SlideShare a Scribd company logo
1 of 28
Distributed Systems Group CSE Department 1
On Managing Social Data for
Enabling Socially-Aware
Applications and Services
Paul Anderson, Nicolas Kourtellis,
Joshua Finnis and Adriana Iamnitchi
Distributed Systems Group CSE Department2
Outline
 Current Applications
 Limitations
 Problem Statement
 Solution
 Motivating Social Applications
 A Geo-Social Data Management Service
 Early Experiences with Real Social Data
 Decentralized Solution (not in paper)
Distributed Systems Group CSE Department3
Current Applications
 Social knowledge used in applications
Distributed Systems Group CSE Department4
Limitations
 Social information collected only from one
application domain
 limited knowledge
 high bootstrap costs
 Information from Online Social Networks
can be misleading
 hidden incentives to have many “friends”
 all friends equal
Distributed Systems Group CSE Department5
Problem Statement
How can we utilize the wealth of diverse
social information to enable novel classes
of social applications?
Distributed Systems Group CSE Department6
Solution
 Collect social information from multiple
sources - social sensors
 Maintain this information in a directed,
weighted, multi-edge social graph
 Offer a set of basic social inference
functions to allow rapid design of new
socially-aware applications and services
Distributed Systems Group CSE Department7
Motivating Social Applications
Silence phone when inappropriate
Distributed Systems Group CSE Department8
Motivating Social Applications
Create personalized emergency evacuation routes
Distributed Systems Group CSE Department9
Motivating Social Applications
Data placement based on social incentives
Distributed Systems Group CSE Department10
Outline
 Current Applications
 Limitations
 Problem Statement
 Solution
 Motivating Social Applications
 A Geo-Social Data Management Service
 Early Experiences with Real Social Data
 Decentralized Solution (not in paper)
Distributed Systems Group CSE Department11
GeoS Overview
Distributed Systems Group CSE Department12
Social Sensors
 Location (via GPS, GSM)
 Collocation (via BT)
 Schedule (e.g., Google calendar)
 Mobile phone activity (calls, sms)
 Online Social Network interactions
 Emails
 Personal relations (family)
 and others
Distributed Systems Group CSE Department13
Research Questions
 GeoS maintains a directed, weighted,
labeled, multi-edge social graph that
stores social information from multiple
social sensors
 Open research issues
 Tags of activities
 Weights for social sensors
 Aging of weights on edges in GeoS
Distributed Systems Group CSE Department14
Geo-Social Inference Functions
 Currently GeoS provides 5 basic social
inference functions
 More complex functions can be composed
from those provided
1. friend_test (ego, alter, , w)ɑ
2. top_friends (ego, , n)ɑ
3. neighborhood (ego, , w, radius)ɑ
4. proximity (ego, , w, radius, distance)ɑ
5. social_strength (ego, alter)
Distributed Systems Group CSE Department15
Social Strength (ego, alter)
 Quantifies the social strength between
ego and alter
 Result normalized to consider overall
user activity
 Search all paths of 2 social hops max
Distributed Systems Group CSE Department16
Neighborhood Inference Example
Distributed Systems Group CSE Department17
Social Strength Example
The normalized weight
from A to its adjacent
neighbor B (NW{AB}) is
the sum of all the weights
of the edges from A to B
(aggregating over all types
of interactions between A
and B) divided by the
largest of all the sums of
weights going from user A
to one of its neighbors (D)
Distributed Systems Group CSE Department18
Social Strength Example (cont)
The path strength from A
to C through B (PS{ABC})
is the lowest of all the NW
on that path, divided by
the length of the path.
The social strength from
user A to user C
(SocS{AC}) is the largest
path strength from A to C.
Distributed Systems Group CSE Department19
Early Experiences with Real Social Data
 Dataset Characteristics:
 104 randomly selected students from
NJIT campus
 Many commuters  sparse traces
 Typical users provided a few hours of
data per day
 Data recorded
 Bluetooth proximity between users
 Facebook friendships
Distributed Systems Group CSE Department20
 81 students appear
in both collocation
and Facebook traces
 Small world
characteristics
APL=2.50,CC=0.366
vs
APL=2.98,CC=0.094
in a random graph
Early Experiences with Real Social Data
Distributed Systems Group CSE Department21
 Application scenario
 Students participate in community volunteering
projects
 Alice wants to invite some of them to an upcoming
activity
 Using the NJIT data set
 Facebook friends (FB): <facebook, 0.1>
 Collocation 45 minutes (CL.45): <volunteering, 0.1>
 Collocation 90 minutes (CL.90): <volunteering, 0.2>
 A neighborhood() request finds students
 A social_strength() request quantifies the importance
of the edge between Alice and a returned student
Early Experiences with Real Social Data
Distributed Systems Group CSE Department22
Neighborhood Function Results
Distributed Systems Group CSE Department23
Social Strength Function Results
0.0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1.0
1 2
SOCIAL HOPS FROM SOURCE
SOCSVALUE
CL.45 or FB CL.45
FB CL.90 or FB
CL.90 CL.45 and FB
CL.90 and FB
Distributed Systems Group CSE Department24
Discussion: Geo-Social Sensors
 Lots of challenges in building a reliable social sensor: must
determine label and weight of input
 Possible solutions for finding label:
 Mine text for keywords (emails, sms, blogs, etc)
 Reverse geo-coding to find where located and/or
collocated
 Use of a label ontology supplied by GeoS to maintain a
consistent dictionary of labels across different sensors.
 A sensor should dynamically calculate the weight of a user
interaction, considering:
 History of user social activity, by aggregating
frequency, time duration, time in-between activity
instances, etc.
 User’s interests
 “Familiar strangers” versus active social interaction
Distributed Systems Group CSE Department25
Discussion: User Privacy
 Perhaps the most important challenge
introduced by aggregated information
from multiple social sensors.
 Using and enforcing user policies on
what data can be collected and used
(particularly from mobile devices) is
necessary for adoption.
 Unfortunately, even if social data are
encrypted and well protected, personal
information can still be exposed by
aggregate or indirect measures (e.g.,
node degree in a graph).
Distributed Systems Group CSE Department26
Decentralized GeoS
Distributed Systems Group CSE Department27
Decentralized GeoS
 Store social information on distributed
nodes (DHT-based infrastructure)
 Use ACLs and PKI encryption to restrict data
access only to trusted users and services
 Experiments on PlanetLab to evaluate the:
 costs of inferences on an Internet-connected
distributed social graph
 effect of mapping information of socially-
connected users onto the same peer
 costs of socially-aware ACL maintenance
Distributed Systems Group CSE Department28
Thank you!
Questions?
nkourtel@mail.usf.edu

