SlideShare a Scribd company logo
1 of 21
Download to read offline
Guangyuan Piao, John G. Breslin
Unit for Social Semantics
20th International Conference on Knowledge Engineering and Knowledge Management
Bologna, Italy, 19-23, November, 2016
Interest Representation, Enrichment, Dynamics, and
Propagation: A Study of the Synergetic Effect of
Different User Modeling Dimensions for Personalized
Recommendations on Twitter
2
1/3 users seek medical information
and over 50% users consume news
on Social Networks
Facebook and Twitter together generate
more than 5 billion microblogs / day
[SOURCE] Semantic Filtering for Social Data, Amit et al., Internet Computing’16
Background – User Modeling
content enrichment
analysis &
user modeling
interest profile
?
personalized content
recommendations
(How) can we infer
user interest profiles
that support the
content recommender?
3[SOURCE] Analyzing User Modeling on Twitter for Personalized News Recommendations, UMAP’11
4
Background – User Modeling
Dimensions
representation enrichment
propagation dynamics
5
Dimensions
representation
Bag of
Words
Topic
Modeling
Bag of
Concepts
Mixed
Approach
Background – User Modeling
Bag-of-Concepts example
dbpedia:The_Black_Keys (3)
dbpedia:Eagles_of_Death_Metal (5)
Background – User Modeling
dbpedia:The_Wombats (2)
Interest Frequency (IF)
7
Background – User Modeling
Dimensions
enrichment
8
Background – User Modeling
Dimensions
dynamics
Assumption:
user interests might
change over time
Background – User Modeling
Dimensions
propagation
dbpedia:The_Wombats
dbpedia:Indie_rockgenre
dbpedia:The_Black_Keys
dbc:Rock_music_duos
subject
10
Background – User Modeling
Dimensions
representation enrichment
propagation dynamics
dimensions have been studied separately
11
Aim of Work
representation enrichment
propagation dynamics
Dimensions
to investigate (how) can we
combine different dimensions for user modeling
12
User Modeling Framework
user interest
profiles
entity extraction
primitive
interestsIF weighting
temporal dynamics
interest propagation
primitive
& propagated
interests
synset extraction
optional enabled
enrichment
IDF weightingnormalization
13
Representation
•  concept-based
!  DBpedia concepts are extracted using Aylien API
•  mixed approach (WordNet synset & concept-based)
!  synsets are extracted using Degemmis’s method [UMUAI]
Enrichment
•  exploring embedded URL in tweets
!  concepts or synsets are extracted from the content of URL
Interest Representation & Enrichment
14
Propagation strategy using DBpedia
•  category-based
SP: sub-pages of the category
SC: sub-categories of the category
•  property-based
P: property count in DBpedia graph
Interest Propagation
15
Temporal Dynamics of User Interests
Interest decay functions
•  Long-term(Orlandi) [SEMANTiCS]
•  Long-term(Ahmed) [SIGKDD]
Long-term(Ahmedα): µ2week, µ2month, µall
•  Long-term(Abel) [WebSci]
µweek = µ = e -1
µmonth = µ 2
µall = µ 3
16
Design Space of User Modeling
The design space of user modeling, spanning
2x2x2x2=16 possible user modeling strategies.
Notation
•  um( representation; enrichment; dynamics; semantics )
•  use “none” to denote a certain dimension is disabled
!  um( synset & concept; enrichment; none; none)
Dataset
•  322 users: shared at least one link in the last two weeks
•  247,676 tweets in total
Experiment
•  task: recommending 10 links (URLs)
•  recommendation algorithm: cosine similarity(P(u), P(i))
P(i): item (link) profile using the same modeling strategy for P(u)
•  ground truth links: links shared in the last two weeks
•  candidate links: 15,440 links
17
Experiment Setup
used for user modeling
ground truth
links (URLs)
recommendation time
Results
with enrichment > without enrichment
Results
synset & concept > concept
Conclusions & Future Work
•  propagation helps
when using concept-based representation without enrichment
•  the most important dimensions :
Content Enrichment & Interest Representation
•  investigation of how different percentages of links affect the performance
•  the best-performing strategy :
um (synset & concept; enrichment; dynamics; none )
21
Thank you for your attention!
Guangyuan Piao
homepage: http://parklize.github.io
e-mail: guangyuan.piao@insight-centre.org
twitter: https://twitter.com/parklize
slideshare: http://www.slideshare.net/parklize

More Related Content

What's hot

Social Information & Browsing March 6
Social Information & Browsing   March 6Social Information & Browsing   March 6
Social Information & Browsing March 6
sritikumar
 
Digital Trails Dave King 1 5 10 Part 2 D3
Digital Trails   Dave King   1 5 10   Part 2   D3Digital Trails   Dave King   1 5 10   Part 2   D3
Digital Trails Dave King 1 5 10 Part 2 D3
Dave King
 
