=Paper=
{{Paper
|id=Vol-1748/paper-01
|storemode=property
|title=A Tool to Analyze the Reading Behavior of the Users in a Mobile Digital Publishing
Platform
|pdfUrl=https://ceur-ws.org/Vol-1748/paper-01.pdf
|volume=Vol-1748
|dblpUrl=https://dblp.org/rec/conf/kdweb/BorattoCCDM16
}}
==A Tool to Analyze the Reading Behavior of the Users in a Mobile Digital Publishing
Platform==
https://ceur-ws.org/Vol-1748/paper-01.pdf
A Tool to Analyze the Reading Behavior of the
Users in a Mobile Digital Publishing Platform?
Ludovico Boratto1 , Mattia Cadeddu1 , Salvatore Carta1 , Gianni Deplano2 , and
Fabio Mereu2
1
Dipartimento di Matematica e Informatica, Università di Cagliari, Italy
ludovico.boratto@acm.org, mattia.cadeddu@gmail.com, salvatore@unica.it
2
Xorovo srl — Applix srl, Italy
{gianni.deplano, fabio.mereu}@applixgroup.com
Abstract. In their daily activities, users interact multiple times with
mobile applications. This generates huge amounts of data related to these
interactions that, when filtered and analyzed, would give insights on the
behavior of the users while using an application. In this paper, we con-
sider a real-world mobile digital publishing platform, named Viewerplus,
which enables a digital, augmented fruition of content from traditional
magazines. The objective is to develop a tool that allows the human edi-
tors to analyze the reading behavior of the users, by providing analytics
that show how the users read magazine issues (i.e., how they browse
an issue and move inside the app, which portions of an issue are most
frequently read and which frequency, and which topics are of interest
for the users during a reading session). The tool has been developed by
employing a dataset extracted from the reading sessions of a magazine
of an important international publisher. In this work we also employ the
dataset to present a preliminary study of the user reading behavior.
Keywords: Reading Behavior, Mobile Application, Data Analysis.
1 Introduction
In order to access information, we interact with different types of devices, from
personal computers, to mobile phones, to tablets. These interactions take var-
ious forms and the usage of mobile applications is certainly the most diffused
nowadays. The vast amounts of data implicitly generated by the users during the
interactions might lead to useful information on the behavior of the users while
using the applications. In [1], the authors highlight that user behavior on mobile
applications is analyzed from three main perspectives, i.e., (i) data usage, (ii)
mobility patterns, and (iii) application usage. In this paper we will focus on the
first and third types of behavior, by analyzing both the usage and the content
?
This work is partially funded by Regione Sardegna under project NOMAD (Next
generation Open Mobile Apps Development), through PIA - Pacchetti Integrati di
Agevolazione “Industria Artigianato e Servizi” (annualità 2013), and by MIUR PRIN
2010-11 under project “Security Horizons”.
browsed by the users of a real-world mobile application, named Viewerplus3 ,
which serves as a magazine reader and provides the users with a digital and
augmented fruition of content. More specifically, we will analyze how the users
browse the issues of a magazine while reading it, and which topics characterize
their interest.
The analysis of the reading behavior of the users is an aspect that is gaining
more and more interest nowadays. In their survey, Okoli et al. [2] highlighted
that less than 1% of the studies focused on the readers of Wikipedia. However,
in [3] it was highlighted that reading can be considered as a form of participation,
and in their recent study Lehmann et al. [4] stated that the reading activity of
the users can provide insights to the human editors. Indeed, by understanding
the reading behavior of the users, human editors can tailor the structure of a
product such as a magazine, and improve aspects like the content organization
or the placing of the ads.
