SlideShare ist ein Scribd-Unternehmen logo
1 von 28
Analyzing User Modeling on Twitter for Personalized News Recommendations UMAP, Girona, July 13, 2011 Fabian Abel, QiGao, Geert-Jan Houben, Ke Tao Web Information Systems, TU Delft
The Social Web Help me to tackle the information overload!  Who is this? What are his  personal demands? How  can we make him happy? Recommend me news articles that now interest me! Help me to find interesting (social) media! Give me personalized support when I do my online training! Personalize my Web experience! Do not bother me with advertisements that are not interesting for me!
What we do: Science and Engineering for the Personal Web domains: news  social mediacultural heritage  public datae-learning Personalized Recommendations Personalized Search Adaptive Systems  Analysis and  User Modeling Semantic Enrichment, Linkage and Alignment user/usage data Social Web
User Modeling Challenge Personalized News Recommender I want my personalized news recommendations! Profile Analysis and  User Modeling ? (How) can we infer a Twitter-based user profile that supports the news recommender? Semantic Enrichment, Linkage and Alignment
1. Temporal Constraints time period temporal patterns hashtag-based entity-based topic-based 2. Profile Type tweet-based further enrichment 3. Semantic Enrichment concept frequency 4. Weighting Scheme User Modeling Framework Building Blocks for generating valuable user profiles
User Modeling Building Blocks 1. Temporal Constraints (a)  time period 1. Which tweets of the user should be analyzed? ? (b) temporal patterns Profile? concept   weight end start weekends Morning: Afternoon: Night: time June 27 July 4 July 11
User Modeling Building Blocks 1. Temporal Constraints Francesca  Schiavone T Sport 2. Profile Type Francesca Schiavone won French Open #fo2010 Francesca Schiavone French Open ? #fo2010 Profile? concept   weight # hashtag-based entity-based French Open T topic-based # fo2010 2. What type of concepts should represent “interests”? time June 27 July 4 July 11
User Modeling Building Blocks 1. Temporal Constraints (a) tweet-based Francesca  Schiavone 2. Profile Type Francesca wins French Open Thirty in women's tennis is primordially old, an age when agility and desire recedes as the … Francesca Schiavone Francesca Schiavone won! http://bit.ly/2f4t7a 3. Semantic Enrichment Profile? concept   weight French Open Tennis French  Open (b) further enrichment Tennis 3. Further enrich the semantics of tweets?
User Modeling Building Blocks 1. Temporal Constraints 2. Profile Type ? Francesca Schiavone 4 4. How to weight the concepts? 3. Semantic Enrichment Profile?          concept          weight 3 French Open 6 Tennis Concept frequency 4. Weighting Scheme weight(FrancescaSchiavone) weight(French Open) weight(Tennis) time June 27 July 4 July 11
User Modeling Building Blocks 1. Temporal Constraints time period temporal patterns hashtag-based entity-based topic-based 2. Profile Type tweet-based further enrichment 3. Semantic Enrichment concept frequency 4. Weighting Scheme
1. Temporal Constraints time period temporal patterns hashtag-based entity-based topic-based 2. Profile Type tweet-based further enrichment 3. Semantic Enrichment concept frequency 4. Weighting Scheme Analysis How do the user modeling building blocks impact the (temporal) characteristics of Twitter-based user profiles?
Dataset more than:  20,000 Twitter users 2 months 10,000,000 WikiLeaks founder, Julian Assange, under arrest in London tweets 75,000 news articles time Dec 15 Jan 15 Nov 15
Size of user profiles Profile Type ~5% of the users do not make use of hashtags hashtag-based profiles are empty entity-based Entity-based user modeling succeeds for 100% of the users topic-based hashtag-based
Semantic Enrichment More distinct topics per profile further enrichment (e.g. exploiting links) further enrichment (e.g. exploiting links) More distinct entities per profile Exploiting external resources allows for significantly richer user profiles (quantitatively) Tweet-based Tweet-based entity-based user profiles topic-based user profiles Impact of Semantic Enrichment
User Profiles change over time Temporal Constraints Hashtag-based profiles change stronger than entity-based and topic-based profiles d1-distance: difference between current profile and past profile Example: # old new ? music The older the profile the more it differs from the current profile tennis football T