A topology based approach twittersdlfkjsdlkfj
A topology based approach twittersdlfkjsdlkfjA topology based approach twittersdlfkjsdlkfj
A topology based approach twittersdlfkjsdlkfj
Kunal Mittal
 
Visualization of Relationship between Social Bookmark Users
Visualization of Relationship between Social Bookmark UsersVisualization of Relationship between Social Bookmark Users
Visualization of Relationship between Social Bookmark Users
Kyohei Hamada
 
Social Media Data Mining
Social Media Data MiningSocial Media Data Mining
Social Media Data Mining
Ryan Reede
 

What's hot (20)

Conor Hayes - Topics, tags and trends in the blogosphere
Conor Hayes - Topics, tags and trends in the blogosphereConor Hayes - Topics, tags and trends in the blogosphere
Conor Hayes - Topics, tags and trends in the blogosphere
 
Dynamic personalized recommendation on sparse data
Dynamic personalized recommendation on sparse dataDynamic personalized recommendation on sparse data
Dynamic personalized recommendation on sparse data
 
Active reranking for web image search
Active reranking for web image searchActive reranking for web image search
Active reranking for web image search
 
Predicting Social Interactions from Different Sources of Location-based Knowl...
Predicting Social Interactions from Different Sources of Location-based Knowl...Predicting Social Interactions from Different Sources of Location-based Knowl...
Predicting Social Interactions from Different Sources of Location-based Knowl...
 
Social Information & Browsing March 6
Social Information & Browsing   March 6Social Information & Browsing   March 6
Social Information & Browsing March 6
 
Multi-Mode Conceptual Clustering Algorithm Based Social Group Identification ...
Multi-Mode Conceptual Clustering Algorithm Based Social Group Identification ...Multi-Mode Conceptual Clustering Algorithm Based Social Group Identification ...
Multi-Mode Conceptual Clustering Algorithm Based Social Group Identification ...
 
Next generation web
Next generation webNext generation web
Next generation web
 
Data mining on Social Media
Data mining on Social MediaData mining on Social Media
Data mining on Social Media
 
Jill Freyne - Collecting community wisdom: integrating social search and soci...
Jill Freyne - Collecting community wisdom: integrating social search and soci...Jill Freyne - Collecting community wisdom: integrating social search and soci...
Jill Freyne - Collecting community wisdom: integrating social search and soci...
 
Data mining in social network
Data mining in social networkData mining in social network
Data mining in social network
 
Digital Trails Dave King 1 5 10 Part 2 D3
Digital Trails   Dave King   1 5 10   Part 2   D3Digital Trails   Dave King   1 5 10   Part 2   D3
Digital Trails Dave King 1 5 10 Part 2 D3
 
Projection Multi Scale Hashing Keyword Search in Multidimensional Datasets
Projection Multi Scale Hashing Keyword Search in Multidimensional DatasetsProjection Multi Scale Hashing Keyword Search in Multidimensional Datasets
Projection Multi Scale Hashing Keyword Search in Multidimensional Datasets
 
“What is WeGov” - User Guide for the Phase 2 Evaluation (in English)
“What is WeGov” - User Guide for the Phase 2 Evaluation (in English)“What is WeGov” - User Guide for the Phase 2 Evaluation (in English)
“What is WeGov” - User Guide for the Phase 2 Evaluation (in English)
 
Recommendation System Using Social Networking
Recommendation System Using Social Networking Recommendation System Using Social Networking
Recommendation System Using Social Networking
 
A topology based approach twittersdlfkjsdlkfj
A topology based approach twittersdlfkjsdlkfjA topology based approach twittersdlfkjsdlkfj
A topology based approach twittersdlfkjsdlkfj
 
An Access Control Model for Collaborative Management of Shared Data in OSNS
An Access Control Model for Collaborative Management of Shared Data in OSNSAn Access Control Model for Collaborative Management of Shared Data in OSNS
An Access Control Model for Collaborative Management of Shared Data in OSNS
 
Visualization of Relationship between Social Bookmark Users
Visualization of Relationship between Social Bookmark UsersVisualization of Relationship between Social Bookmark Users
Visualization of Relationship between Social Bookmark Users
 
Social Data Mining
Social Data MiningSocial Data Mining
Social Data Mining
 
Social Media Data Mining
Social Media Data MiningSocial Media Data Mining
Social Media Data Mining
 
Information Access on Social Web
Information Access on Social WebInformation Access on Social Web
Information Access on Social Web
 