In the recently mentioned study, the authors focus on the user preferences
and reading behavior on Wikipedia [4]. According our knowledge, no study on the
reading behavior in mobile content fruition applications has been performed, and
the two application domains present substantial differences. When analyzing the
reading behavior in a mobile content fruition application, it should be noted that
the browsing of a magazine in form of a pdf file inside an application presents
many differences with respect to web browsing. Indeed, the type of browsing
we are considering is usually sequential (users usually move from one page to
the next), while web pages usually contain links and this is not the case of a
magazine issue, which reports the printed version in a digital file. Moreover, the
web pages usually form a hierarchy, and this is not the case in our scenario (users
employ the mobile application to read pdf files, which is structured as a sequence
of pages).
In order to allow the human editors of a magazine to analyze the reading
behavior of the users, in this paper we present Reader Behavior, a Java tool that
analyzes the interactions of the users with the Viewerplus mobile application.
The tool presents analytics on how the users browsed a specific issue, which
portions have been read more and with which frequency, and which topics are
more interesting for the users.
The scientific contributions of this paper are the following:
– we study for the first time in the literature the reading behavior of the users
in mobile applications;
– we present a tool that gives the human editors the possibility to dynamically
explore the reading of different magazine issues, by selecting them and seeing
how users read their content;
– we perform a preliminary study of the users’ reading behavior, based on a
real-world dataset extracted from the reading sessions of a magazine pub-
lished by a famous international publisher.
The rest of the paper is organized as follows: we first present related work
(Section 2), followed by a description of the Viewerplus mobile application (Sec-
3
http://www.viewerplus.com/
tion 3); next, we present the tool developed to analyze the reading behavior
of the users along with a preliminary analysis of the results obtained consider-
ing the reading sessions of a magazine (Section 4); the paper ends with some
concluding remarks and by presenting future work (Section 5).
2 Related Work
The reading behavior of the users in Web environments has been studied from
several perspectives. In [4], the readers of Wikipedia are analyzed and the authors
found out that the most read article are not the most edited ones, and they
identified four patterns that describe how the articles are read. Castillo et al. [5]
analyzed the life cycle of online news stories and discovered that the number of
visits of a news article and the activity on Twitter and Facebook decay after
a short time; moreover, the reactions on the social networks can be employed
to predict the future visits an article will receive. Zhang and Ma [6] analyzed
the correlations between users’ educational level and their reading behavior,
and found out that higher educated people pay for academic papers, while the
other users prefer online literature. In [7, 8], systems to analyze the web reading
behavior of the users by employing eye tracking systems were presented.
Regarding the analysis of the user behavior in mobile applications, some
studies analyze the motivation behind their use. In [9], Church and Oliveira
compare the use of Whatsapp with respect to traditional SMS, and the results
show that WhatsApp is usually employed because of the reduced cost, the social
interactions it can offer, and its immediacy, while SMS is considered more reli-
able and privacy preserving. In [10, 11] the factors that lead to user engagement
are studied, and those that emerged as the most important are the perceived
enjoyment and usefulness of an application.
The patterns in the usage of mobile applications were also studied. Xu et
al. [12] found out that 20% of the applications are local (e.g., radio stations),
that some applications co-occur in a smartphone (i.e., they can be treated as a
bundle), and that diurnal patterns of different genres of applications can be sig-
nificantly different. In [13], Tossell et al. identified behavioral patterns associated
with browsing, native internet applications’ use, and physical locations.
The search behavior of the users has been investigated in [14], which discov-
ered that mobile information access is characterized in 94% of the sessions by
browsing content, that 8% of the users are involved in search activities, and that
these users have a much richer online behavior than the browsing-only counter-
part. In [15] it was highlighted that 70% of mobile information access happens
in a stationary place (e.g., at home or at work).
The geospatial dynamics of mobile application usage were mostly analyzed
with clustering algorithms. In [16], the authors clustered cell locations and per-
formed an analysis of the cells belonging to different clusters, finding that the
byte, packet, flow, and user distributions across different geographical regions
are significantly different. Keralapura et al. [17] performed a co-clustering of
users and websites, discovering that the browsing behavior of most users can be
classified as either homogeneous in terms of interests and characterized by short
sessions, or heterogeneous with very long sessions.