More Related Content

What's hot

Recomendation system: Community Detection Based Recomendation System using Hy...
Recomendation system: Community Detection Based Recomendation System using Hy...Recomendation system: Community Detection Based Recomendation System using Hy...
Recomendation system: Community Detection Based Recomendation System using Hy...Rajul Kukreja
 
Community detection algorithms
Community detection algorithmsCommunity detection algorithms
Community detection algorithmsAlireza Andalib
 
Clique-based Network Clustering
Clique-based Network ClusteringClique-based Network Clustering
Clique-based Network ClusteringGuang Ouyang
 
Node XL - features and demo
Node XL - features and demoNode XL - features and demo
Node XL - features and demoMayank Mohan
 
Simplifying Social Network Diagrams
Simplifying Social Network Diagrams Simplifying Social Network Diagrams
Simplifying Social Network Diagrams Lynn Cherny
 
Community detection in complex social networks
Community detection in complex social networksCommunity detection in complex social networks
Community detection in complex social networksAboul Ella Hassanien
 
Inferring Peer Centrality in Socially-Informed Peer-to-Peer Systems
Inferring Peer Centrality in Socially-Informed Peer-to-Peer SystemsInferring Peer Centrality in Socially-Informed Peer-to-Peer Systems
Inferring Peer Centrality in Socially-Informed Peer-to-Peer SystemsNicolas Kourtellis
 
Mining and analyzing social media part 2 - hicss47 tutorial - dave king
Mining and analyzing social media   part 2 - hicss47 tutorial - dave kingMining and analyzing social media   part 2 - hicss47 tutorial - dave king
Mining and analyzing social media part 2 - hicss47 tutorial - dave kingDave King
 
A Picture Is Worth A Thousand Questions Docx
A Picture Is Worth A Thousand Questions DocxA Picture Is Worth A Thousand Questions Docx
A Picture Is Worth A Thousand Questions DocxWebometrics Class
 
Social network analysis basics
Social network analysis basicsSocial network analysis basics
Social network analysis basicsPradeep Kumar
 
Exploring Social Media with NodeXL
Exploring Social Media with NodeXL Exploring Social Media with NodeXL
Exploring Social Media with NodeXL Shalin Hai-Jew
 
Social Network Analysis Using Gephi
Social Network Analysis Using Gephi Social Network Analysis Using Gephi
Social Network Analysis Using Gephi Goa App
 
Social media community using optimized algorithm by M. Gomathi / Lecturer
Social media community using optimized algorithm by M. Gomathi / LecturerSocial media community using optimized algorithm by M. Gomathi / Lecturer
Social media community using optimized algorithm by M. Gomathi / Lecturergomathi chlm
 