Viewers also liked

JIST2015-Computing the Semantic Similarity of Resources in DBpedia for Recomm...
JIST2015-Computing the Semantic Similarity of Resources in DBpedia for Recomm...JIST2015-Computing the Semantic Similarity of Resources in DBpedia for Recomm...
JIST2015-Computing the Semantic Similarity of Resources in DBpedia for Recomm...
GUANGYUAN PIAO
 
Data mining for causal inference: Effect of recommendations on Amazon.com
Data mining for causal inference: Effect of recommendations on Amazon.comData mining for causal inference: Effect of recommendations on Amazon.com
Data mining for causal inference: Effect of recommendations on Amazon.com
Amit Sharma
 

Viewers also liked (20)

How to survive your PhD
How to survive your PhDHow to survive your PhD
How to survive your PhD
 
SAC2016-Measuring Semantic Distance for Linked Open Data-enabled Recommender ...
SAC2016-Measuring Semantic Distance for Linked Open Data-enabled Recommender ...SAC2016-Measuring Semantic Distance for Linked Open Data-enabled Recommender ...
SAC2016-Measuring Semantic Distance for Linked Open Data-enabled Recommender ...
 
JIST2015-Computing the Semantic Similarity of Resources in DBpedia for Recomm...
JIST2015-Computing the Semantic Similarity of Resources in DBpedia for Recomm...JIST2015-Computing the Semantic Similarity of Resources in DBpedia for Recomm...
JIST2015-Computing the Semantic Similarity of Resources in DBpedia for Recomm...
 
SSSW 2013 - Feeding Recommender Systems with Linked Open Data
SSSW 2013 - Feeding Recommender Systems with Linked Open DataSSSW 2013 - Feeding Recommender Systems with Linked Open Data
SSSW 2013 - Feeding Recommender Systems with Linked Open Data
 
How to find right institution & advisor for your research
How to find right institution & advisor for your researchHow to find right institution & advisor for your research
How to find right institution & advisor for your research
 
JIST2015-data challenge
JIST2015-data challengeJIST2015-data challenge
JIST2015-data challenge
 
Growing Galway's Startup Community
Growing Galway's Startup CommunityGrowing Galway's Startup Community
Growing Galway's Startup Community
 
Making More Sense Out of Social Data
Making More Sense Out of Social DataMaking More Sense Out of Social Data
Making More Sense Out of Social Data
 
Intellectual Property: Protecting Ideas, Designs and Brands in the Real World...
Intellectual Property: Protecting Ideas, Designs and Brands in the Real World...Intellectual Property: Protecting Ideas, Designs and Brands in the Real World...
Intellectual Property: Protecting Ideas, Designs and Brands in the Real World...
 
Analyzing User Modeling on Twitter for Personalized News Recommendations
Analyzing User Modeling on Twitter for Personalized News RecommendationsAnalyzing User Modeling on Twitter for Personalized News Recommendations
Analyzing User Modeling on Twitter for Personalized News Recommendations
 
Recommender Systems and Linked Open Data
Recommender Systems and Linked Open DataRecommender Systems and Linked Open Data
Recommender Systems and Linked Open Data
 
Monitoring and Analysis of Online Communities
Monitoring and Analysis of Online CommunitiesMonitoring and Analysis of Online Communities
Monitoring and Analysis of Online Communities
 
Content Recommendation using factorisation machines ; Pycon Ireland 2016
Content Recommendation using  factorisation machines ; Pycon Ireland 2016Content Recommendation using  factorisation machines ; Pycon Ireland 2016
Content Recommendation using factorisation machines ; Pycon Ireland 2016
 
Semantics-aware Graph-based Recommender Systems exploiting Linked Open Data
Semantics-aware Graph-based Recommender Systems exploiting Linked Open DataSemantics-aware Graph-based Recommender Systems exploiting Linked Open Data
Semantics-aware Graph-based Recommender Systems exploiting Linked Open Data
 
Automatic Selection of Linked Open Data features in Graph-based Recommender S...
Automatic Selection of Linked Open Data features in Graph-based Recommender S...Automatic Selection of Linked Open Data features in Graph-based Recommender S...
Automatic Selection of Linked Open Data features in Graph-based Recommender S...
 