Temporal patterns of user profiles Temporal Constraints 2 1. Weekend profiles differ significantly from weekday profiles 2. the difference is stronger than between day and night profiles  weekday vs. weekend profiles d1(pweekday, pweekend) day vs. night profiles d1(pday, pnight) topic-based user profiles
Observations Semantic enrichment allows for richer user profiles Profiles change over time: fresh profiles seem to better reflect current user demands Temporal patterns: weekend profiles differ significantly form weekday profiles
1. Temporal Constraints time period temporal patterns hashtag-based entity-based topic-based 2. Profile Type tweet-based further enrichment 3. Semantic Enrichment concept frequency 4. Weighting Scheme Evaluation How do the user modeling building blocks impact the quality of Twitter-based profiles for personalized news recommendations? And can we benefit from the findings of the analysis to improve recommendations?
Twitter-based Profiles for Personalization Task: Recommending news articles (= tweets with URLs pointing to news articles) Recommender algorithm: cosine similarity between user profile and tweets Ground truth: re-tweets of users Candidate items: news article tweets posted during evaluation period 5.5 relevant tweets per user 5529 candidate news articles Recommendations = ? P(u)= ? time 1 week
Profile Type Overview: Performance of User Modeling strategies Topic-based strategy improves S@10 significantly # Entity-based strategy improves the recommendation quality significantly (MRR & S@10) T
Impact of Semantic Enrichment Semantic Enrichment T Tweet-based Further enrichment Further semantic enrichment (exploiting links) improves the quality of the Twitter-based profiles!
Impact of temporal characteristics Temporal Constraints startcomplete startfresh end Adapting to temporal context helps? Selection of temporal constraints depends on type of user profile.  ,[object Object],adapting to temporal    context is beneficial ,[object Object],  long-term profiles    perform better Recommendations = ? yes T time no complete: 2 months fresh: 2 weeks end start yes weekends T Recommendations = ? no time
Conclusions and Future Work What we did: Twitter-based User Modeling for Recommending News Articles Analysis:  Semantic enrichment results in richer user profiles (quantitative) User interest profiles change over time (hashtag-based stronger than others) Weekend/weekday pattern more significant than day/night pattern Evaluation: Best user modeling strategy: Entity-based > topic-based > hashtag-based  Semantic enrichment improves recommendation quality Adapting to temporal context helps for topic-based strategy Future work: for what type of personalization tasks can we exploit what type of Twitter profiles?
Thank you! Fabian Abel, QiGao, Geert-Jan Houben, Ke Tao Twitter: @persweb http://persweb.org/  http://u-sem.org/
Research Questions What type of user interest profiles can we infer from Twitter activities?  Can we exploit Twitter-based profiles for personalizing users’ Social Web experience? Personalized news  recommendations in time: interest twitter Good Morning! #tooearly ? ? I like this http://bit.ly/5d4r2t Why do people now blame Julian Assange? time time Ajax deserves it! #sport
Analyzing Twitter-based Profiles for Personalized News Recommendations (in time) News Recommendations in time: Interests: Tennis Football Francesca Schiavone is great! Thirty in women's tennis is primordially old, an age when agility and desire recedes as the next wave of younger/faster/stronger players encroaches. It's uncommon for any athlete to have a breakthrough season at 30, but it's exceedingly… Ajax gives  De Jong a break Ajax manager Frank de Boer announced that… Personalized news recommendations interest interest I like this http://bit.ly/4Gfd2 Analysis and  User Modeling time time topic:Tennis Semantic Enrichment, Linkage, Alignment dbpedia:Schiavone Nice, thank you! oc:Sports event:FrenchOpen tweets
User Modeling Challenge Wednesday, July 13th 2011, 9:10am Personalized news recommender Profile? I want my personalized news recommendations! ? (How) can we infer a Twitter-based user profile that supports the news recommender?
Bob tweets… Why do people now blame Julian Assange? Ajax deserves it! #sport Good Morning! #tooearly I like this http://bit.ly/5d4r2t time Fr, 6am Fr, 3pm Fr, 8pm Sa, 5pm People publish more than 60 million tweets per day!