Community detection in social networks[1]
Community detection in social networks[1]Community detection in social networks[1]
Community detection in social networks[1]sdnumaygmailcom
 
Multi-Layer Friendship Modeling for Location-Based Mobile Social Networks
Multi-Layer Friendship Modeling for Location-Based Mobile Social NetworksMulti-Layer Friendship Modeling for Location-Based Mobile Social Networks
Multi-Layer Friendship Modeling for Location-Based Mobile Social Networksguanling
 
Finding prominent features in communities in social networks using ontology
Finding prominent features in communities in social networks using ontologyFinding prominent features in communities in social networks using ontology
Finding prominent features in communities in social networks using ontologycsandit
 

What's hot (20)

Recomendation system: Community Detection Based Recomendation System using Hy...
Recomendation system: Community Detection Based Recomendation System using Hy...Recomendation system: Community Detection Based Recomendation System using Hy...
Recomendation system: Community Detection Based Recomendation System using Hy...
 
Community detection algorithms
Community detection algorithmsCommunity detection algorithms
Community detection algorithms
 
Social network analysis
Social network analysisSocial network analysis
Social network analysis
 
Clique-based Network Clustering
Clique-based Network ClusteringClique-based Network Clustering
Clique-based Network Clustering
 
Node XL - features and demo
Node XL - features and demoNode XL - features and demo
Node XL - features and demo
 
Simplifying Social Network Diagrams
Simplifying Social Network Diagrams Simplifying Social Network Diagrams
Simplifying Social Network Diagrams
 
Community detection in complex social networks
Community detection in complex social networksCommunity detection in complex social networks
Community detection in complex social networks
 
Inferring Peer Centrality in Socially-Informed Peer-to-Peer Systems
Inferring Peer Centrality in Socially-Informed Peer-to-Peer SystemsInferring Peer Centrality in Socially-Informed Peer-to-Peer Systems
Inferring Peer Centrality in Socially-Informed Peer-to-Peer Systems
 
Mining and analyzing social media part 2 - hicss47 tutorial - dave king
Mining and analyzing social media   part 2 - hicss47 tutorial - dave kingMining and analyzing social media   part 2 - hicss47 tutorial - dave king
Mining and analyzing social media part 2 - hicss47 tutorial - dave king
 
CSE509 Lecture 6
CSE509 Lecture 6CSE509 Lecture 6
CSE509 Lecture 6
 
A Picture Is Worth A Thousand Questions Docx
A Picture Is Worth A Thousand Questions DocxA Picture Is Worth A Thousand Questions Docx
A Picture Is Worth A Thousand Questions Docx
 
Social network analysis basics
Social network analysis basicsSocial network analysis basics
Social network analysis basics
 
Exploring Social Media with NodeXL
Exploring Social Media with NodeXL Exploring Social Media with NodeXL
Exploring Social Media with NodeXL
 
Can we predict your sentiments by listening to your peers?
Can we predict your sentiments by listening to your peers?Can we predict your sentiments by listening to your peers?
Can we predict your sentiments by listening to your peers?
 
Social Network Analysis Using Gephi
Social Network Analysis Using Gephi Social Network Analysis Using Gephi
Social Network Analysis Using Gephi
 
Social media community using optimized algorithm by M. Gomathi / Lecturer
Social media community using optimized algorithm by M. Gomathi / LecturerSocial media community using optimized algorithm by M. Gomathi / Lecturer
Social media community using optimized algorithm by M. Gomathi / Lecturer
 
24 The Evolution of Network Thinking
24 The Evolution of Network Thinking24 The Evolution of Network Thinking
24 The Evolution of Network Thinking
 
Community detection in social networks[1]
Community detection in social networks[1]Community detection in social networks[1]
Community detection in social networks[1]
 
Multi-Layer Friendship Modeling for Location-Based Mobile Social Networks
Multi-Layer Friendship Modeling for Location-Based Mobile Social NetworksMulti-Layer Friendship Modeling for Location-Based Mobile Social Networks
Multi-Layer Friendship Modeling for Location-Based Mobile Social Networks
 
Finding prominent features in communities in social networks using ontology
Finding prominent features in communities in social networks using ontologyFinding prominent features in communities in social networks using ontology
Finding prominent features in communities in social networks using ontology
 

Viewers also liked

Privacy Concerns vs. User Behavior in Community Question Answering
Privacy Concerns vs. User Behavior in Community Question AnsweringPrivacy Concerns vs. User Behavior in Community Question Answering
Privacy Concerns vs. User Behavior in Community Question AnsweringNicolas Kourtellis
 