Innovation and Entrepreneurship: Tips, Tools and Tricks
Innovation and Entrepreneurship: Tips, Tools and TricksInnovation and Entrepreneurship: Tips, Tools and Tricks
Innovation and Entrepreneurship: Tips, Tools and Tricks
 
Data mining for causal inference: Effect of recommendations on Amazon.com
Data mining for causal inference: Effect of recommendations on Amazon.comData mining for causal inference: Effect of recommendations on Amazon.com
Data mining for causal inference: Effect of recommendations on Amazon.com
 
도서관 Linked Open Data의 필요성
도서관 Linked Open Data의 필요성도서관 Linked Open Data의 필요성
도서관 Linked Open Data의 필요성
 
Steffen Rendle, Research Scientist, Google at MLconf SF
Steffen Rendle, Research Scientist, Google at MLconf SFSteffen Rendle, Research Scientist, Google at MLconf SF
Steffen Rendle, Research Scientist, Google at MLconf SF
 
Photogallery IIS Donmilani
Photogallery IIS DonmilaniPhotogallery IIS Donmilani
Photogallery IIS Donmilani
 

Similar to EKAW2016 - Interest Representation, Enrichment, Dynamics, and Propagation: A Study of the Synergetic Effect of Different User Modeling Dimensions for Personalized Recommendations on Twitter

Extracting, Mining and Predicting Users’ Interests from Social Media
Extracting, Mining and Predicting Users’ Interests from Social MediaExtracting, Mining and Predicting Users’ Interests from Social Media
Extracting, Mining and Predicting Users’ Interests from Social Media
Fattane Zarrinkalam
 
One does not simply crowdsource the Semantic Web: 10 years with people, URIs,...
One does not simply crowdsource the Semantic Web: 10 years with people, URIs,...One does not simply crowdsource the Semantic Web: 10 years with people, URIs,...
One does not simply crowdsource the Semantic Web: 10 years with people, URIs,...
Elena Simperl
 
20120622 web sci12-won-marc smith-semantic and social network analysis of …
20120622 web sci12-won-marc smith-semantic and social network analysis of …20120622 web sci12-won-marc smith-semantic and social network analysis of …
20120622 web sci12-won-marc smith-semantic and social network analysis of …
Marc Smith
 
Community analysis using graph representation learning on social networks
Community analysis using graph representation learning on social networksCommunity analysis using graph representation learning on social networks
Community analysis using graph representation learning on social networks
Marco Brambilla
 

Similar to EKAW2016 - Interest Representation, Enrichment, Dynamics, and Propagation: A Study of the Synergetic Effect of Different User Modeling Dimensions for Personalized Recommendations on Twitter (20)

Extracting, Mining and Predicting Users’ Interests from Social Media
Extracting, Mining and Predicting Users’ Interests from Social MediaExtracting, Mining and Predicting Users’ Interests from Social Media
Extracting, Mining and Predicting Users’ Interests from Social Media
 
Profiling User Interests on the Social Semantic Web
Profiling User Interests on the Social Semantic WebProfiling User Interests on the Social Semantic Web
Profiling User Interests on the Social Semantic Web
 
Exploring Generative Models of Tripartite Graphs for Recommendation in Social...
Exploring Generative Models of Tripartite Graphs for Recommendation in Social...Exploring Generative Models of Tripartite Graphs for Recommendation in Social...
Exploring Generative Models of Tripartite Graphs for Recommendation in Social...
 
Overview of the Research in Wimmics 2018
Overview of the Research in Wimmics 2018Overview of the Research in Wimmics 2018
Overview of the Research in Wimmics 2018
 
Anatomy of Social Networks, a guide for social media strategists
Anatomy of Social Networks, a guide for social media strategistsAnatomy of Social Networks, a guide for social media strategists
Anatomy of Social Networks, a guide for social media strategists
 
Exploration & Promotion: Implementation Strategies of Corporate Social Software
Exploration & Promotion: Implementation Strategies of Corporate Social SoftwareExploration & Promotion: Implementation Strategies of Corporate Social Software
Exploration & Promotion: Implementation Strategies of Corporate Social Software
 
Web 2.0 Messaging Tools for Knowledge Management? Exploring the Potentials of...
Web 2.0 Messaging Tools for Knowledge Management? Exploring the Potentials of...Web 2.0 Messaging Tools for Knowledge Management? Exploring the Potentials of...
Web 2.0 Messaging Tools for Knowledge Management? Exploring the Potentials of...
 
GIJC19 - NodeXL Tutorial - Session 1
GIJC19 - NodeXL Tutorial - Session 1GIJC19 - NodeXL Tutorial - Session 1
GIJC19 - NodeXL Tutorial - Session 1
 
Social Friend Overlying Communities Based on Social Network Context
Social Friend Overlying Communities Based on Social Network ContextSocial Friend Overlying Communities Based on Social Network Context
Social Friend Overlying Communities Based on Social Network Context
 
Final PhD defense presentation
Final PhD defense presentationFinal PhD defense presentation
Final PhD defense presentation
 
Q046049397
Q046049397Q046049397
Q046049397
 
One does not simply crowdsource the Semantic Web: 10 years with people, URIs,...
One does not simply crowdsource the Semantic Web: 10 years with people, URIs,...One does not simply crowdsource the Semantic Web: 10 years with people, URIs,...
One does not simply crowdsource the Semantic Web: 10 years with people, URIs,...
 
