SlideShare una empresa de Scribd logo
1 de 25
Descargar para leer sin conexión
Dynamic learning of
keyword-based preferences
for news recommendation
A.Moreno, L.Marin, D.Isern, D.Perelló
ITAKA-Intelligent Tech. for Advanced Knowledge Acquisition
Departament d’Enginyeria Informàtica i Matemàtiques
Universitat Rovira i Virgili, Tarragona
http://deim.urv.cat/~itaka
Outline of the talk
 Introduction: motivation of the problem
 User profile management
 Automatic learning of user interests
 Evaluation
 Conclusions
Outline of the talk
 Introduction: motivation of the problem
 User profile management
 Automatic learning of user interests
 Evaluation
 Conclusions
Introduction: preference learning
 Important issue in recommender systems:
discover the user interests to provide
accurate recommendations.
 User preferences may be explicitly given by
the user or may be inferred through the
analysis of his/her actions.
 We focus our attention on the case in which
the objects to be recommended are purely
textual (e.g. News).
Outline of the talk
 Introduction: motivation of the problem
 User profile management
 Automatic learning of user interests
 Evaluation
 Conclusions
Representation of preferences
 The user profile will store a dynamic set of
keywords. Each of them will have a
positive/negative level of preference, in the
range [-100, 100]
Manchester United +80
Angela Merkel -90
tennis 0
Representation of a textual object
 Given a corpus of textual documents, an
object (news) will be represented by a set of n
relevant keywords, determined by the standard
TF-IDF measure.
Evaluation of a textual object
 Given a user profile P and a document d, the
score assigned to the document in the first
ranking phase is the addition of the user
preferences on the document’s keywords
Keywords of the
document
Preference
value of
keyword w
Outline of the talk
 Introduction: motivation of the problem
 User profile management
 Automatic learning of user interests
 Evaluation
 Conclusions
Selected / Over-ranked alternatives
Over-ranked alternatives
Increase preference value
Smaller increase of preference value
Decrease preference value
Summary of learning algorithm (I)
 Increase the preference value of the keywords
of the selected news that do not appear in the
over-ranked alternatives.
 The more over-ranked alternatives, the greater the
increase
 Increase (in a smaller degree) the preference
value of the keywords of the selected news
that appear in the over-ranked alternatives.
 The more repetitions on the over-ranked
alternatives, the smaller the increase.
Summary of learning algorithm (II)
 Decrease the preference value of the
keywords of the over-ranked alternatives that
do not appear in the selected news.
 The more repetitions on the over-ranked
alternatives, the greater the decrease.
The amounts of increase/decrease were
determined empirically, and the details may be
found in the paper.
Outline of the talk
 Introduction: motivation of the problem
 User profile management
 Automatic learning of user interests
 Evaluation
 Conclusions
Evaluation framework
 Retrieval of 6000 news from The Guardian.
 Definition of an ideal profile to be learnt.
 Random generation of 10 initial profiles.
 A single test consists in a series of 400
recommendations over 6000 alternatives, considering
15 alternatives at each step and 30 keywords/news
 After each recommendation, the normalised distance
between the current profile P and the ideal one I is
calculated
Outline of the talk
 Introduction: motivation of the problem
 User profile management
 Automatic learning of user interests
 Evaluation
 Conclusions
Conclusions
 User preferences on textual documents may
be efficiently learned in an implicit way if the
user has a frequent interaction with the
system.
 In the future work we intend to introduce
semantic information in the learning process
 If a user likes tennis/football/golf, the system
could infer a general interest on sports.
 Treat natural language phenomena like
synonymity and polysemy.
Dynamic learning of
keyword-based preferences
for news recommendation
A.Moreno, L.Marin, D.Isern, D.Perelló
ITAKA-Intelligent Tech. for Advanced Knowledge Acquisition
Departament d’Enginyeria Informàtica i Matemàtiques
Universitat Rovira i Virgili, Tarragona
http://deim.urv.cat/~itaka
Dynamic learning of keyword-based preferences for news recommendation (WI-2014)
Dynamic learning of keyword-based preferences for news recommendation (WI-2014)