Weitere ähnliche Inhalte

Ähnlich wie UMAP 2011: Analyzing User Modeling on Twitter for Personalized News Recommendations

Using Social Media in Behavioral Healthcare
Using Social Media in Behavioral HealthcareUsing Social Media in Behavioral Healthcare
Using Social Media in Behavioral HealthcareJennifer Iacovelli
 
Workshop key actions to support and share your TEL research
Workshop key actions to support and share your TEL researchWorkshop key actions to support and share your TEL research
Workshop key actions to support and share your TEL researchMikhail Fominykh
 
Social media management Oct 2016
Social media management   Oct 2016Social media management   Oct 2016
Social media management Oct 2016DigiArabs
 
How to Build and Sustain Buzz Online
How to Build and Sustain Buzz OnlineHow to Build and Sustain Buzz Online
How to Build and Sustain Buzz OnlineLeslie Bradshaw
 
Content Sharing for Researchers
Content Sharing for ResearchersContent Sharing for Researchers
Content Sharing for ResearchersNikki Martinez
 
Cosmic Ethical IT Presents : CIPD Presentation
Cosmic Ethical IT Presents : CIPD PresentationCosmic Ethical IT Presents : CIPD Presentation
Cosmic Ethical IT Presents : CIPD Presentationcosmicuk
 
Social media for coaches
Social media for coachesSocial media for coaches
Social media for coachesJörg Probst
 
Making your research social: using social media as a pathway for sharing rese...
Making your research social: using social media as a pathway for sharing rese...Making your research social: using social media as a pathway for sharing rese...
Making your research social: using social media as a pathway for sharing rese...Simone Staiger-Rivas
 
Academic online profile development - NARTI Workshop - Salford Business School
Academic online profile development - NARTI Workshop - Salford Business SchoolAcademic online profile development - NARTI Workshop - Salford Business School
Academic online profile development - NARTI Workshop - Salford Business SchoolSalford Business School
 
A Baseline Based Deep Learning Approach of Live Tweets
A Baseline Based Deep Learning Approach of Live TweetsA Baseline Based Deep Learning Approach of Live Tweets
A Baseline Based Deep Learning Approach of Live Tweetsijtsrd
 
Ismte2011 social media
Ismte2011 social mediaIsmte2011 social media
Ismte2011 social mediabobsumnerjr
 
21st Century Research Profiles
21st Century Research Profiles21st Century Research Profiles
21st Century Research ProfilesEmma Gillaspy
 
The new literacy: strategies, tools and techniques for incorporating new media
The new literacy: strategies, tools and techniques for incorporating new media The new literacy: strategies, tools and techniques for incorporating new media
The new literacy: strategies, tools and techniques for incorporating new media Marco Campana
 
Using twitter and facebook in extension programming
Using twitter and facebook in extension programmingUsing twitter and facebook in extension programming
Using twitter and facebook in extension programmingSteven Newman
 
Introduction to Social Media and Public Relations (Unitarian Universalist Ass...
Introduction to Social Media and Public Relations (Unitarian Universalist Ass...Introduction to Social Media and Public Relations (Unitarian Universalist Ass...
Introduction to Social Media and Public Relations (Unitarian Universalist Ass...Unitarian Universalist Association
 
Social Superheroes - Behind the Scenes of a Massive Marketing Campaign
Social Superheroes - Behind the Scenes of a Massive Marketing CampaignSocial Superheroes - Behind the Scenes of a Massive Marketing Campaign
Social Superheroes - Behind the Scenes of a Massive Marketing CampaignHubSpot
 
#WordPower for Social Media
#WordPower for Social Media#WordPower for Social Media
#WordPower for Social MediaRichie Escovedo
 
Social and open journalism v3
Social and open journalism v3Social and open journalism v3
Social and open journalism v3Chris Gordon
 
Coordinating a social media presence for the library
Coordinating a social media presence for the libraryCoordinating a social media presence for the library
Coordinating a social media presence for the librarySarah Houghton
 