20120622 web sci12-won-marc smith-semantic and social network analysis of …
20120622 web sci12-won-marc smith-semantic and social network analysis of …20120622 web sci12-won-marc smith-semantic and social network analysis of …
20120622 web sci12-won-marc smith-semantic and social network analysis of …
 
Community analysis using graph representation learning on social networks
Community analysis using graph representation learning on social networksCommunity analysis using graph representation learning on social networks
Community analysis using graph representation learning on social networks
 
Who are the top influencers and what characterizes them?
Who are the top influencers and what characterizes them?Who are the top influencers and what characterizes them?
Who are the top influencers and what characterizes them?
 
Leveraging Graph Neural Networks for User Profiling: Recent Advances and Open...
Leveraging Graph Neural Networks for User Profiling: Recent Advances and Open...Leveraging Graph Neural Networks for User Profiling: Recent Advances and Open...
Leveraging Graph Neural Networks for User Profiling: Recent Advances and Open...
 
Benoit Visual Only Retrieval
Benoit Visual Only RetrievalBenoit Visual Only Retrieval
Benoit Visual Only Retrieval
 
ICSME 2016 keynote: An ecosystemic and socio-technical view on software maint...
ICSME 2016 keynote: An ecosystemic and socio-technical view on software maint...ICSME 2016 keynote: An ecosystemic and socio-technical view on software maint...
ICSME 2016 keynote: An ecosystemic and socio-technical view on software maint...
 
Tutorial on User Profiling with Graph Neural Networks and Related Beyond-Acc...
Tutorial on User Profiling with Graph Neural Networks  and Related Beyond-Acc...Tutorial on User Profiling with Graph Neural Networks  and Related Beyond-Acc...
Tutorial on User Profiling with Graph Neural Networks and Related Beyond-Acc...
 
Jx2517481755
Jx2517481755Jx2517481755
Jx2517481755
 

More from GUANGYUAN PIAO

A Study of the Similarities of Entity Embeddings Learned from Different Aspec...
A Study of the Similarities of Entity Embeddings Learned from Different Aspec...A Study of the Similarities of Entity Embeddings Learned from Different Aspec...
A Study of the Similarities of Entity Embeddings Learned from Different Aspec...
GUANGYUAN PIAO
 
WISE2017 - Factorization Machines Leveraging Lightweight Linked Open Data-ena...
WISE2017 - Factorization Machines Leveraging Lightweight Linked Open Data-ena...WISE2017 - Factorization Machines Leveraging Lightweight Linked Open Data-ena...
WISE2017 - Factorization Machines Leveraging Lightweight Linked Open Data-ena...
GUANGYUAN PIAO
 

More from GUANGYUAN PIAO (11)

Env2Vec: Accelerating VNF Testing with Deep Learning
Env2Vec: Accelerating VNF Testing with Deep LearningEnv2Vec: Accelerating VNF Testing with Deep Learning
Env2Vec: Accelerating VNF Testing with Deep Learning
 
Domain-Aware Sentiment Classification with GRUs and CNNs
Domain-Aware Sentiment Classification with GRUs and CNNsDomain-Aware Sentiment Classification with GRUs and CNNs
Domain-Aware Sentiment Classification with GRUs and CNNs
 
A Study of the Similarities of Entity Embeddings Learned from Different Aspec...
A Study of the Similarities of Entity Embeddings Learned from Different Aspec...A Study of the Similarities of Entity Embeddings Learned from Different Aspec...
A Study of the Similarities of Entity Embeddings Learned from Different Aspec...
 
Retweet Prediction with Attention-based Deep Neural Network
Retweet Prediction with Attention-based Deep Neural NetworkRetweet Prediction with Attention-based Deep Neural Network
Retweet Prediction with Attention-based Deep Neural Network
 
WISE2017 - Factorization Machines Leveraging Lightweight Linked Open Data-ena...
WISE2017 - Factorization Machines Leveraging Lightweight Linked Open Data-ena...WISE2017 - Factorization Machines Leveraging Lightweight Linked Open Data-ena...
WISE2017 - Factorization Machines Leveraging Lightweight Linked Open Data-ena...
 
Hypertext2017-Leveraging Followee List Memberships for Inferring User Interes...
Hypertext2017-Leveraging Followee List Memberships for Inferring User Interes...Hypertext2017-Leveraging Followee List Memberships for Inferring User Interes...
Hypertext2017-Leveraging Followee List Memberships for Inferring User Interes...
 