Más contenido relacionado

La actualidad más candente

Query formulation process
Query formulation processQuery formulation process
Query formulation processmalathimurugan
 
Filtering out improper user accounts from twitter user accounts for discoveri...
Filtering out improper user accounts from twitter user accounts for discoveri...Filtering out improper user accounts from twitter user accounts for discoveri...
Filtering out improper user accounts from twitter user accounts for discoveri...siramatu-lab
 
Tag recommendation in social bookmarking sites like deli
Tag recommendation in social bookmarking sites like deliTag recommendation in social bookmarking sites like deli
Tag recommendation in social bookmarking sites like deliVinay Singri
 
IRJET - Twitter Sentiment Analysis using Machine Learning
IRJET -  	  Twitter Sentiment Analysis using Machine LearningIRJET -  	  Twitter Sentiment Analysis using Machine Learning
IRJET - Twitter Sentiment Analysis using Machine LearningIRJET Journal
 
Supervised Sentiment Classification using DTDP algorithm
Supervised Sentiment Classification using DTDP algorithmSupervised Sentiment Classification using DTDP algorithm
Supervised Sentiment Classification using DTDP algorithmIJSRD
 
Not Good Enough but Try Again! Mitigating the Impact of Rejections on New Con...
Not Good Enough but Try Again! Mitigating the Impact of Rejections on New Con...Not Good Enough but Try Again! Mitigating the Impact of Rejections on New Con...
Not Good Enough but Try Again! Mitigating the Impact of Rejections on New Con...Aleksi Aaltonen
 
Blog project media and rubric2
Blog project media and rubric2Blog project media and rubric2
Blog project media and rubric2sherrychapman
 
IRJET- Sentimental Analysis of Product Reviews for E-Commerce Websites
IRJET- Sentimental Analysis of Product Reviews for E-Commerce WebsitesIRJET- Sentimental Analysis of Product Reviews for E-Commerce Websites
IRJET- Sentimental Analysis of Product Reviews for E-Commerce WebsitesIRJET Journal
 
Opinion mining on newspaper headlines using SVM and NLP
Opinion mining on newspaper headlines using SVM and NLPOpinion mining on newspaper headlines using SVM and NLP
Opinion mining on newspaper headlines using SVM and NLPIJECEIAES
 
Effective research strategies
Effective research strategiesEffective research strategies
Effective research strategiesDr-Heba Mustafa
 
A Novel Voice Based Sentimental Analysis Technique to Mine the User Driven Re...
A Novel Voice Based Sentimental Analysis Technique to Mine the User Driven Re...A Novel Voice Based Sentimental Analysis Technique to Mine the User Driven Re...
A Novel Voice Based Sentimental Analysis Technique to Mine the User Driven Re...IRJET Journal
 
Twitter Sentiment Analysis on 2013 Curriculum Using Ensemble Features and K-N...
Twitter Sentiment Analysis on 2013 Curriculum Using Ensemble Features and K-N...Twitter Sentiment Analysis on 2013 Curriculum Using Ensemble Features and K-N...
Twitter Sentiment Analysis on 2013 Curriculum Using Ensemble Features and K-N...IJECEIAES
 
Ijmer 46067276
Ijmer 46067276Ijmer 46067276
Ijmer 46067276IJMER
 
SENTIMENT ANALYSIS FOR MOVIES REVIEWS DATASET USING DEEP LEARNING MODELS
SENTIMENT ANALYSIS FOR MOVIES REVIEWS DATASET USING DEEP LEARNING MODELSSENTIMENT ANALYSIS FOR MOVIES REVIEWS DATASET USING DEEP LEARNING MODELS
SENTIMENT ANALYSIS FOR MOVIES REVIEWS DATASET USING DEEP LEARNING MODELSIJDKP
 
Stock prediction using social network
Stock prediction using social networkStock prediction using social network
Stock prediction using social networkChanon Hongsirikulkit
 

La actualidad más candente (19)

Query formulation process
Query formulation processQuery formulation process
Query formulation process
 
Filtering out improper user accounts from twitter user accounts for discoveri...
Filtering out improper user accounts from twitter user accounts for discoveri...Filtering out improper user accounts from twitter user accounts for discoveri...
Filtering out improper user accounts from twitter user accounts for discoveri...
 