Ähnlich wie UMAP 2011: Analyzing User Modeling on Twitter for Personalized News Recommendations (20)

Using Social Media in Behavioral Healthcare
Using Social Media in Behavioral HealthcareUsing Social Media in Behavioral Healthcare
Using Social Media in Behavioral Healthcare
 
Workshop key actions to support and share your TEL research
Workshop key actions to support and share your TEL researchWorkshop key actions to support and share your TEL research
Workshop key actions to support and share your TEL research
 
Social media management Oct 2016
Social media management   Oct 2016Social media management   Oct 2016
Social media management Oct 2016
 
How to Build and Sustain Buzz Online
How to Build and Sustain Buzz OnlineHow to Build and Sustain Buzz Online
How to Build and Sustain Buzz Online
 
Content Sharing for Researchers
Content Sharing for ResearchersContent Sharing for Researchers
Content Sharing for Researchers
 
Cosmic Ethical IT Presents : CIPD Presentation
Cosmic Ethical IT Presents : CIPD PresentationCosmic Ethical IT Presents : CIPD Presentation
Cosmic Ethical IT Presents : CIPD Presentation
 
Social media for coaches
Social media for coachesSocial media for coaches
Social media for coaches
 
Making your research social: using social media as a pathway for sharing rese...
Making your research social: using social media as a pathway for sharing rese...Making your research social: using social media as a pathway for sharing rese...
Making your research social: using social media as a pathway for sharing rese...
 
Academic online profile development - NARTI Workshop - Salford Business School
Academic online profile development - NARTI Workshop - Salford Business SchoolAcademic online profile development - NARTI Workshop - Salford Business School
Academic online profile development - NARTI Workshop - Salford Business School
 
A Baseline Based Deep Learning Approach of Live Tweets
A Baseline Based Deep Learning Approach of Live TweetsA Baseline Based Deep Learning Approach of Live Tweets
A Baseline Based Deep Learning Approach of Live Tweets
 
Ismte2011 social media
Ismte2011 social mediaIsmte2011 social media
Ismte2011 social media
 
21st Century Research Profiles
21st Century Research Profiles21st Century Research Profiles
21st Century Research Profiles
 
The new literacy: strategies, tools and techniques for incorporating new media
The new literacy: strategies, tools and techniques for incorporating new media The new literacy: strategies, tools and techniques for incorporating new media
The new literacy: strategies, tools and techniques for incorporating new media
 
Using twitter and facebook in extension programming
Using twitter and facebook in extension programmingUsing twitter and facebook in extension programming
Using twitter and facebook in extension programming
 
Introduction to Social Media and Public Relations (Unitarian Universalist Ass...
Introduction to Social Media and Public Relations (Unitarian Universalist Ass...Introduction to Social Media and Public Relations (Unitarian Universalist Ass...
Introduction to Social Media and Public Relations (Unitarian Universalist Ass...
 
Hands-On Social Media Strategy
Hands-On Social Media StrategyHands-On Social Media Strategy
Hands-On Social Media Strategy
 
Social Superheroes - Behind the Scenes of a Massive Marketing Campaign
Social Superheroes - Behind the Scenes of a Massive Marketing CampaignSocial Superheroes - Behind the Scenes of a Massive Marketing Campaign
Social Superheroes - Behind the Scenes of a Massive Marketing Campaign
 
#WordPower for Social Media
#WordPower for Social Media#WordPower for Social Media
#WordPower for Social Media
 
Social and open journalism v3
Social and open journalism v3Social and open journalism v3
Social and open journalism v3
 
Coordinating a social media presence for the library
Coordinating a social media presence for the libraryCoordinating a social media presence for the library
Coordinating a social media presence for the library
 

Mehr von Web Information Systems, TU Delft

Twitter, Twinder, Twitcident: Filtering and Search in Social Web Streams
Twitter, Twinder, Twitcident: Filtering and Search in Social Web StreamsTwitter, Twinder, Twitcident: Filtering and Search in Social Web Streams
Twitter, Twinder, Twitcident: Filtering and Search in Social Web StreamsWeb Information Systems, TU Delft
 