Prometheus: Distributed Management of Geo-Social Data
Prometheus: Distributed Management of Geo-Social DataPrometheus: Distributed Management of Geo-Social Data
Prometheus: Distributed Management of Geo-Social DataNicolas Kourtellis
 
Scalable Online Betweenness Centrality in Evolving Graphs
Scalable Online Betweenness Centrality in Evolving GraphsScalable Online Betweenness Centrality in Evolving Graphs
Scalable Online Betweenness Centrality in Evolving GraphsNicolas Kourtellis
 
VHT: Vertical Hoeffding Tree (IEEE BigData 2016)
VHT: Vertical Hoeffding Tree (IEEE BigData 2016)VHT: Vertical Hoeffding Tree (IEEE BigData 2016)
VHT: Vertical Hoeffding Tree (IEEE BigData 2016)Nicolas Kourtellis
 
Exercicis de formulació
Exercicis de formulacióExercicis de formulació
Exercicis de formulacióhelenabonet
 
Exercicis de formulació
Exercicis de formulacióExercicis de formulació
Exercicis de formulacióJavier Pérez
 
Exercicis de formulació
Exercicis de formulacióExercicis de formulació
Exercicis de formulacióAdriaTocados
 
Grace farfan
Grace farfanGrace farfan
Grace farfangracelili
 
Baromètre vacances Ipsos-Europ Assistance 2014_infographie3
Baromètre vacances Ipsos-Europ Assistance 2014_infographie3Baromètre vacances Ipsos-Europ Assistance 2014_infographie3
Baromètre vacances Ipsos-Europ Assistance 2014_infographie3Europ Assistance Group
 

Viewers also liked (17)

Privacy Concerns vs. User Behavior in Community Question Answering
Privacy Concerns vs. User Behavior in Community Question AnsweringPrivacy Concerns vs. User Behavior in Community Question Answering
Privacy Concerns vs. User Behavior in Community Question Answering
 
Prometheus: Distributed Management of Geo-Social Data
Prometheus: Distributed Management of Geo-Social DataPrometheus: Distributed Management of Geo-Social Data
Prometheus: Distributed Management of Geo-Social Data
 
Scalable Online Betweenness Centrality in Evolving Graphs
Scalable Online Betweenness Centrality in Evolving GraphsScalable Online Betweenness Centrality in Evolving Graphs
Scalable Online Betweenness Centrality in Evolving Graphs
 
VHT: Vertical Hoeffding Tree (IEEE BigData 2016)
VHT: Vertical Hoeffding Tree (IEEE BigData 2016)VHT: Vertical Hoeffding Tree (IEEE BigData 2016)
VHT: Vertical Hoeffding Tree (IEEE BigData 2016)
 
Exercicis de formulació
Exercicis de formulacióExercicis de formulació
Exercicis de formulació
 
Exercicis de formulació
Exercicis de formulacióExercicis de formulació
Exercicis de formulació
 
Portrait evaluation
Portrait evaluationPortrait evaluation
Portrait evaluation
 
Exercicis de formulació
Exercicis de formulacióExercicis de formulació
Exercicis de formulació
 
Exercicis de formulació
Exercicis de formulacióExercicis de formulació
Exercicis de formulació
 
Social Media Marketing
Social Media MarketingSocial Media Marketing
Social Media Marketing
 
Grace farfan
Grace farfanGrace farfan
Grace farfan
 
drogas
drogasdrogas
drogas
 
Baromètre vacances Ipsos-Europ Assistance 2014_infographie3
Baromètre vacances Ipsos-Europ Assistance 2014_infographie3Baromètre vacances Ipsos-Europ Assistance 2014_infographie3
Baromètre vacances Ipsos-Europ Assistance 2014_infographie3
 
Seminário sobre a água 2ºc
Seminário sobre a água  2ºcSeminário sobre a água  2ºc
Seminário sobre a água 2ºc
 
desarrollo del pensamiento
desarrollo del pensamientodesarrollo del pensamiento
desarrollo del pensamiento
 
2850-M-P-50-GM-1-A0
2850-M-P-50-GM-1-A02850-M-P-50-GM-1-A0
2850-M-P-50-GM-1-A0
 
20150128113528275
2015012811352827520150128113528275
20150128113528275
 

Similar to On managing social data for enabling socially-aware applications and services

Socialnetworkanalysis 100225055227-phpapp02
Socialnetworkanalysis 100225055227-phpapp02Socialnetworkanalysis 100225055227-phpapp02
Socialnetworkanalysis 100225055227-phpapp02Adil Alpkoçak
 