RDFa Basics
RDFa BasicsRDFa Basics
RDFa Basics
 
Owl 2.0 Overview
Owl 2.0 OverviewOwl 2.0 Overview
Owl 2.0 Overview
 
OWL 2.0 Primer Part01
OWL 2.0 Primer Part01OWL 2.0 Primer Part01
OWL 2.0 Primer Part01
 
OWL2.0 Primer Part02
OWL2.0 Primer Part02OWL2.0 Primer Part02
OWL2.0 Primer Part02
 
Hdd industry
Hdd industryHdd industry
Hdd industry
 

Recently uploaded

Sociocosmos empowers you to go trendy on social media with a few clicks..pdf
Sociocosmos empowers you to go trendy on social media with a few clicks..pdfSociocosmos empowers you to go trendy on social media with a few clicks..pdf
Sociocosmos empowers you to go trendy on social media with a few clicks..pdf
SocioCosmos
 
Jual Obat Aborsi Kudus ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan Cy...
Jual Obat Aborsi Kudus ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan Cy...Jual Obat Aborsi Kudus ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan Cy...
Jual Obat Aborsi Kudus ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan Cy...
ZurliaSoop
 
+971565801893>> ORIGINAL CYTOTEC ABORTION PILLS FOR SALE IN DUBAI AND ABUDHABI<<
+971565801893>> ORIGINAL CYTOTEC ABORTION PILLS FOR SALE IN DUBAI AND ABUDHABI<<+971565801893>> ORIGINAL CYTOTEC ABORTION PILLS FOR SALE IN DUBAI AND ABUDHABI<<
+971565801893>> ORIGINAL CYTOTEC ABORTION PILLS FOR SALE IN DUBAI AND ABUDHABI<<
Health
 
JUAL PILL CYTOTEC PALOPO SULAWESI 087776558899 OBAT PENGGUGUR KANDUNGAN PALOP...
JUAL PILL CYTOTEC PALOPO SULAWESI 087776558899 OBAT PENGGUGUR KANDUNGAN PALOP...JUAL PILL CYTOTEC PALOPO SULAWESI 087776558899 OBAT PENGGUGUR KANDUNGAN PALOP...
JUAL PILL CYTOTEC PALOPO SULAWESI 087776558899 OBAT PENGGUGUR KANDUNGAN PALOP...
Cara Menggugurkan Kandungan 087776558899
 
Capstone slidedeck for my capstone project part 2.pdf
Capstone slidedeck for my capstone project part 2.pdfCapstone slidedeck for my capstone project part 2.pdf
Capstone slidedeck for my capstone project part 2.pdf
eliklein8
 
Jual Obat Aborsi Palu ( Taiwan No.1 ) 085657271886 Obat Penggugur Kandungan C...
Jual Obat Aborsi Palu ( Taiwan No.1 ) 085657271886 Obat Penggugur Kandungan C...Jual Obat Aborsi Palu ( Taiwan No.1 ) 085657271886 Obat Penggugur Kandungan C...
Jual Obat Aborsi Palu ( Taiwan No.1 ) 085657271886 Obat Penggugur Kandungan C...
ZurliaSoop
 
💊💊 OBAT PENGGUGUR KANDUNGAN SEMARANG 087776-558899 ABORSI KLINIK SEMARANG
💊💊 OBAT PENGGUGUR KANDUNGAN SEMARANG 087776-558899 ABORSI KLINIK SEMARANG💊💊 OBAT PENGGUGUR KANDUNGAN SEMARANG 087776-558899 ABORSI KLINIK SEMARANG
💊💊 OBAT PENGGUGUR KANDUNGAN SEMARANG 087776-558899 ABORSI KLINIK SEMARANG
Cara Menggugurkan Kandungan 087776558899
 
Meet Incall & Out Escort Service in D -9634446618 | #escort Service in GTB Na...
Meet Incall & Out Escort Service in D -9634446618 | #escort Service in GTB Na...Meet Incall & Out Escort Service in D -9634446618 | #escort Service in GTB Na...
Meet Incall & Out Escort Service in D -9634446618 | #escort Service in GTB Na...
Heena Escort Service
 
Capstone slidedeck for my capstone final edition.pdf
Capstone slidedeck for my capstone final edition.pdfCapstone slidedeck for my capstone final edition.pdf
Capstone slidedeck for my capstone final edition.pdf
eliklein8
 

Recently uploaded (17)

Sociocosmos empowers you to go trendy on social media with a few clicks..pdf
Sociocosmos empowers you to go trendy on social media with a few clicks..pdfSociocosmos empowers you to go trendy on social media with a few clicks..pdf
Sociocosmos empowers you to go trendy on social media with a few clicks..pdf
 
BVG BEACH CLEANING PROJECTS- ORISSA , ANDAMAN, PORT BLAIR
BVG BEACH CLEANING PROJECTS- ORISSA , ANDAMAN, PORT BLAIRBVG BEACH CLEANING PROJECTS- ORISSA , ANDAMAN, PORT BLAIR
BVG BEACH CLEANING PROJECTS- ORISSA , ANDAMAN, PORT BLAIR
 
Jual Obat Aborsi Kudus ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan Cy...
Jual Obat Aborsi Kudus ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan Cy...Jual Obat Aborsi Kudus ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan Cy...
Jual Obat Aborsi Kudus ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan Cy...
 