GeniUS: Generic User Modeling Library for the Social Semantic Web
GeniUS: Generic User Modeling Library for the Social Semantic WebGeniUS: Generic User Modeling Library for the Social Semantic Web
GeniUS: Generic User Modeling Library for the Social Semantic WebWeb Information Systems, TU Delft
 
Generating Resource Profiles by Exploiting the Context of Social Annotations
Generating Resource Profiles by Exploiting the Context of Social AnnotationsGenerating Resource Profiles by Exploiting the Context of Social Annotations
Generating Resource Profiles by Exploiting the Context of Social AnnotationsWeb Information Systems, TU Delft
 
Leveraging the Semantics of Tweets for Adaptive Faceted Search on Twitter
Leveraging the Semantics of Tweets for Adaptive Faceted Search on TwitterLeveraging the Semantics of Tweets for Adaptive Faceted Search on Twitter
Leveraging the Semantics of Tweets for Adaptive Faceted Search on TwitterWeb Information Systems, TU Delft
 
UMAP 2011: Analyzing User Modeling on Twitter for Personalized News Recommend...
UMAP 2011: Analyzing User Modeling on Twitter for Personalized News Recommend...UMAP 2011: Analyzing User Modeling on Twitter for Personalized News Recommend...
UMAP 2011: Analyzing User Modeling on Twitter for Personalized News Recommend...Web Information Systems, TU Delft
 

Mehr von Web Information Systems, TU Delft (8)

Twitter, Twinder, Twitcident: Filtering and Search in Social Web Streams
Twitter, Twinder, Twitcident: Filtering and Search in Social Web StreamsTwitter, Twinder, Twitcident: Filtering and Search in Social Web Streams
Twitter, Twinder, Twitcident: Filtering and Search in Social Web Streams
 
GeniUS: Generic User Modeling Library for the Social Semantic Web
GeniUS: Generic User Modeling Library for the Social Semantic WebGeniUS: Generic User Modeling Library for the Social Semantic Web
GeniUS: Generic User Modeling Library for the Social Semantic Web
 
Generating Resource Profiles by Exploiting the Context of Social Annotations
Generating Resource Profiles by Exploiting the Context of Social AnnotationsGenerating Resource Profiles by Exploiting the Context of Social Annotations
Generating Resource Profiles by Exploiting the Context of Social Annotations
 
Leveraging the Semantics of Tweets for Adaptive Faceted Search on Twitter
Leveraging the Semantics of Tweets for Adaptive Faceted Search on TwitterLeveraging the Semantics of Tweets for Adaptive Faceted Search on Twitter
Leveraging the Semantics of Tweets for Adaptive Faceted Search on Twitter
 
Payday on the Social Semantic Web
Payday on the Social Semantic WebPayday on the Social Semantic Web
Payday on the Social Semantic Web
 
UMAP 2011: Analyzing User Modeling on Twitter for Personalized News Recommend...
UMAP 2011: Analyzing User Modeling on Twitter for Personalized News Recommend...UMAP 2011: Analyzing User Modeling on Twitter for Personalized News Recommend...
UMAP 2011: Analyzing User Modeling on Twitter for Personalized News Recommend...
 
Analyzing Cross-System User Modeling on the Social Web
Analyzing Cross-System User Modeling on the Social WebAnalyzing Cross-System User Modeling on the Social Web
Analyzing Cross-System User Modeling on the Social Web
 
Learning Semantic Relationships between Entities in Twitter
Learning Semantic Relationships between Entities in TwitterLearning Semantic Relationships between Entities in Twitter
Learning Semantic Relationships between Entities in Twitter
 

Kürzlich hochgeladen

08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEarley Information Science
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?Igalia
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessPixlogix Infotech
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsJoaquim Jorge
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 

Kürzlich hochgeladen (20)

08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptxEIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
EIS-Webinar-Prompt-Knowledge-Eng-2024-04-08.pptx
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Advantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your BusinessAdvantages of Hiring UIUX Design Service Providers for Your Business
Advantages of Hiring UIUX Design Service Providers for Your Business
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 

UMAP 2011: Analyzing User Modeling on Twitter for Personalized News Recommendations