As this analysis showed, no study in the literature is devoted at analyzing
the reading behavior of the users in mobile applications, and the problem we are
studying is novel.
3 Viewerplus: a Mobile Digital Publishing Platform
In this section we set out the mobile application employed in our study and
developed by Applix, called Viewerplus4 , by providing an overview of its core
features, specifically designed to address the needs of users during their reading
activities. For the purpose of this work, it is important to note that Viewerplus
is not a prototype, but a full-featured application used by thousands people
everyday, freely available for Android- and iOS-powered devices, and available in
the main digital distribution platforms, such as Apple’s App Store, Google Play,
Amazon Marketplace, and Samsung Galaxy Apps. Vierwerplus is the leading
application for the visualization and digital fruition of magazine periodicals,
and it is employed by the main Italian editorial groups.
The application allows users to browse magazine issues in a mobile device,
by interacting with a pdf file through several types of interactions and features
(e.g., zoom, underline, page saving, bookmark). The interaction is made possible
both offline (users can read a magazine issue without being connected to the
Internet) and online, thanks to push notifications and the possibility to access
to multimedia content. Indeed, the application supports integrations to include
photos, audios, videos, links to external pages, and ads. Moreover, users can
share excerpts of what they are viewing or reading on the main social media
platforms. Thanks to these online features, Viewerplus is also largely employed
by companies who want to provide their customers with their latest catalogue.
The monitoring of the users activity inside the application is made possible
by a suite developed by Xorovo, named APP-BI5 , which tracks the interactions
of the users with the application, and extracts analytics that can be employed
for different purposes, such as business intelligence.
With this work, we aim to extend the functionalities offered by APP-BI,
by introducing the concept of reading session and by analyzing in detail the
behavior of the users while reading magazine issues (e.g., which portions are
read and with which frequency, which pages are read together based on the
reading sessions). In conclusion, we would also like to point out that we will
focus on the functionalities offered by Viewerplus as a reader. This means that
we will consider a scenario where a user can browse a pdf with a magazine
issue and no link, multimedia, or online content is available. Indeed, a user can
move through the pages of a pdf by reading a magazine and by exploring its
content with classic gestures that allow her to interact with the device and the
application (i.e., scroll, tap, zoom, swipe, etc.).
4
http://www.viewerplus.com/
5
http://www.app-bi.com/
4 Reading Behavior Analysis
Here, we will present Reader Behavior, a Java tool developed to analyze and
automatically describe how users behave while reading magazine issues. This
section starts with a description of the collected dataset (Section 4.1), the data
processing performed to extract the reading sessions employed in our analysis
(Section 4.2), ending with a presentation of the tool developed to support the
human editors at analyzing the reading behavior and with a preliminary presen-
tation of our findings (Section 4.3).
4.1 Data Collection
In order to build the tool and analyze the user behavior, we analyzed the inter-
actions of the users with the application, considering a magazine of a widely-
renowned publisher. APP-BI keeps track of different types of events, but not all
of them are related to the reading behavior of the users (e.g., the purchase of an
issue).
For this study, we collected the data related to the visualization of a page.
Such events are tracked if a user visits a page for at least two seconds (this value
was studied internally by the APP-BI development team and set as the optimal
one). Each record contains the following attributes: , where deviceID is employed to monitor the
behavior of a user that employs the same device, issueID identifies the maga-
zine issue, time indicates the timestamp in which the event started, duration is
the number of seconds that the user spent on the page, pageID is an absolute
identifier of the page number, and pageN umber indicates the number of the
page indicated in the pdf of the magazine issue. Note that having an anony-
mous deviceID, in order to monitor the activities performed inside a device,
helps us analyzing the behavior by respecting the privacy of the users: indeed,
the identity of a user is not tracked by APP-BI and no personal information is
disclosed.
We monitored the interactions of the users with the application between
01/04/2014 and 04/06/2015, recording 10994 events of this type, which involve
110 different magazine issues.