Enhancing Consumer Trust Through Strategic Content Marketing
Enhancing Consumer Trust Through Strategic Content MarketingEnhancing Consumer Trust Through Strategic Content Marketing
Enhancing Consumer Trust Through Strategic Content Marketing
 
Capstone slide deck on the TikTok revolution
Capstone slide deck on the TikTok revolutionCapstone slide deck on the TikTok revolution
Capstone slide deck on the TikTok revolution
 
+971565801893>> ORIGINAL CYTOTEC ABORTION PILLS FOR SALE IN DUBAI AND ABUDHABI<<
+971565801893>> ORIGINAL CYTOTEC ABORTION PILLS FOR SALE IN DUBAI AND ABUDHABI<<+971565801893>> ORIGINAL CYTOTEC ABORTION PILLS FOR SALE IN DUBAI AND ABUDHABI<<
+971565801893>> ORIGINAL CYTOTEC ABORTION PILLS FOR SALE IN DUBAI AND ABUDHABI<<
 
Content strategy : Content empire and cash in
Content strategy : Content empire and cash inContent strategy : Content empire and cash in
Content strategy : Content empire and cash in
 
The Butterfly Effect
The Butterfly EffectThe Butterfly Effect
The Butterfly Effect
 
Marketing Plan - Social Media. The Sparks Foundation
Marketing Plan -  Social Media. The Sparks FoundationMarketing Plan -  Social Media. The Sparks Foundation
Marketing Plan - Social Media. The Sparks Foundation
 
JUAL PILL CYTOTEC PALOPO SULAWESI 087776558899 OBAT PENGGUGUR KANDUNGAN PALOP...
JUAL PILL CYTOTEC PALOPO SULAWESI 087776558899 OBAT PENGGUGUR KANDUNGAN PALOP...JUAL PILL CYTOTEC PALOPO SULAWESI 087776558899 OBAT PENGGUGUR KANDUNGAN PALOP...
JUAL PILL CYTOTEC PALOPO SULAWESI 087776558899 OBAT PENGGUGUR KANDUNGAN PALOP...
 
SEO Expert in USA - 5 Ways to Improve Your Local Ranking - Macaw Digital.pdf
SEO Expert in USA - 5 Ways to Improve Your Local Ranking - Macaw Digital.pdfSEO Expert in USA - 5 Ways to Improve Your Local Ranking - Macaw Digital.pdf
SEO Expert in USA - 5 Ways to Improve Your Local Ranking - Macaw Digital.pdf
 
Capstone slidedeck for my capstone project part 2.pdf
Capstone slidedeck for my capstone project part 2.pdfCapstone slidedeck for my capstone project part 2.pdf
Capstone slidedeck for my capstone project part 2.pdf
 
Jual Obat Aborsi Palu ( Taiwan No.1 ) 085657271886 Obat Penggugur Kandungan C...
Jual Obat Aborsi Palu ( Taiwan No.1 ) 085657271886 Obat Penggugur Kandungan C...Jual Obat Aborsi Palu ( Taiwan No.1 ) 085657271886 Obat Penggugur Kandungan C...
Jual Obat Aborsi Palu ( Taiwan No.1 ) 085657271886 Obat Penggugur Kandungan C...
 
💊💊 OBAT PENGGUGUR KANDUNGAN SEMARANG 087776-558899 ABORSI KLINIK SEMARANG
💊💊 OBAT PENGGUGUR KANDUNGAN SEMARANG 087776-558899 ABORSI KLINIK SEMARANG💊💊 OBAT PENGGUGUR KANDUNGAN SEMARANG 087776-558899 ABORSI KLINIK SEMARANG
💊💊 OBAT PENGGUGUR KANDUNGAN SEMARANG 087776-558899 ABORSI KLINIK SEMARANG
 
Meet Incall & Out Escort Service in D -9634446618 | #escort Service in GTB Na...
Meet Incall & Out Escort Service in D -9634446618 | #escort Service in GTB Na...Meet Incall & Out Escort Service in D -9634446618 | #escort Service in GTB Na...
Meet Incall & Out Escort Service in D -9634446618 | #escort Service in GTB Na...
 