  • 1. Analyzing User Modeling on Twitter for Personalized News Recommendations UMAP, Girona, July 13, 2011 Fabian Abel, QiGao, Geert-Jan Houben, Ke Tao Web Information Systems, TU Delft
  • 2. The Social Web Help me to tackle the information overload! Who is this? What are his personal demands? How can we make him happy? Recommend me news articles that now interest me! Help me to find interesting (social) media! Give me personalized support when I do my online training! Personalize my Web experience! Do not bother me with advertisements that are not interesting for me!
  • 3. What we do: Science and Engineering for the Personal Web domains: news social mediacultural heritage public datae-learning Personalized Recommendations Personalized Search Adaptive Systems Analysis and User Modeling Semantic Enrichment, Linkage and Alignment user/usage data Social Web
  • 4. User Modeling Challenge Personalized News Recommender I want my personalized news recommendations! Profile Analysis and User Modeling ? (How) can we infer a Twitter-based user profile that supports the news recommender? Semantic Enrichment, Linkage and Alignment
  • 5. 1. Temporal Constraints time period temporal patterns hashtag-based entity-based topic-based 2. Profile Type tweet-based further enrichment 3. Semantic Enrichment concept frequency 4. Weighting Scheme User Modeling Framework Building Blocks for generating valuable user profiles
  • 6. User Modeling Building Blocks 1. Temporal Constraints (a) time period 1. Which tweets of the user should be analyzed? ? (b) temporal patterns Profile? concept weight end start weekends Morning: Afternoon: Night: time June 27 July 4 July 11
  • 7. User Modeling Building Blocks 1. Temporal Constraints Francesca Schiavone T Sport 2. Profile Type Francesca Schiavone won French Open #fo2010 Francesca Schiavone French Open ? #fo2010 Profile? concept weight # hashtag-based entity-based French Open T topic-based # fo2010 2. What type of concepts should represent “interests”? time June 27 July 4 July 11
  • 8. User Modeling Building Blocks 1. Temporal Constraints (a) tweet-based Francesca Schiavone 2. Profile Type Francesca wins French Open Thirty in women's tennis is primordially old, an age when agility and desire recedes as the … Francesca Schiavone Francesca Schiavone won! http://bit.ly/2f4t7a 3. Semantic Enrichment Profile? concept weight French Open Tennis French Open (b) further enrichment Tennis 3. Further enrich the semantics of tweets?
  • 9. User Modeling Building Blocks 1. Temporal Constraints 2. Profile Type ? Francesca Schiavone 4 4. How to weight the concepts? 3. Semantic Enrichment Profile? concept weight 3 French Open 6 Tennis Concept frequency 4. Weighting Scheme weight(FrancescaSchiavone) weight(French Open) weight(Tennis) time June 27 July 4 July 11
  • 10. User Modeling Building Blocks 1. Temporal Constraints time period temporal patterns hashtag-based entity-based topic-based 2. Profile Type tweet-based further enrichment 3. Semantic Enrichment concept frequency 4. Weighting Scheme
  • 11. 1. Temporal Constraints time period temporal patterns hashtag-based entity-based topic-based 2. Profile Type tweet-based further enrichment 3. Semantic Enrichment concept frequency 4. Weighting Scheme Analysis How do the user modeling building blocks impact the (temporal) characteristics of Twitter-based user profiles?
  • 12. Dataset more than: 20,000 Twitter users 2 months 10,000,000 WikiLeaks founder, Julian Assange, under arrest in London tweets 75,000 news articles time Dec 15 Jan 15 Nov 15
  • 13. Size of user profiles Profile Type ~5% of the users do not make use of hashtags hashtag-based profiles are empty entity-based Entity-based user modeling succeeds for 100% of the users topic-based hashtag-based
  • 14. Semantic Enrichment More distinct topics per profile further enrichment (e.g. exploiting links) further enrichment (e.g. exploiting links) More distinct entities per profile Exploiting external resources allows for significantly richer user profiles (quantitatively) Tweet-based Tweet-based entity-based user profiles topic-based user profiles Impact of Semantic Enrichment
  • 15. User Profiles change over time Temporal Constraints Hashtag-based profiles change stronger than entity-based and topic-based profiles d1-distance: difference between current profile and past profile Example: # old new ? music The older the profile the more it differs from the current profile tennis football T
