=Paper=
{{Paper
|id=Vol-478/paper-9
|storemode=property
|title=Efficient Reachability Management with a Semantic User Profile Framework
|pdfUrl=https://ceur-ws.org/Vol-478/paper9.pdf
|volume=Vol-478
|dblpUrl=https://dblp.org/rec/conf/um/StanEMD09
}}
==Efficient Reachability Management with a Semantic User Profile Framework==
https://ceur-ws.org/Vol-478/paper9.pdf
Efficient Reachability Management with a
Semantic User Profile Framework
Johann Stan1,3 , Elöd Egyed-Zsigmond2 , Pierre Maret3 and
Johann Daigremont1
1
Alcatel-Lucent Bell Labs France, Centre de Villarceaux,
Route de Villejust, 91620 Nozay, France
johann.stan; johann.daigremont@alcatel-lucent.com
2
Liris UMR CNRS 5205, Université de Lyon, 20 avenue Albert Einstein, 69621
Villeurbanne, France,
elod.egyed-zsigmond@insa-lyon.fr
3
Laboratoire Hubert-Curien UMR CNRS 5516, Universit Jean-Monnet, 18 Rue du
Professeur Benoit Lauras 42000 Saint-Etienne, France
pierre.maret@univ-st-etienne.fr
Abstract. The possession of mobile devices eased a lot our communi-
cation habits: contacting somebody in almost any situation is becoming
more and more easier. However, this implies the fact that unexpected
interruptions can occur that may cause discomfort to the user. A typ-
ical example is the case when an important meeting is interrupted by
an unexpected phone call, which is not important to consider in the
given context. The need for an efficient control of unexpected incoming
communications is immediate. This paper proposes the efficient handling
of interruptions by providing a new reachability preference model that
considers two dimensions for a reachability preference: (i) the currenet
situation of the user and (ii) the social category of the communication
partner. We propose a mechanism to build user preferences that specify
the level of interruptibility during an activity, situation or event. The
proposed system leverages semantic technologies for modeling the user
and data mining techniques for populating the user model.
1 Introduction and Related Work
Today, as smart phones become a daily companion for most people, user mod-
eling must address several new challenges. In our point of view, one of them is
the issue of how to provide meaningful assistance to end-users in communica-
tion needs. One domain is the reachability of the user in a given situation. We
define reachability as the preference of the end-user to be interruptible (by a
given service, like a phone call, sms, IM, notification) at a given time or time
interval. This choice for the definition is mainly based on [3], which claims that
users actually discriminate situations (in terms of caller, time, activity, situation
etc.) when they have to make decisions about accepting an interruption. Also,
an interesting approach of handling interruption is proposed by Schmidt et al.
[8]. In this approach, users of a mobile phone can share their context with the
caller with the help of predefined keywords (Home, Meeting, Work etc.). The
user has now the choice - knowing the context of the communication partner -
to establish a connection, to leave a message, or to cancel the call. Hofte also
studies the context information users are willing to share with a person about
their current situation in the case of an incoming phone call [9]. [10] uses un-
supervised learning, specifically co-clustering, to derive latent situation-based
patterns from usage logs of user interactions with the device and environments
and use the patterns for task and communication mode recommendations.
From the user’s point of view, assistance in reachability is an efficient filtering
of interruptions to his current state of mind or activity. As pointed out in [1],
interruptions are found mostly intrusive and have negative effects on the mental
state of the individual. Few solutions have been proposed for reachability man-
agement. The Negotiator system [2] attempts to make interruption handling less
cognitively demanding. The system allows the receiver of an incoming call to
negotiate with the sender an appropriate time for the interaction, but does not
prevent them from occurring. Traditional IM services (Yahoo Messenger, Google
Talk, MSN) allow users to explicitly define their availability as a status message:
“available”, “busy”, “on the phone”. Another approach is to gather information
about the user with sensors (keyboard or mouse activity or environmental data)
and thus automatically infer availability. The major problem in existing solutions
is that reachability preferences cannot be sufficiently personalized and that there
is no automatic control mechanism. In our view, reachability preferences depend
mainly on 3 major parameters: the current situation of the user, the social net-
work category of the person behind an attempt to interrupt the user and the
device used. These dimensions of a reachability preference were also highlighted
by [7]. These 3 parameters allow to specify rich rules like the following: “When
(Situation = Meeting) and (SocialNetworkCategory = Friends) and (Device =
Phone) then Block”. This means that friends will not be able to call the user
when he/she is in a meeting. However, the preference could be different for an
important family member.