Delta-Screening: A Fast and Efficient Technique to Update Communities in Dyna...
Delta-Screening: A Fast and Efficient Technique to Update Communities in Dyna...Delta-Screening: A Fast and Efficient Technique to Update Communities in Dyna...
Delta-Screening: A Fast and Efficient Technique to Update Communities in Dyna...Subhajit Sahu
 
Extracting Social Network Data and Multimedia Communications from Social Medi...
Extracting Social Network Data and Multimedia Communications from Social Medi...Extracting Social Network Data and Multimedia Communications from Social Medi...
Extracting Social Network Data and Multimedia Communications from Social Medi...Shalin Hai-Jew
 
Analyzing Social Media with Digital Methods. Possibilities, Requirements, and...
Analyzing Social Media with Digital Methods. Possibilities, Requirements, and...Analyzing Social Media with Digital Methods. Possibilities, Requirements, and...
Analyzing Social Media with Digital Methods. Possibilities, Requirements, and...Bernhard Rieder
 
From context aware to socially awareness computing - IEEE Pervasive Computing...
From context aware to socially awareness computing - IEEE Pervasive Computing...From context aware to socially awareness computing - IEEE Pervasive Computing...
From context aware to socially awareness computing - IEEE Pervasive Computing...Fread Mzee
 
Designing People’s Interconnections in Mobile Social Networks
Designing People’s Interconnections in Mobile Social NetworksDesigning People’s Interconnections in Mobile Social Networks
Designing People’s Interconnections in Mobile Social Networksinscit2006
 
Effective community search_dami2015
Effective community search_dami2015Effective community search_dami2015
Effective community search_dami2015Nicola Barbieri
 
Researching Social Media – Big Data and Social Media Analysis
Researching Social Media – Big Data and Social Media AnalysisResearching Social Media – Big Data and Social Media Analysis
Researching Social Media – Big Data and Social Media AnalysisFarida Vis
 
Geo community-based broadcasting for data dissemination in mobile social netw...
Geo community-based broadcasting for data dissemination in mobile social netw...Geo community-based broadcasting for data dissemination in mobile social netw...
Geo community-based broadcasting for data dissemination in mobile social netw...IEEEFINALYEARPROJECTS
 
Social Event Detection using Multimodal Clustering and Integrating Supervisor...
Social Event Detection using Multimodal Clustering and Integrating Supervisor...Social Event Detection using Multimodal Clustering and Integrating Supervisor...
Social Event Detection using Multimodal Clustering and Integrating Supervisor...Symeon Papadopoulos
 
Knowledge Sharing over social networking systems
Knowledge Sharing over social networking systemsKnowledge Sharing over social networking systems
Knowledge Sharing over social networking systemstanguy
 
Infrastructures Supporting Inter-disciplinary Research - Exemplars from the UK

Infrastructures Supporting Inter-disciplinary Research - Exemplars from the UK
Infrastructures Supporting Inter-disciplinary Research - Exemplars from the UK

Infrastructures Supporting Inter-disciplinary Research - Exemplars from the UK
NeISSProject
 
User Identity Linkage: Data Collection, DataSet Biases, Method, Control and A...
User Identity Linkage: Data Collection, DataSet Biases, Method, Control and A...User Identity Linkage: Data Collection, DataSet Biases, Method, Control and A...
User Identity Linkage: Data Collection, DataSet Biases, Method, Control and A...IIIT Hyderabad
 
One Tag to bind them all: Measuring Term abstractness in Social Metadata
One Tag to bind them all: Measuring Term abstractness in Social MetadataOne Tag to bind them all: Measuring Term abstractness in Social Metadata
One Tag to bind them all: Measuring Term abstractness in Social MetadataInovex GmbH
 
Proactive Displays IIIA 20080627
Proactive Displays IIIA 20080627Proactive Displays IIIA 20080627
Proactive Displays IIIA 20080627Joe McCarthy
 
Social Software and Community Information Systems
Social Software and Community Information SystemsSocial Software and Community Information Systems
Social Software and Community Information SystemsRalf Klamma
 

Similar to On managing social data for enabling socially-aware applications and services (20)

CSE509 Lecture 5
CSE509 Lecture 5CSE509 Lecture 5
CSE509 Lecture 5
 
Social Network Analysis
Social Network AnalysisSocial Network Analysis
Social Network Analysis
 
Socialnetworkanalysis 100225055227-phpapp02
Socialnetworkanalysis 100225055227-phpapp02Socialnetworkanalysis 100225055227-phpapp02
Socialnetworkanalysis 100225055227-phpapp02
 
Cyberistructure
CyberistructureCyberistructure
Cyberistructure
 
Web and Complex Systems Lab @ Kno.e.sis
Web and Complex Systems Lab @ Kno.e.sisWeb and Complex Systems Lab @ Kno.e.sis
Web and Complex Systems Lab @ Kno.e.sis
 
Delta-Screening: A Fast and Efficient Technique to Update Communities in Dyna...
Delta-Screening: A Fast and Efficient Technique to Update Communities in Dyna...Delta-Screening: A Fast and Efficient Technique to Update Communities in Dyna...
Delta-Screening: A Fast and Efficient Technique to Update Communities in Dyna...
 