We would like to point out that no metadata was made available, so we had no
table of contents that linked the articles to the pages, and no separation between
the title of an article and its text. All this information had to be automatically
extracted by us in order to analyze the user behavior, and we will describe this
process in the following subsection.
4.2 Data Preparation and Processing
In order to have a more structured data representation and to link the collected
events to the content of a magazine issue, we performed three steps to divide
the events into reading sessions, get the text of each page in a magazine issue,
and automatically extract the topics of the magazine.
Reading sessions definition In [18], the authors define a browsing session
as all the activities that occur in less than 30 minutes between an activity and
the following. This definition was also employed in [4], to define the reading
sessions of the users in Wikipedia. In order to characterize the reading behavior
of the users, we also adopted this definition, and considered as reading session
all the events that involve the same user and for which less than 30 minutes
passed between the end of an event (time + duration) and the beginning of the
following.
Text extraction Given the pdf file of a magazine issue, we used Apache’s
PDFBox6 to parse it and get as output the text.
Page topics extraction Given the text of each issue, we automatically ex-
tracted the topics that characterize the magazine. This was made thanks to
Latent Dirichlet Allocation (LDA), which is usually employed for this purpose
(i.e., extract the topics from a set of documents), by employing a Java imple-
mentation of the algorithm made available in the MALLET framework [19].
The framework received as input a text corpus with the content of all the
110 issues in the dataset and the number of topics to extract, and produced a
set of topics. After a set of experiments (not reported to facilitate the reading
of the paper), we extracted seven topics. This choice was made since having a
lower number of topics led to having keywords that belong to different domains
in the same topic, while having a number of topics higher than seven meant that
keywords that belong to the same domain were split into two topics.
Out of the seven detected topics, two were characterized by keywords that
occur in all the issues (i.e., the details of the publisher, and common keywords
that appear in an issue such as “number”, “price”, and “data”). These two topics
were removed, and we manually assigned the following labels to the remaining
five, according to the keywords extracted through LDA:
1. family life;
2. tv;
3. lifestyle;
4. health and self-care;
5. cinema.
The choice to extract the topics for the whole magazine was made since a
magazine’s articles are usually about the same topics (a magazine is usually
directed toward a specific user target), to facilitate the manual labelling of the
topics given the keywords extracted by LDA, and to be able to compare the
reading behavior on different issues (e.g., the interest generated by the “cinema”
articles published in an issue with respect to those published in another).
Given these five topics, we processed each page of each issue through MAL-
LET, and extracted a vector whose elements indicate the relevance of each topic
for the page.
6
https://pdfbox.apache.org/
4.3 A Tool to Analyze the Reading Behavior of the Users
Reader Behavior offers three main types of features to human editors:
1. Co-readings graph. By selecting a magazine issue, the tool shows a graph
that contains a node for each page, and an undirected weighted edge that
connects two pages that have been read one after the other. A human editor
has the possibility to interact with the graph and visualize only the edges
whose weight is above a certain threshold, in order to isolate the most read
subgraphs.
2. Visualization of the interest toward the pages. Given a magazine issue,
the tool shows each page as a box, whose color is based on the frequency
with which the page was read. This allows the human editors to analyze how
the readings are distributed and which pages caused more interest on the
users.
3. Clustering of the pages that have been read together. For each maga-
zine issue, we perform a clustering to put together the pages that have been
read in the same sessions. Thanks to this feature, the human editors are
allowed to re-organize the content of future issue, by having an automatic
description of what users have read together.
In the following, we will describe the details of each feature.
Co-readings graph The first feature offers the possibility to human editors to
select a magazine issue and visualize a graph that contains a node for each page
in the issue, and an undirected weighted edge that connects two pages that have
been read one after the other in the same reading session of a user; the weight
represents the number of times the two pages have been read one after the other.
A screenshot of the feature is shown in Fig. 1.
As it can be seen, a human editor is provided with the possibility to interact
with the graph, in order to see only the edges whose weight is above a certain
threshold (in the figure, the threshold is 75). This type of dynamic interaction
with the graph offers the possibility to analyze in real time how the graph is split
into subgraphs and which components are strongly connected (each subgraph
represents a subset of pages for which users have shown the same interest).