For interoperability purposes, our user model is based on semantic tech-
nologies (OWL as description schema, SPARQL query language for information
retrieval). This choice is based on current research initiative to leverage semantic
technologies for a richer user profile representation. Several user profile models,
like GUMO (General User Model Ontology) [4] or UPOS (User-Profile Ontology
with Situation-Dependent Preferences Support) [5] are highly relevant to this
initiative. We propose in this paper a user profile model design that contains
reachability preferences based on the 3 parameters described before. Our user
model framework is composed of an ontological front-end for the general prob-
lem domain and a back-end that uses data mining and learning techniques to
assist the user in the definition of reachability preferences.
The rest of this paper is organized as follows. Section 2 presents the ontology
for the user profile model. Section 3 presents an upper-view of the framework.
Future enhancements of the system and conclusions are presented in Section 3.
2 The User Profile Ontology
The objective of this user model is to allow end-users to have personalizable pref-
erences in terms of reachability that are automatically activated. Preferences are
personalized according to three dimensions: the current situation of the user ,
the service (phone, IM, SMS, Mail) and the social network category (friend,
family, professional etc.) of the person who is behind the incoming interaction.
We divide the user model into submodels (Figure 1) (Concept: SituationalPro-
fileSubset). A submodel contains user preferences that are activated when that
specific situation occurs (Concept: Situation). A situation is described by several
contextual information (Concept: Context), composed of the Physical Context of
the user (Location, Environment etc.) and the context relative to the user itself
(Activity, Agenda, Tasks etc.). Each submodel contains the reachability prefer-
ences for the given situation. A preference concerns a Service (Phone, SMS, IM
etc.) and a Social Network Category (Friend, Family, Professional etc.) and con-
tains the notification modality for the Service in case it is activated by a contact
belonging to that category. An important aspect of this model is the categoriza-
tion of the address book into categories (SocialNetworkCategory). This needs a
manual intervention of the user but the benefits are considerable.
To illustrate the model, we consider an instance with two sub-profiles :
(Home Profile and Office Profile). Each sub-profile is activated when the given
situation occurs (e.g. the user is at home or at work). The Home Profile is asso-
ciated to the At Home situation, which has the following context: the location of
the user is Massy (a French town near Paris) - inferred from the Cell Tower Iden-
tifier from the mobile phone- , it is evening (Time), the user is with his son (Blue-
tooth peer detection) and the user is preparing to watch a movie(Agenda). Here
each value is an instance of a context concept (Location, Time, Environment,
Agenda). In this profile, the user has two preferences, the Home Preference,
which defines that when friends (Carla) and family members call, the phone will
ring. The other preference is the Office Preference, which consists in the fact,
that if an office colleague tries to call, he/she will receive a message: ”I am cur-
rently available on E-Mail.”. The second sub-profile is the Office Profile with 2
preferences. A Work Preference states that when the manager calls, the phone
will ring. The Family Preference states the same thing about important family
members. However, the Friend Preference states that if a friend calls (Carla),
the phone will only vibrate.
3 The Reachability Framework
The reachability framework contains tools for both filling the user profile with
information from different data sources and for retrieving this information. These
tools are separated in a front-end (information retrieval) and a back-end (pro-
file filling, data sources). Both components will be described in the following
paragraphs.
The front-end contains SPARQL query templates that are instantiated to
retrieve the notification modality from the user model. Such a query template
contains three parameters in input: the situation, the service and the category
of the incoming caller and the result is the notification modality for the service.
SPARQL was the optimal choice for this, since the user model has an OWL
representation.
Fig. 1. The user model ontology (main concepts are shown only)
The back-end of the framework contains the necessary mechanism for the
automatic profile construction and evolution. Our choice was for a flexible user
model in terms of preferences. An argument for this is the fact that neither
situations (the location for the Home situation can change), nor social network
categories are stable (a friend can become a family member, professional rela-
tionships can change etc.). The framework uses a technique that combines data
mining and machine learning in order to learn and update context of the differ-
ent situations of the user. The context of a situation is the primary source to
trigger a preference, since is contains machine-interpretable raw-data (a location
coordinate, a Bluetooth address). It is important to stress out that this algo-
rithm is only able to find general or regular situations of the user (habits), like
Home, Work, Shopping. Another data source is used to handle social events, that
occur occasionally, like going to the cinema on Friday night. A situation has a
rich contextual description. In the current state of the framework, we are able to
capture phone cellule identifiers for location and the list of available Bluetooth
peers, that give information about the social environment of the user (single or
in an open space): Context Snapshot = {Time of the snapshot, list GSM Cell
ID, list Bluetooth Peers}.