Tag recommendation in social bookmarking sites like deli
Tag recommendation in social bookmarking sites like deliTag recommendation in social bookmarking sites like deli
Tag recommendation in social bookmarking sites like deli
 
Demo of my e learning course
Demo of my e learning courseDemo of my e learning course
Demo of my e learning course
 
IRJET - Twitter Sentiment Analysis using Machine Learning
IRJET -  	  Twitter Sentiment Analysis using Machine LearningIRJET -  	  Twitter Sentiment Analysis using Machine Learning
IRJET - Twitter Sentiment Analysis using Machine Learning
 
Ieee format 5th nccci_a study on factors influencing as a best practice for...
Ieee format 5th nccci_a study on factors influencing as  a  best practice for...Ieee format 5th nccci_a study on factors influencing as  a  best practice for...
Ieee format 5th nccci_a study on factors influencing as a best practice for...
 
J1803015357
J1803015357J1803015357
J1803015357
 
Abstract
AbstractAbstract
Abstract
 
Supervised Sentiment Classification using DTDP algorithm
Supervised Sentiment Classification using DTDP algorithmSupervised Sentiment Classification using DTDP algorithm
Supervised Sentiment Classification using DTDP algorithm
 
Not Good Enough but Try Again! Mitigating the Impact of Rejections on New Con...
Not Good Enough but Try Again! Mitigating the Impact of Rejections on New Con...Not Good Enough but Try Again! Mitigating the Impact of Rejections on New Con...
Not Good Enough but Try Again! Mitigating the Impact of Rejections on New Con...
 
Blog project media and rubric2
Blog project media and rubric2Blog project media and rubric2
Blog project media and rubric2
 
IRJET- Sentimental Analysis of Product Reviews for E-Commerce Websites
IRJET- Sentimental Analysis of Product Reviews for E-Commerce WebsitesIRJET- Sentimental Analysis of Product Reviews for E-Commerce Websites
IRJET- Sentimental Analysis of Product Reviews for E-Commerce Websites
 
Opinion mining on newspaper headlines using SVM and NLP
Opinion mining on newspaper headlines using SVM and NLPOpinion mining on newspaper headlines using SVM and NLP
Opinion mining on newspaper headlines using SVM and NLP
 
Effective research strategies
Effective research strategiesEffective research strategies
Effective research strategies
 
A Novel Voice Based Sentimental Analysis Technique to Mine the User Driven Re...
A Novel Voice Based Sentimental Analysis Technique to Mine the User Driven Re...A Novel Voice Based Sentimental Analysis Technique to Mine the User Driven Re...
A Novel Voice Based Sentimental Analysis Technique to Mine the User Driven Re...
 
Twitter Sentiment Analysis on 2013 Curriculum Using Ensemble Features and K-N...
Twitter Sentiment Analysis on 2013 Curriculum Using Ensemble Features and K-N...Twitter Sentiment Analysis on 2013 Curriculum Using Ensemble Features and K-N...
Twitter Sentiment Analysis on 2013 Curriculum Using Ensemble Features and K-N...
 
Ijmer 46067276
Ijmer 46067276Ijmer 46067276
Ijmer 46067276
 
SENTIMENT ANALYSIS FOR MOVIES REVIEWS DATASET USING DEEP LEARNING MODELS
SENTIMENT ANALYSIS FOR MOVIES REVIEWS DATASET USING DEEP LEARNING MODELSSENTIMENT ANALYSIS FOR MOVIES REVIEWS DATASET USING DEEP LEARNING MODELS
SENTIMENT ANALYSIS FOR MOVIES REVIEWS DATASET USING DEEP LEARNING MODELS
 
Stock prediction using social network
Stock prediction using social networkStock prediction using social network
Stock prediction using social network
 