Capstone slidedeck for my capstone final edition.pdf
Capstone slidedeck for my capstone final edition.pdfCapstone slidedeck for my capstone final edition.pdf
Capstone slidedeck for my capstone final edition.pdf
 
Ignite Your Online Influence: Sociocosmos - Where Social Media Magic Happens
Ignite Your Online Influence: Sociocosmos - Where Social Media Magic HappensIgnite Your Online Influence: Sociocosmos - Where Social Media Magic Happens
Ignite Your Online Influence: Sociocosmos - Where Social Media Magic Happens
 

EKAW2016 - Interest Representation, Enrichment, Dynamics, and Propagation: A Study of the Synergetic Effect of Different User Modeling Dimensions for Personalized Recommendations on Twitter

  • 1. Guangyuan Piao, John G. Breslin Unit for Social Semantics 20th International Conference on Knowledge Engineering and Knowledge Management Bologna, Italy, 19-23, November, 2016 Interest Representation, Enrichment, Dynamics, and Propagation: A Study of the Synergetic Effect of Different User Modeling Dimensions for Personalized Recommendations on Twitter
  • 2. 2 1/3 users seek medical information and over 50% users consume news on Social Networks Facebook and Twitter together generate more than 5 billion microblogs / day [SOURCE] Semantic Filtering for Social Data, Amit et al., Internet Computing’16
  • 3. Background – User Modeling content enrichment analysis & user modeling interest profile ? personalized content recommendations (How) can we infer user interest profiles that support the content recommender? 3[SOURCE] Analyzing User Modeling on Twitter for Personalized News Recommendations, UMAP’11
  • 4. 4 Background – User Modeling Dimensions representation enrichment propagation dynamics
  • 6. Bag-of-Concepts example dbpedia:The_Black_Keys (3) dbpedia:Eagles_of_Death_Metal (5) Background – User Modeling dbpedia:The_Wombats (2) Interest Frequency (IF)
  • 7. 7 Background – User Modeling Dimensions enrichment
  • 8. 8 Background – User Modeling Dimensions dynamics Assumption: user interests might change over time
  • 9. Background – User Modeling Dimensions propagation dbpedia:The_Wombats dbpedia:Indie_rockgenre dbpedia:The_Black_Keys dbc:Rock_music_duos subject
  • 10. 10 Background – User Modeling Dimensions representation enrichment propagation dynamics dimensions have been studied separately
  • 11. 11 Aim of Work representation enrichment propagation dynamics Dimensions to investigate (how) can we combine different dimensions for user modeling
  • 12. 12 User Modeling Framework user interest profiles entity extraction primitive interestsIF weighting temporal dynamics interest propagation primitive & propagated interests synset extraction optional enabled enrichment IDF weightingnormalization
  • 13. 13 Representation •  concept-based !  DBpedia concepts are extracted using Aylien API •  mixed approach (WordNet synset & concept-based) !  synsets are extracted using Degemmis’s method [UMUAI] Enrichment •  exploring embedded URL in tweets !  concepts or synsets are extracted from the content of URL Interest Representation & Enrichment
  • 14. 14 Propagation strategy using DBpedia •  category-based SP: sub-pages of the category SC: sub-categories of the category •  property-based P: property count in DBpedia graph Interest Propagation
  • 15. 15 Temporal Dynamics of User Interests Interest decay functions •  Long-term(Orlandi) [SEMANTiCS] •  Long-term(Ahmed) [SIGKDD] Long-term(Ahmedα): µ2week, µ2month, µall •  Long-term(Abel) [WebSci] µweek = µ = e -1 µmonth = µ 2 µall = µ 3
  • 16. 16 Design Space of User Modeling The design space of user modeling, spanning 2x2x2x2=16 possible user modeling strategies. Notation •  um( representation; enrichment; dynamics; semantics ) •  use “none” to denote a certain dimension is disabled !  um( synset & concept; enrichment; none; none)
  • 17. Dataset •  322 users: shared at least one link in the last two weeks •  247,676 tweets in total Experiment •  task: recommending 10 links (URLs) •  recommendation algorithm: cosine similarity(P(u), P(i)) P(i): item (link) profile using the same modeling strategy for P(u) •  ground truth links: links shared in the last two weeks •  candidate links: 15,440 links 17 Experiment Setup used for user modeling ground truth links (URLs) recommendation time
  • 18. Results with enrichment > without enrichment
  • 20. Conclusions & Future Work •  propagation helps when using concept-based representation without enrichment •  the most important dimensions : Content Enrichment & Interest Representation •  investigation of how different percentages of links affect the performance •  the best-performing strategy : um (synset & concept; enrichment; dynamics; none )
  • 21. 21 Thank you for your attention! Guangyuan Piao homepage: http://parklize.github.io e-mail: guangyuan.piao@insight-centre.org twitter: https://twitter.com/parklize slideshare: http://www.slideshare.net/parklize