We are currently working on an automatic description of each subgraph in
terms of the topics that characterize its pages. A preliminary analysis shows
that pages that have been read together and with a similar frequency are also
characterized by the same topics. This is visually indicated by the colors in the
nodes, which are homogeneous in each subgraph (i.e, users tend to read together
pages related to the same topics).
Visualization of the interest toward the pages With this feature, the
tool visualizes all the pages of a magazine issue. For each page we consider the
number of times it has been read and split these values based on the quartiles.
Fig. 1. Co-readings graph feature, showing only the edges whose weight is above 75.
This allows us to obtain four data quarters, which indicate how the interest
toward the pages of that issue is distributed.
The tool visualizes the issue in a unique representation, and each page is
represented as a box whose color is given by the data quarter associated with
the number of times the page has been read. To give a clear differentiation of
the data quarters, we chose four vivid colors; the 25% of less read pages (first
quarter) is represented with a green color, the 25% of pages under the median
(second quarter) has a cyan color, the 25% above the median (third quarter) is
given a violet color, and 25% of most read pages (fourth quarter) has a red color.
Fig. 2 shows a representative example of an issue. With representative, we
mean that it depicts the usual distribution of the page readings if considering
different issues. Indeed, the first part of the issue is usually the most read (red
boxes), alternated and followed by the violet boxes that represent the third
quarter. The cyan boxes that can be occasionally met even in the first half of
the issue represent pages with ads, which have been automatically detected since
they are the ones with no text. The less read pages can be found at the end of the
issue, represented in green. The fact that the advertising pages do not represent
the less considered quarter shows the effectiveness of placing ads in between
pages that are of interest for the users.
Fig. 2. An example of issue, whose color indicate the frequency with which they have
been read.
Clustering of the pages that have been read together The last feature we
present is a clustering of the pages in a magazine issue, based on the sessions in
which they have been read. Each page is represented by a binary vector, whose
elements represent the session IDs and contain 1 if the page was read in the
corresponding session, 0 otherwise.
To estimate the number of clusters a priori, the tool employs a technique
called canopy. This is a fast approximate clustering technique, used to divide
the input set of points into overlapping clusters, known as canopies. Although
this algorithm may not give accurate and precise clusters, it can detect the
optimal number of clusters extremely quickly (i.e., with a single pass over the
data). For this reason, the tool runs the algorithm as a pre-processing step to
automatically find the optimal number of clusters k, which is given as input to
the k-means clustering algorithm, along with the vector representation of the
pages, to generate the clusters.
Once the clusters have been detected, the output is given as a set of pages
that are in a cluster, plus an automatically-generated description of the cluster
in terms of topics, where the relevance of the topic for the cluster is indicated.
Let relevancet,p indicate the relevance of a topic t for a page p, and distancep,c
indicate the distance of a page p from the centroid of the cluster c in which the
page is. The relevance of a topic t for a cluster c is built as follows:
X relevancet,p
relevancet,c =
p∈c
distancep,c
Thanks to this formula, the highest is the difference in the reading behavior
of a page p with respect to the the others in the cluster c, the lower is the
weight assigned to the topic t for that cluster (the value distancep,c is seen as
an indication of “cohesion” between the page and the rest of the cluster).
In order to give a relative value to the relevance of a topic for a cluster and
give the human editor the perception of the reading behavior in a cluster, we
normalize the relevance of each topic with a value between 0 and 1, as follows:
relevancet,c − min(relevancec )
relevancet,c =
max(relevancec ) − min(relevancec )
where min(relevancec ) and max(relevancec ) respectively indicate the mini-
mum and maximum relevance values obtained by a topic in a cluster c. Trivially,
1 is the score assigned to the most relevant topic, and 0 is the score assigned to
the least relevant topic.