Destacado

גיבוי ושחזור סימניות בפיירפוקס
גיבוי ושחזור סימניות בפיירפוקסגיבוי ושחזור סימניות בפיירפוקס
גיבוי ושחזור סימניות בפיירפוקס012 Smile
 
Oregon/Washington Association of Broadcasters AM presentation
Oregon/Washington Association of Broadcasters AM presentationOregon/Washington Association of Broadcasters AM presentation
Oregon/Washington Association of Broadcasters AM presentationIntegrate
 
הגדרות פרטיות בפייסבוק
הגדרות פרטיות בפייסבוקהגדרות פרטיות בפייסבוק
הגדרות פרטיות בפייסבוק012 Smile
 
The Power of Integrating Social and Traditional PR
The Power of Integrating Social and Traditional PRThe Power of Integrating Social and Traditional PR
The Power of Integrating Social and Traditional PRIntegrate
 
Diageo\'s Digital Marketing Code
Diageo\'s Digital Marketing CodeDiageo\'s Digital Marketing Code
Diageo\'s Digital Marketing CodeClayton T Ford
 
Airports and Social Media
Airports and Social MediaAirports and Social Media
Airports and Social MediaIntegrate
 
Image Management Academy
Image Management AcademyImage Management Academy
Image Management Academynikosvoglis
 
Presentation 5 The Heart
Presentation 5 The HeartPresentation 5 The Heart
Presentation 5 The Heartmissdianacuevas
 
La Festa De La Pau 2010
La Festa De La Pau 2010La Festa De La Pau 2010
La Festa De La Pau 2010guesta2dd30
 
Automatic and unsupervised topic discovery in social networks
Automatic and unsupervised topic discovery in social networksAutomatic and unsupervised topic discovery in social networks
Automatic and unsupervised topic discovery in social networksAntonio Moreno
 
Helistin Dvd Ja Netti - Uuden Sukupolven Apu Lasta Odottaville
Helistin Dvd Ja Netti - Uuden Sukupolven Apu Lasta OdottavilleHelistin Dvd Ja Netti - Uuden Sukupolven Apu Lasta Odottaville
Helistin Dvd Ja Netti - Uuden Sukupolven Apu Lasta OdottavilleDarwin Oy
 
Kad kerja tahun 4
Kad kerja tahun 4Kad kerja tahun 4
Kad kerja tahun 4peicui89
 
ניהול סימניות בגוגל כרום
ניהול סימניות בגוגל כרוםניהול סימניות בגוגל כרום
ניהול סימניות בגוגל כרום012 Smile
 

Destacado (20)

גיבוי ושחזור סימניות בפיירפוקס
גיבוי ושחזור סימניות בפיירפוקסגיבוי ושחזור סימניות בפיירפוקס
גיבוי ושחזור סימניות בפיירפוקס
 
Oregon/Washington Association of Broadcasters AM presentation
Oregon/Washington Association of Broadcasters AM presentationOregon/Washington Association of Broadcasters AM presentation
Oregon/Washington Association of Broadcasters AM presentation
 
הגדרות פרטיות בפייסבוק
הגדרות פרטיות בפייסבוקהגדרות פרטיות בפייסבוק
הגדרות פרטיות בפייסבוק
 
The Power of Integrating Social and Traditional PR
The Power of Integrating Social and Traditional PRThe Power of Integrating Social and Traditional PR
The Power of Integrating Social and Traditional PR
 
Diageo\'s Digital Marketing Code
Diageo\'s Digital Marketing CodeDiageo\'s Digital Marketing Code
Diageo\'s Digital Marketing Code
 
Airports and Social Media
Airports and Social MediaAirports and Social Media
Airports and Social Media
 
Image Management Academy
Image Management AcademyImage Management Academy
Image Management Academy
 
FCS C4 Lesson 8-2
FCS C4 Lesson 8-2FCS C4 Lesson 8-2
FCS C4 Lesson 8-2
 
TNM классификация немелкоклеточного рака легкого
TNM классификация немелкоклеточного рака легкогоTNM классификация немелкоклеточного рака легкого
TNM классификация немелкоклеточного рака легкого
 