Extracting Social Network Data and Multimedia Communications from Social Medi...
Extracting Social Network Data and Multimedia Communications from Social Medi...Extracting Social Network Data and Multimedia Communications from Social Medi...
Extracting Social Network Data and Multimedia Communications from Social Medi...
 
Analyzing Social Media with Digital Methods. Possibilities, Requirements, and...
Analyzing Social Media with Digital Methods. Possibilities, Requirements, and...Analyzing Social Media with Digital Methods. Possibilities, Requirements, and...
Analyzing Social Media with Digital Methods. Possibilities, Requirements, and...
 
From context aware to socially awareness computing - IEEE Pervasive Computing...
From context aware to socially awareness computing - IEEE Pervasive Computing...From context aware to socially awareness computing - IEEE Pervasive Computing...
From context aware to socially awareness computing - IEEE Pervasive Computing...
 
Designing People’s Interconnections in Mobile Social Networks
Designing People’s Interconnections in Mobile Social NetworksDesigning People’s Interconnections in Mobile Social Networks
Designing People’s Interconnections in Mobile Social Networks
 
Effective community search_dami2015
Effective community search_dami2015Effective community search_dami2015
Effective community search_dami2015
 
Researching Social Media – Big Data and Social Media Analysis
Researching Social Media – Big Data and Social Media AnalysisResearching Social Media – Big Data and Social Media Analysis
Researching Social Media – Big Data and Social Media Analysis
 
Geo community-based broadcasting for data dissemination in mobile social netw...
Geo community-based broadcasting for data dissemination in mobile social netw...Geo community-based broadcasting for data dissemination in mobile social netw...
Geo community-based broadcasting for data dissemination in mobile social netw...
 
Social Event Detection using Multimodal Clustering and Integrating Supervisor...
Social Event Detection using Multimodal Clustering and Integrating Supervisor...Social Event Detection using Multimodal Clustering and Integrating Supervisor...
Social Event Detection using Multimodal Clustering and Integrating Supervisor...
 
Knowledge Sharing over social networking systems
Knowledge Sharing over social networking systemsKnowledge Sharing over social networking systems
Knowledge Sharing over social networking systems
 
Infrastructures Supporting Inter-disciplinary Research - Exemplars from the UK

Infrastructures Supporting Inter-disciplinary Research - Exemplars from the UK
Infrastructures Supporting Inter-disciplinary Research - Exemplars from the UK

Infrastructures Supporting Inter-disciplinary Research - Exemplars from the UK

 
User Identity Linkage: Data Collection, DataSet Biases, Method, Control and A...
User Identity Linkage: Data Collection, DataSet Biases, Method, Control and A...User Identity Linkage: Data Collection, DataSet Biases, Method, Control and A...
User Identity Linkage: Data Collection, DataSet Biases, Method, Control and A...
 
One Tag to bind them all: Measuring Term abstractness in Social Metadata
One Tag to bind them all: Measuring Term abstractness in Social MetadataOne Tag to bind them all: Measuring Term abstractness in Social Metadata
One Tag to bind them all: Measuring Term abstractness in Social Metadata
 
Proactive Displays IIIA 20080627
Proactive Displays IIIA 20080627Proactive Displays IIIA 20080627
Proactive Displays IIIA 20080627
 
Social Software and Community Information Systems
Social Software and Community Information SystemsSocial Software and Community Information Systems
Social Software and Community Information Systems
 

Recently uploaded

Disentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTDisentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTSérgio Sacani
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsSérgio Sacani
 
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxSOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxkessiyaTpeter
 
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...Sérgio Sacani
 
Artificial Intelligence In Microbiology by Dr. Prince C P
Artificial Intelligence In Microbiology by Dr. Prince C PArtificial Intelligence In Microbiology by Dr. Prince C P
Artificial Intelligence In Microbiology by Dr. Prince C PPRINCE C P
 
Types of different blotting techniques.pptx
Types of different blotting techniques.pptxTypes of different blotting techniques.pptx
Types of different blotting techniques.pptxkhadijarafiq2012
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSarthak Sekhar Mondal
 
Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )aarthirajkumar25
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsAArockiyaNisha
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)PraveenaKalaiselvan1
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...anilsa9823
 
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRStunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRDelhi Call girls
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptxanandsmhk
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxAleenaTreesaSaji
 
Caco-2 cell permeability assay for drug absorption
Caco-2 cell permeability assay for drug absorptionCaco-2 cell permeability assay for drug absorption
Caco-2 cell permeability assay for drug absorptionPriyansha Singh
 
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡anilsa9823
 
Work, Energy and Power for class 10 ICSE Physics
Work, Energy and Power for class 10 ICSE PhysicsWork, Energy and Power for class 10 ICSE Physics
Work, Energy and Power for class 10 ICSE Physicsvishikhakeshava1
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfmuntazimhurra
 

Recently uploaded (20)

Disentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOSTDisentangling the origin of chemical differences using GHOST
Disentangling the origin of chemical differences using GHOST
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
 
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxSOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
 
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
PossibleEoarcheanRecordsoftheGeomagneticFieldPreservedintheIsuaSupracrustalBe...
 
Artificial Intelligence In Microbiology by Dr. Prince C P
Artificial Intelligence In Microbiology by Dr. Prince C PArtificial Intelligence In Microbiology by Dr. Prince C P
Artificial Intelligence In Microbiology by Dr. Prince C P
 
Types of different blotting techniques.pptx
Types of different blotting techniques.pptxTypes of different blotting techniques.pptx
Types of different blotting techniques.pptx
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
 
Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )Recombination DNA Technology (Nucleic Acid Hybridization )
Recombination DNA Technology (Nucleic Acid Hybridization )
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based Nanomaterials
 
CELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdfCELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdf
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)
 
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
Lucknow 💋 Russian Call Girls Lucknow Finest Escorts Service 8923113531 Availa...
 
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRStunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
 
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
 
GFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptxGFP in rDNA Technology (Biotechnology).pptx
GFP in rDNA Technology (Biotechnology).pptx
 
Caco-2 cell permeability assay for drug absorption
Caco-2 cell permeability assay for drug absorptionCaco-2 cell permeability assay for drug absorption
Caco-2 cell permeability assay for drug absorption
 
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service  🪡
CALL ON ➥8923113531 🔝Call Girls Kesar Bagh Lucknow best Night Fun service 🪡
 
Work, Energy and Power for class 10 ICSE Physics
Work, Energy and Power for class 10 ICSE PhysicsWork, Energy and Power for class 10 ICSE Physics
Work, Energy and Power for class 10 ICSE Physics
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdf
 