Due to space constraints, we will not show a screenshot of this feature, but we
will provide an example of the description of an issue, whose pages can be split
into three clusters based on the readings sessions. The automatic descriptions
generated by the tool are the following:
1. lifestyle (1.00), family life (0.99), health and self-care (0.31), cinema (0.00),
tv (0.00)
2. family life (1.00), lifestyle (0.56), health and self-care (0.24), cinema (0.05),
tv (0.00)
3. lifestyle (1.00), family life (0.84), health and self-care (0.32), cinema (0.03),
tv (0.00)
Apart from the content in terms of pages of these three clusters (which would
not be interesting for this purpose of this paper), we can see that based on the
reading sessions, the interest of the users varies significantly from cluster to
cluster. Indeed, in the first cluster, the pages that are characterized by lifestyle
and family life have been read with similar interest in the same sessions, while
health and self-care generated a much lower interest, and the users showed the
lowest interest for cinema- or tv-related topics. The second cluster of pages is
instead much more centered toward pages related to family life, while lifestyle
has been half as relevant in those reading sessions; health and self-care is a topic
that generates little interest, and cinema and tv still represent the topics that
generate less interest in the users. Finally, the third cluster shows the same
ranking as the first one, but with different weights.
This feature gives insights to the human editor on both the ways in which the
users read a magazine issue (pages are grouped based on the reading sessions)
and on the topics that characterize these sessions with their associated relevance.
It should be noted that the combined use of the features provided by our tool
can be very helpful to the human editors. For example, if given these clusters a
human editor wanted to increase the relevance of cinema and tv pages, knowing
that they are usually placed at the end of an issue (i.e., the less read portion),
the articles related to these topics could be moved into a section of the magazine
that appears earlier in future issues.
5 Conclusions and Future Work
In this paper we presented Reader Behavior, a Java tool developed to analyze the
reading behavior of the users, based on their interactions with a mobile digital
publishing platform, named Viewerplus.
Our proposal takes the data collected during the browsing of a magazine’s
issues, extracts the reading sessions of the users, and provides visual and de-
scriptive features of how the users read a given magazine issue. The objective is
to provide the human editors with tools that allow them to get to know their
customers more and improve the service they provide to them.
At the moment, the tool provides three features that describe the reading
behavior of the users from different perspectives. Future work will extend the
tool with additional features, like the automatic description of the subgraphs in
the “co-readings graph”, or the possibility to click on a box with the interest
toward a page, in order to show which topics characterize that page. Moreover,
we will employ more real-world datasets and try to develop metrics to describe
the reading behavior not only in terms of single magazine issues, but by giving
a global view on how a magazine is read.
Acknowledgments
The authors would like to thank Gianluca Zuddas, Andrea Aresu, Giacomo
Piseddu, Paolo Tanzi, Davide Melis, Corrado Alvau, and Francesco Argiolas,
for their contribution in this research work.