Presentation 5 The Heart
Presentation 5 The HeartPresentation 5 The Heart
Presentation 5 The Heart
 
Otchet
OtchetOtchet
Otchet
 
E&e
E&eE&e
E&e
 
La Festa De La Pau 2010
La Festa De La Pau 2010La Festa De La Pau 2010
La Festa De La Pau 2010
 
model's
model'smodel's
model's
 
Automatic and unsupervised topic discovery in social networks
Automatic and unsupervised topic discovery in social networksAutomatic and unsupervised topic discovery in social networks
Automatic and unsupervised topic discovery in social networks
 
Lesson18post
Lesson18postLesson18post
Lesson18post
 
Helistin Dvd Ja Netti - Uuden Sukupolven Apu Lasta Odottaville
Helistin Dvd Ja Netti - Uuden Sukupolven Apu Lasta OdottavilleHelistin Dvd Ja Netti - Uuden Sukupolven Apu Lasta Odottaville
Helistin Dvd Ja Netti - Uuden Sukupolven Apu Lasta Odottaville
 
Kad kerja tahun 4
Kad kerja tahun 4Kad kerja tahun 4
Kad kerja tahun 4
 
ניהול סימניות בגוגל כרום
ניהול סימניות בגוגל כרוםניהול סימניות בגוגל כרום
ניהול סימניות בגוגל כרום
 
TNM классификация рака легкого (6 редакция)
TNM классификация рака легкого (6 редакция)TNM классификация рака легкого (6 редакция)
TNM классификация рака легкого (6 редакция)
 

Similar a Dynamic learning of keyword-based preferences for news recommendation (WI-2014)

Feature Based Semantic Polarity Analysis Through Ontology
Feature Based Semantic Polarity Analysis Through OntologyFeature Based Semantic Polarity Analysis Through Ontology
Feature Based Semantic Polarity Analysis Through OntologyIOSR Journals
 
CS8091_BDA_Unit_III_Content_Based_Recommendation
CS8091_BDA_Unit_III_Content_Based_RecommendationCS8091_BDA_Unit_III_Content_Based_Recommendation
CS8091_BDA_Unit_III_Content_Based_RecommendationPalani Kumar
 
Articulation
Articulation Articulation
Articulation butest
 
Sentiment Analysis in Hindi Language : A Survey
Sentiment Analysis in Hindi Language : A SurveySentiment Analysis in Hindi Language : A Survey
Sentiment Analysis in Hindi Language : A SurveyEditor IJMTER
 
When to use the different text analytics tools - Meaning Cloud
When to use the different text analytics tools - Meaning CloudWhen to use the different text analytics tools - Meaning Cloud
When to use the different text analytics tools - Meaning CloudMeaningCloud
 
Data Science - Experiments
Data Science - ExperimentsData Science - Experiments
Data Science - ExperimentsGaurav Marwaha
 
Information products by aman kr kushwaha
Information products by aman kr kushwahaInformation products by aman kr kushwaha
Information products by aman kr kushwahaAMAN KUMAR KUSHWAHA
 
Rule-based expert systems for supporting university students
Rule-based expert systems for supporting university studentsRule-based expert systems for supporting university students
Rule-based expert systems for supporting university studentsertekg
 
Rule-based expert systems for supporting university students
Rule-based expert systems for supporting university studentsRule-based expert systems for supporting university students
Rule-based expert systems for supporting university studentsGurdal Ertek
 
MAC411(A) Analysis in Communication Researc.ppt
MAC411(A) Analysis in Communication Researc.pptMAC411(A) Analysis in Communication Researc.ppt
MAC411(A) Analysis in Communication Researc.pptPreciousOsoOla
 
Basics of Paper Writing and Publishing in TEL (JTEL 2014 Workshop)
Basics of Paper Writing and Publishing in TEL (JTEL 2014 Workshop)Basics of Paper Writing and Publishing in TEL (JTEL 2014 Workshop)
Basics of Paper Writing and Publishing in TEL (JTEL 2014 Workshop)Michael Derntl
 