  • 16. Temporal patterns of user profiles Temporal Constraints 2 1. Weekend profiles differ significantly from weekday profiles 2. the difference is stronger than between day and night profiles weekday vs. weekend profiles d1(pweekday, pweekend) day vs. night profiles d1(pday, pnight) topic-based user profiles
  • 17. Observations Semantic enrichment allows for richer user profiles Profiles change over time: fresh profiles seem to better reflect current user demands Temporal patterns: weekend profiles differ significantly form weekday profiles
  • 18. 1. Temporal Constraints time period temporal patterns hashtag-based entity-based topic-based 2. Profile Type tweet-based further enrichment 3. Semantic Enrichment concept frequency 4. Weighting Scheme Evaluation How do the user modeling building blocks impact the quality of Twitter-based profiles for personalized news recommendations? And can we benefit from the findings of the analysis to improve recommendations?
  • 19. Twitter-based Profiles for Personalization Task: Recommending news articles (= tweets with URLs pointing to news articles) Recommender algorithm: cosine similarity between user profile and tweets Ground truth: re-tweets of users Candidate items: news article tweets posted during evaluation period 5.5 relevant tweets per user 5529 candidate news articles Recommendations = ? P(u)= ? time 1 week
  • 20. Profile Type Overview: Performance of User Modeling strategies Topic-based strategy improves S@10 significantly # Entity-based strategy improves the recommendation quality significantly (MRR & S@10) T
  • 21. Impact of Semantic Enrichment Semantic Enrichment T Tweet-based Further enrichment Further semantic enrichment (exploiting links) improves the quality of the Twitter-based profiles!
  • 22.
  • 23. Conclusions and Future Work What we did: Twitter-based User Modeling for Recommending News Articles Analysis: Semantic enrichment results in richer user profiles (quantitative) User interest profiles change over time (hashtag-based stronger than others) Weekend/weekday pattern more significant than day/night pattern Evaluation: Best user modeling strategy: Entity-based > topic-based > hashtag-based Semantic enrichment improves recommendation quality Adapting to temporal context helps for topic-based strategy Future work: for what type of personalization tasks can we exploit what type of Twitter profiles?
  • 24. Thank you! Fabian Abel, QiGao, Geert-Jan Houben, Ke Tao Twitter: @persweb http://persweb.org/ http://u-sem.org/
  • 25. Research Questions What type of user interest profiles can we infer from Twitter activities? Can we exploit Twitter-based profiles for personalizing users’ Social Web experience? Personalized news recommendations in time: interest twitter Good Morning! #tooearly ? ? I like this http://bit.ly/5d4r2t Why do people now blame Julian Assange? time time Ajax deserves it! #sport
  • 26. Analyzing Twitter-based Profiles for Personalized News Recommendations (in time) News Recommendations in time: Interests: Tennis Football Francesca Schiavone is great! Thirty in women's tennis is primordially old, an age when agility and desire recedes as the next wave of younger/faster/stronger players encroaches. It's uncommon for any athlete to have a breakthrough season at 30, but it's exceedingly… Ajax gives De Jong a break Ajax manager Frank de Boer announced that… Personalized news recommendations interest interest I like this http://bit.ly/4Gfd2 Analysis and User Modeling time time topic:Tennis Semantic Enrichment, Linkage, Alignment dbpedia:Schiavone Nice, thank you! oc:Sports event:FrenchOpen tweets
  • 27. User Modeling Challenge Wednesday, July 13th 2011, 9:10am Personalized news recommender Profile? I want my personalized news recommendations! ? (How) can we infer a Twitter-based user profile that supports the news recommender?
  • 28. Bob tweets… Why do people now blame Julian Assange? Ajax deserves it! #sport Good Morning! #tooearly I like this http://bit.ly/5d4r2t time Fr, 6am Fr, 3pm Fr, 8pm Sa, 5pm People publish more than 60 million tweets per day!

Hinweis der Redaktion

  1. large dataset of more than 10 million tweets and 70,000 news articles