In the back-end of the framework, we use a multi-layered algorithm that
extracts habits of the user to learn situations and populates the ontology front-
end with the learned situations. Situations are strongly related to user habits. A
habit is a frequent pattern or item in the user’s context or activity. A frequent
pattern is an association of multiple context dimensions that frequently occur
together. The signature of a situation is a list of context dimension instances,
that indicates in which context the situation occurs for the user. In this way, if
we log the user context, finding situations in the context log is a problem similar
to finding frequent patterns in any kind of data log and can be solved with
data mining techniques [6]. Our choice was to adapt association rule mining
[6]. In our context model, generally one Cell ID co-occurs with one or more
Bluetooth peer. A frequent pattern is for example the co-occurrence of 40737 (a
Cell ID where Bell Labs France is situated) with ROLyyx0021 (Bluetooth peer
ID- smart phone of a colleague at work). When these two context instances are
present together frequently, it can be inferred that the user is at work: {CellID:
40737, Bluetooth: ROLyyx0021} : Situation: At Work. The feature extraction
algorithm uses two parameters, the support and the confidence of an itemset to
find frequent patterns. Support is an indicator of whether the item is frequent
or not. First the algorithm retrieves all items from the context database where
the support measure is superior to a minimal threshold (MinSupp):
[
F requentItems = { Item, Supp(Item) ≥ M inSupp} (1)
The second step in this layer is to combine elements from FrequentItems and
generate association rules. An association rule of two or more frequent items
creates rules with high confidence (superior to a MinConf threshold) in that
if the LHS (left-hand-side) is present in a context snapshot, the RHS (right-
hand-side) will also be present. Confidence can be interpreted as an estimate of
the conditional probability of RHS, knowing the probability of LHS, that is the
probability of finding the RHS of the rule in transactions under the condition
that these transactions also contain the LHS.
S
[ Supp(A B)
F requentRules = { (A ⇒ B), ≥ M inConf } (2)
Supp(B)
The result of the first layer is a set of associations between context dimensions
in form of rules. These rules encode the signature of a situation candidate with
two measures, the support and the confidence. The second layer is responsible of
classifying these rules. The classification Layer allows merging similar situations
and erasing those that did not occur for a long time. This layer allows the
method to be incremental (the database can be erased after extraction, which is
very important because of the limited storage space on a smart phone). First, a
merge of the LHC and RHC of association rules is realized, creating a signature
from the rule. A situation class candidate is created for each signature. For each
signature, the algorithm computes the distance to all other (existing already
or extracted) classes, except the signature itself. Distance is computed by the
number of co-occurrences in the two signatures. Then, the signature is unified
with the class that is the most similar. A local age parameter is associated to
each situation class. This parameter allows to erase classes that no longer appear.
The result of this classification step is a limited number of situation signa-
tures, which have the following properties: each context dimension respects the
minimal support threshold, the signature is a union of very similar association
rules and contains strongly correlated elements since this union is based on asso-
ciation rules respecting the minimal confidence level and this signature contains
all possible context dimensions that have a high probability to occur when the
user is in the given situation.
As mentioned before, this algorithm is able only to find regular situations.
The detection of exceptions (in this case occasional events) is a big challenge
in any data mining approach. We consider the user calendar (Agenda concept
in the user model) as an important, yet unexplored source for this category of
situations. Users often introduce their social events in a calendar application
(Google, Outlook). The framework proposes a mechanism to the user to define
the reachability preference for a social event. This can be considered as an ex-
tension of the calendar template, where typically one specifies the name of the
event, the participants and the time interval. Our framework proposes a mech-
anism that prompts the user before the event to specify his/her reachability
preference. The only requirement for this to work is that the user fills regularly
in his/her calendar application the upcoming social event. Currently an imple-
mentation for mobile devices is deployed and we are gathering user feedback.
