social networks venues and users
analysis. In: WWW. pp. 163—-166. Seoul, Korea (2014)
13. Esuli, A., Sebastiani, F.: Sentiwordnet: A publicly available lexical resource for
opinion mining. In: LREC ’06 (2006)
14. Hong, L., Ahmed, A., Gurumurthy, S., Smola, A.J., Tsioutsiouliklis, K.: Discover-
ing geographical topics in the twitter stream. In: WWW. pp. 769—-778 (2012)
15. Huang, Y., Tresp, V., Bundschus, M., Rettinger, A., Kriegel, H.P.: Multivariate
prediction for learning on the semantic web. In: ILP. pp. 92–104 (2010)
16. Mahmud, J., Zhou, M.X., Megiddo, N., Nichols, J., Drews, C.: Optimizing the
selection of strangers to answer questions in social media. CoRR abs/1404.2013
(2014)
17. Nii, H.P.: Blackboard systems, part one: The blackboard model of problem solving
and the evolution of blackboard architectures. AI Magazine 7(2), 38–53 (1986)
18. Noulas, A., Scellato, S., Mascolo, C., Pontil, M.: Exploiting semantic annotations
for clustering geographic areas and users in location-based social networks. In: The
Social Mobile Web (2011)
19. Pianta, E., Bentivogli, L., Girardi, C.: Multiwordnet: developing an aligned multi-
lingual database. In: Proc. of the 1st Int. Conf. on Global WordNet (2002)
20. T. Lebo et al.: Prov-o: The prov ontology. W3C Recommendation (2013)
21. Thelwall, M., Buckley, K., Paltoglou, G., Cai, D., Kappas, A.: Sentiment strength
detection in short informal text. J. Am. Soc. Inf. Sci. Technol. 61(12), 2544–2558
(Dec 2010)
22. Tsytsarau, M., Palpanas, T., Denecke, K.: Scalable detection of sentiment-based
contradictions. In: DiversiWeb Workshop (2011)