On managing social data for enabling socially-aware applications and services

  • 1. Distributed Systems Group CSE Department 1 On Managing Social Data for Enabling Socially-Aware Applications and Services Paul Anderson, Nicolas Kourtellis, Joshua Finnis and Adriana Iamnitchi
  • 2. Distributed Systems Group CSE Department2 Outline  Current Applications  Limitations  Problem Statement  Solution  Motivating Social Applications  A Geo-Social Data Management Service  Early Experiences with Real Social Data  Decentralized Solution (not in paper)
  • 3. Distributed Systems Group CSE Department3 Current Applications  Social knowledge used in applications
  • 4. Distributed Systems Group CSE Department4 Limitations  Social information collected only from one application domain  limited knowledge  high bootstrap costs  Information from Online Social Networks can be misleading  hidden incentives to have many “friends”  all friends equal
  • 5. Distributed Systems Group CSE Department5 Problem Statement How can we utilize the wealth of diverse social information to enable novel classes of social applications?
  • 6. Distributed Systems Group CSE Department6 Solution  Collect social information from multiple sources - social sensors  Maintain this information in a directed, weighted, multi-edge social graph  Offer a set of basic social inference functions to allow rapid design of new socially-aware applications and services
  • 7. Distributed Systems Group CSE Department7 Motivating Social Applications Silence phone when inappropriate
  • 8. Distributed Systems Group CSE Department8 Motivating Social Applications Create personalized emergency evacuation routes
  • 9. Distributed Systems Group CSE Department9 Motivating Social Applications Data placement based on social incentives
  • 10. Distributed Systems Group CSE Department10 Outline  Current Applications  Limitations  Problem Statement  Solution  Motivating Social Applications  A Geo-Social Data Management Service  Early Experiences with Real Social Data  Decentralized Solution (not in paper)
  • 11. Distributed Systems Group CSE Department11 GeoS Overview
  • 12. Distributed Systems Group CSE Department12 Social Sensors  Location (via GPS, GSM)  Collocation (via BT)  Schedule (e.g., Google calendar)  Mobile phone activity (calls, sms)  Online Social Network interactions  Emails  Personal relations (family)  and others
  • 13. Distributed Systems Group CSE Department13 Research Questions  GeoS maintains a directed, weighted, labeled, multi-edge social graph that stores social information from multiple social sensors  Open research issues  Tags of activities  Weights for social sensors  Aging of weights on edges in GeoS
  • 14. Distributed Systems Group CSE Department14 Geo-Social Inference Functions  Currently GeoS provides 5 basic social inference functions  More complex functions can be composed from those provided 1. friend_test (ego, alter, , w)ɑ 2. top_friends (ego, , n)ɑ 3. neighborhood (ego, , w, radius)ɑ 4. proximity (ego, , w, radius, distance)ɑ 5. social_strength (ego, alter)
  • 15. Distributed Systems Group CSE Department15 Social Strength (ego, alter)  Quantifies the social strength between ego and alter  Result normalized to consider overall user activity  Search all paths of 2 social hops max
  • 16. Distributed Systems Group CSE Department16 Neighborhood Inference Example
  • 17. Distributed Systems Group CSE Department17 Social Strength Example The normalized weight from A to its adjacent neighbor B (NW{AB}) is the sum of all the weights of the edges from A to B (aggregating over all types of interactions between A and B) divided by the largest of all the sums of weights going from user A to one of its neighbors (D)
  • 18. Distributed Systems Group CSE Department18 Social Strength Example (cont) The path strength from A to C through B (PS{ABC}) is the lowest of all the NW on that path, divided by the length of the path. The social strength from user A to user C (SocS{AC}) is the largest path strength from A to C.
  • 19. Distributed Systems Group CSE Department19 Early Experiences with Real Social Data  Dataset Characteristics:  104 randomly selected students from NJIT campus  Many commuters  sparse traces  Typical users provided a few hours of data per day  Data recorded  Bluetooth proximity between users  Facebook friendships
  • 20. Distributed Systems Group CSE Department20  81 students appear in both collocation and Facebook traces  Small world characteristics APL=2.50,CC=0.366 vs APL=2.98,CC=0.094 in a random graph Early Experiences with Real Social Data
  • 21. Distributed Systems Group CSE Department21  Application scenario  Students participate in community volunteering projects  Alice wants to invite some of them to an upcoming activity  Using the NJIT data set  Facebook friends (FB): <facebook, 0.1>  Collocation 45 minutes (CL.45): <volunteering, 0.1>  Collocation 90 minutes (CL.90): <volunteering, 0.2>  A neighborhood() request finds students  A social_strength() request quantifies the importance of the edge between Alice and a returned student Early Experiences with Real Social Data
  • 22. Distributed Systems Group CSE Department22 Neighborhood Function Results
  • 23. Distributed Systems Group CSE Department23 Social Strength Function Results 0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0 1 2 SOCIAL HOPS FROM SOURCE SOCSVALUE CL.45 or FB CL.45 FB CL.90 or FB CL.90 CL.45 and FB CL.90 and FB
  • 24. Distributed Systems Group CSE Department24 Discussion: Geo-Social Sensors  Lots of challenges in building a reliable social sensor: must determine label and weight of input  Possible solutions for finding label:  Mine text for keywords (emails, sms, blogs, etc)  Reverse geo-coding to find where located and/or collocated  Use of a label ontology supplied by GeoS to maintain a consistent dictionary of labels across different sensors.  A sensor should dynamically calculate the weight of a user interaction, considering:  History of user social activity, by aggregating frequency, time duration, time in-between activity instances, etc.  User’s interests  “Familiar strangers” versus active social interaction
  • 25. Distributed Systems Group CSE Department25 Discussion: User Privacy  Perhaps the most important challenge introduced by aggregated information from multiple social sensors.  Using and enforcing user policies on what data can be collected and used (particularly from mobile devices) is necessary for adoption.  Unfortunately, even if social data are encrypted and well protected, personal information can still be exposed by aggregate or indirect measures (e.g., node degree in a graph).
  • 26. Distributed Systems Group CSE Department26 Decentralized GeoS
  • 27. Distributed Systems Group CSE Department27 Decentralized GeoS  Store social information on distributed nodes (DHT-based infrastructure)  Use ACLs and PKI encryption to restrict data access only to trusted users and services  Experiments on PlanetLab to evaluate the:  costs of inferences on an Internet-connected distributed social graph  effect of mapping information of socially- connected users onto the same peer  costs of socially-aware ACL maintenance
  • 28. Distributed Systems Group CSE Department28 Thank you! Questions? nkourtel@mail.usf.edu