The implementation also contains a user-friendly interface that allows to tag
the social network category of a contact. The tagging happens after an interac-
tion with the given contact through pop-ups with buttons (Friend, Professional,
Family...). This allows the user to rapidly include all contacts into a category,
which is an important requirement for the system to work. Screenshots of the
current implementation are shown in Figure 2.
Fig. 2. Definition of reachability rules and assigning a category to an incoming caller
Our partial feedback resulting from experiences made on 5 persons during
different time periods has allowed us to validate the fact that social network
categories play an extremely important role in such preferences. Typically, in
the case of a professional meeting almost every person using the application
blocked phone calls from friends. Family seems to be the category that is always
allowed to interrupt. Another observation is the fact that preferences change
very dynamically. Initially we thought that preferences change only for general
situations (like work or home) and this seems to be wrong. A preference changes
even when the user moves from one place to another, like from the office to the
coffee machine. Currently this can be detected only when the user adds into the
calendar this event, which is not very frequent. We are currently investigating
how to detect such minor situations. Another major issue is the privacy concern,
since the context of the users is logged. An efficient mechanism is needed to allow
the algorithm to be incremental and thus to erase systematically the gathered
context logs.
4 Conclusion and Future Work
We address in this paper the question of how to build a user profile model that
can help better control our reachability in the context of an increasing exposure
to unexpected interactions (spam messages, incoming calls that are not impor-
tant in a situation etc.). We present a dynamic, situation-aware user model
framework that enables real-time situation detection and a better control on
the user’s reachability. We propose mechanisms (extraction, classification algo-
rithms, user feedback and services) that allow the model to adapt to the user.
Future work include a real evaluation for the current implementation and im-
provement of the data mining algorithm. Also, gateways to social networking
sites are considered to better automatize the categorization of contacts, leverag-
ing that specific sites consider different spheres of the social network and that
these systems are open for this kind of information retrieval.
References
1. R. Harr, V. Kaptelinin. 2007. Unpacking the social dimension of external inter-
ruptions, GROUP ’07: Proceedings of the 2007 international ACM conference on
Conference on supporting group work, ACM Press, 2007, pp. 399-408.
2. M. Wiberg, S. Whittaker. 2005. Managing Availability: Supporting Lightweight
Negotiations to Handle Interruptions. ACM T. HCI. 12, 4 (Dec. 2005), 365-387.
3. A. Toninelli, D. Khushraj, O. Lassila, R. Montanari. 2008. Towards Socially Aware
Mobile Phones. 7th International Semantic Web Conference (ISWC2008).
4. D. Heckmann, B. Brandherm. 2005. Gumo - the general user model ontology. In
Proceedings of User Modeling, Edinburgh, Scotland (2005)
5. M. Sutterer, O. Droegehorn, K. David. 2007. UPOS: User Profile Ontology with
Situation-Dependent Preferences Support. Proceedings of the First International
Conference on Advances in Computer-Human Interaction (2007) 230–235.
6. R. Agrawal, T. Imielinski, A. Swami. 1993. Mining Association Rules between Sets
of Items in Large Databases. SIGMOD. June 1993, 22(2):207–16,
7. Khalil, A. and Connelly, K. 2006. Context-aware telephony: privacy preferences
and sharing patterns. In Proceedings of the 2006 20th Anniversary Conference on
Computer Supported Cooperative Work (Banff, Alberta, Canada, November 04 -
08, 2006). CSCW ’06. ACM, New York, NY, 469-478.
8. Albrecht Schmidt, Antti Takaluoma and Jani Mntyjrvi. Context-Aware Telephony
over WAP. Personal Technologies Volume 4(4), September 2000. pp225-229.
9. Hofte, G. H. 2007. Xensible interruptions from your mobile phone. In Proceedings
of the 9th international Conference on Human Computer interaction with Mobile
Devices and Services (Singapore, September 09 - 12, 2007). MobileHCI ’07, vol.
309. ACM, New York, NY, 178-181.
10. D. Cheng, H. Song, H. Cho, S. Jeong, S. Kalasapur, A. Messer, ”Mobile Situation-
Aware Task Recommendation Application,” Next Generation Mobile Applications,
Services and Technologies, International Conference on, pp. 228-233, 2008 The Sec-
ond International Conference on Next Generation Mobile Applications, Services,
and Technologies, 2008.