Transcript Measuring Serendipity: Connecting People, Locations and Interests

Measuring Serendipity: Connecting
People, Locations and Interests in a
Mobile 3G Network
Ionut Trestian
Supranamaya Ranjan
Aleksandar Kuzmanovic
Antonio Nucci
Northwestern University
Narus Inc.
http://networks.cs.northwestern.edu
http://www.narus.com
Online Social Networks
Social network websites among the most
popular websites on the Internet
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
2
Mobage Town
Japan based mobile
social network
11 million users
Allows users to:
– Send messages, chat in
communities, exchange
music, read pocket novels,
write blogs, play games etc.
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
3
Loopt
Allows contacts to
visualize one another’s
location using mobile
phones and share
information
Available for Sprint,
Verizon, At&t, T-Mobile
on devices such as
BlackBerry, iPhone and
gPhone
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
4
Other Location Based Services
Sharing your location with
friends (BuddyBeacon –for
iPhone)
Location based searches
(EarthComber)
Notifications about places and
events around you (LightPole)
Tagging locations
(Metosphere)
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
5
Research Questions
How likely are we to meet in our daily lives people who
share common interests in the cyber domain?
What is the relationship between mobility properties,
location, and application affiliation in the cyber domain?
3,162,818 packet data sessions generated by 281,394
clients in 1196 locations (Base Stations) across a large
metropolitan area
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
6
Extracting Human Movement
Base
Station 1
1. Inter-session
2.
Intra-session movement
RADA Start
(contains BSID)
Base
Station 2
RADA Stop
Update
(contains BSID)
RADIUS
Server
Note that we have only a sampled view of
human movement.
How well can we do?
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
7
Extracting Human Movement
Despite sampled observations we still do a good job at
understanding user movement.
Most human movement is over short distances.
The ordering of the curves accounts for the larger time
span which can accommodate larger travel distances
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
8
Extracting Application Interest
Music
Social download
networking
Dating
website
website
website
http://www.singlesnet.com
http://www.facebook.com
http://www.mp3.com
Keyword based URL mining
Ionut Trestian
Interest
Keywords
Dating
dating, harmony, personals, single, match
Music
song, mp3, audio, music, track, pandora
Social netw.
facebook, myspace, blog
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
9
Rule Definitions
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
10
Rule Mining
Location A
Rule support:
Number of people
present at A
Rule confidence:
Number of people that
move from A to B
Rule confidence probability:
confidence/support
Location B
(A, B, w, δ)
W
Ionut Trestian
δ
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
11
Rule Statistics
IncreaseMovement
in numberrules
of active
are more
usersactive
at commute
during day time,
hours
also
(8AM
lessand
active
5PM)
during weekend
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
12
Location Rank – Application Accesses
Music
Socialdownloads
netw.
Mail –– dominates
correlation
– anti-correlation
the
withmedium
mobility
withmobility
span
mobilityrange
span
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
13
Location Ranking
Comfort zone
3
All users spend most of their time in
their top 3 locations
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
14
Location Rank – Application Accesses
Comfort zone
Music
Note
Social
that
downloads,
netw.
Dating
News
isDating,
accessed
and Mail
Trading
more
tend heavily
to
inbe
the
accessed
accessed
Comfort
in the
outside
comfort
Zone toozone
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
15
Home vs. Work
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
Hotspots
Via rule mining we detect highly active locations
We identify 4 types of such locations
– Noon hotspots – 28 such locations
• Highly active during Noon hours
– Night hotspots – 62 such locations
• Highly active during night hours
– Day-office hotspots – 23 such locations
• Highly active during day hours
– Evening hotspots – 8 such locations
• Highly active during the evening
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
17
Biased Application Access at Hotspots
Normalized
user affiliation
Despite similar userbase at hotspots during the seven
day interval, application accesses are highly skewed
towards certain applications.
Application
accesses
hotspots
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
18
Application Access - Time of Day
Application
accesses
non hotspots
However the bias in application access is not entirely
due to an illusive “time of day” effect !
Application
accesses
non hotspot
times
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
19
Regional analysis – Spectral Clustering
Using spectral
clustering we:
Cluster locations as
belonging to regions
Cluster users as
belonging to regions
Spectral clustering doesn’t make any assumptions on
the shape of the clusters(opposed to k-means)
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
20
Clustering Results
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
Regional Analysis – Research issues
Two relevant issues for location based services:
– Time independent interactions(useful for tagging
services) – part of user trajectories overlap irrespective
of the time of the movement
– Time dependent interactions – same location same time
Questions:
– How many distinct people with the same interests do we
meet?
• Strongly dependent on userbase (probability to meet people
higher in clusters with bigger userbase)
– How often do we meet people?
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
22
Time Independent Interactions
Cluster 1 has a higher number of interactions per
location mainly because of larger hotspot density
27/162 (Cluster 1)> 26/257 (Cluster 4) for night hotspots
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
23
Who Will Win the Interaction Race?
Event type
Mobile users
Seen in more
than 20
locations
Static users
(hotspot)
Spent more
than 6 hours in
a Hotspot
Static users
(non-hotspot)
Spent more
than 6 hours in
a non-hotspot
Social netw.
704
604
424
Music
828
565
319
Dating
253
188
96
However
Mobile
it pays
usersoffclearly
to spend
win time
the interaction
in popular race
locations
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
24
Conclusions
First study at such a large scale aimed at
correlating mobility, location, and application
usage
Provided new insights from user perspective,
location perspective, and provider perspective
that shows the enormous location based
service potential
Ionut Trestian
Measuring Serendipity: Connecting People, Locations and
Interests in a Mobile 3G Network
25