References
1. Yang, J., Qiao, Y., Zhang, X., He, H., Liu, F., Cheng, G.: Characterizing user
behavior in mobile internet. IEEE Trans. Emerging Topics Comput. 3 (2015)
95–106
2. Okoli, C., Mehdi, M., Mesgari, M., Nielsen, F.A., Lanamäki, A.: The people’s
encyclopedia under the gaze of the sages: A systematic review of scholarly research
on Wikipedia (2012)
3. Antin, J., Cheshire, C.: Readers are not free-riders: Reading as a form of partici-
pation on wikipedia. In: Proceedings of the 2010 ACM Conference on Computer
Supported Cooperative Work. CSCW ’10, New York, NY, USA, ACM (2010) 127–
130
4. Lehmann, J., Müller-Birn, C., Laniado, D., Lalmas, M., Kaltenbrunner, A.: Reader
preferences and behavior on wikipedia. In: Proceedings of the 25th ACM Confer-
ence on Hypertext and Social Media. HT ’14, New York, NY, USA, ACM (2014)
88–97
5. Castillo, C., El-Haddad, M., Pfeffer, J., Stempeck, M.: Characterizing the life
cycle of online news stories using social media reactions. In: Proceedings of the
17th ACM Conference on Computer Supported Cooperative Work & Social
Computing. CSCW ’14, New York, NY, USA, ACM (2014) 211–223
6. Zhang, L., Ma, W.: Correlation analysis between users’ educational level and
mobile reading behavior. Library Hi Tech 29 (2011) 424–435
7. Beymer, D., Russell, D.M.: Webgazeanalyzer: A system for capturing and analyzing
web reading behavior using eye gaze. In: CHI ’05 Extended Abstracts on Human
Factors in Computing Systems. CHI EA ’05, New York, NY, USA, ACM (2005)
1913–1916
8. Granka, L.A., Joachims, T., Gay, G.: Eye-tracking analysis of user behavior in www
search. In: Proceedings of the 27th Annual International ACM SIGIR Conference
on Research and Development in Information Retrieval. SIGIR ’04, New York, NY,
USA, ACM (2004) 478–479
9. Church, K., de Oliveira, R.: What’s up with whatsapp?: Comparing mobile instant
messaging behaviors with traditional sms. In: Proceedings of the 15th International
Conference on Human-computer Interaction with Mobile Devices and Services.
MobileHCI ’13, New York, NY, USA, ACM (2013) 352–361
10. Kim, Y.H., Kim, D.J., Wachter, K.: A study of mobile user engagement (moen):
Engagement motivations, perceived value, satisfaction, and continued engagement
intention. Decis. Support Syst. 56 (2013) 361–370
11. Verkasalo, H., López-Nicolás, C., Molina-Castillo, F.J., Bouwman, H.: Analysis of
users and non-users of smartphone applications. Telemat. Inf. 27 (2010) 242–255
12. Xu, Q., Erman, J., Gerber, A., Mao, Z., Pang, J., Venkataraman, S.: Identifying
diverse usage behaviors of smartphone apps. In: Proceedings of the 2011 ACM
SIGCOMM Conference on Internet Measurement Conference. IMC ’11, New York,
NY, USA, ACM (2011) 329–344
13. Tossell, C., Kortum, P., Rahmati, A., Shepard, C., Zhong, L.: Characterizing web
use on smartphones. In: Proceedings of the SIGCHI Conference on Human Factors
in Computing Systems. CHI ’12, New York, NY, USA, ACM (2012) 2769–2778
14. Church, K., Smyth, B., Cotter, P., Bradley, K.: Mobile information access: A study
of emerging search behavior on the mobile internet. ACM Trans. Web 1 (2007)
15. Church, K., Oliver, N.: Understanding mobile web and mobile search use in today’s
dynamic mobile landscape. In: Proceedings of the 13th International Conference
on Human Computer Interaction with Mobile Devices and Services. MobileHCI
’11, New York, NY, USA, ACM (2011) 67–76
16. Shafiq, M.Z., Ji, L., Liu, A.X., Pang, J., Wang, J.: Characterizing geospatial
dynamics of application usage in a 3g cellular data network. In Greenberg, A.G.,
Sohraby, K., eds.: Proceedings of the IEEE INFOCOM 2012, Orlando, FL, USA,
March 25-30, 2012, IEEE (2012) 1341–1349
17. Keralapura, R., Nucci, A., Zhang, Z.L., Gao, L.: Profiling users in a 3g network us-
ing hourglass co-clustering. In: Proceedings of the Sixteenth Annual International
Conference on Mobile Computing and Networking. MobiCom ’10, New York, NY,
USA, ACM (2010) 341–352
18. Catledge, L.D., Pitkow, J.E.: Characterizing browsing strategies in the world-wide
web. In: Proceedings of the Third International World-Wide Web Conference on
Technology, Tools and Applications, New York, NY, USA, Elsevier North-Holland,
Inc. (1995) 1065–1073
19. McCallum, A.K.: Mallet: A machine learning for language toolkit.
http://mallet.cs.umass.edu (2002)