[PythonPH] Transforming the call center with Text mining and Deep learning (C...
[PythonPH] Transforming the call center with Text mining and Deep learning (C...[PythonPH] Transforming the call center with Text mining and Deep learning (C...
[PythonPH] Transforming the call center with Text mining and Deep learning (C...Paul Lo
 
Mb0050 research methodology (1)
Mb0050   research methodology (1)Mb0050   research methodology (1)
Mb0050 research methodology (1)smumbahelp
 
Mining Opinion Features in Customer Reviews
Mining Opinion Features in Customer ReviewsMining Opinion Features in Customer Reviews
Mining Opinion Features in Customer ReviewsIJCERT JOURNAL
 
Information overload in emergency management
Information overload in emergency managementInformation overload in emergency management
Information overload in emergency managementguestf66e810
 
Information overload for communities of practice
Information overload for communities of practiceInformation overload for communities of practice
Information overload for communities of practiceMurray Turoff
 
SUPPORT VECTOR MACHINE CLASSIFIER FOR SENTIMENT ANALYSIS OF FEEDBACK MARKETPL...
SUPPORT VECTOR MACHINE CLASSIFIER FOR SENTIMENT ANALYSIS OF FEEDBACK MARKETPL...SUPPORT VECTOR MACHINE CLASSIFIER FOR SENTIMENT ANALYSIS OF FEEDBACK MARKETPL...
SUPPORT VECTOR MACHINE CLASSIFIER FOR SENTIMENT ANALYSIS OF FEEDBACK MARKETPL...AM Publications
 
Understanding voice of the member via text mining
Understanding voice of the member via text miningUnderstanding voice of the member via text mining
Understanding voice of the member via text miningChi-Yi Kuan
 

Similar a Dynamic learning of keyword-based preferences for news recommendation (WI-2014) (20)

C017141317
C017141317C017141317
C017141317
 
Feature Based Semantic Polarity Analysis Through Ontology
Feature Based Semantic Polarity Analysis Through OntologyFeature Based Semantic Polarity Analysis Through Ontology
Feature Based Semantic Polarity Analysis Through Ontology
 
CS8091_BDA_Unit_III_Content_Based_Recommendation
CS8091_BDA_Unit_III_Content_Based_RecommendationCS8091_BDA_Unit_III_Content_Based_Recommendation
CS8091_BDA_Unit_III_Content_Based_Recommendation
 
Articulation
Articulation Articulation
Articulation
 
M045067275
M045067275M045067275
M045067275
 
Sentiment Analysis in Hindi Language : A Survey
Sentiment Analysis in Hindi Language : A SurveySentiment Analysis in Hindi Language : A Survey
Sentiment Analysis in Hindi Language : A Survey
 
When to use the different text analytics tools - Meaning Cloud
When to use the different text analytics tools - Meaning CloudWhen to use the different text analytics tools - Meaning Cloud
When to use the different text analytics tools - Meaning Cloud
 
Data Science - Experiments
Data Science - ExperimentsData Science - Experiments
Data Science - Experiments
 
Information products by aman kr kushwaha
Information products by aman kr kushwahaInformation products by aman kr kushwaha
Information products by aman kr kushwaha
 
Rule-based expert systems for supporting university students
Rule-based expert systems for supporting university studentsRule-based expert systems for supporting university students
Rule-based expert systems for supporting university students
 
Rule-based expert systems for supporting university students
Rule-based expert systems for supporting university studentsRule-based expert systems for supporting university students
Rule-based expert systems for supporting university students
 
MAC411(A) Analysis in Communication Researc.ppt
MAC411(A) Analysis in Communication Researc.pptMAC411(A) Analysis in Communication Researc.ppt
MAC411(A) Analysis in Communication Researc.ppt
 
Basics of Paper Writing and Publishing in TEL (JTEL 2014 Workshop)
Basics of Paper Writing and Publishing in TEL (JTEL 2014 Workshop)Basics of Paper Writing and Publishing in TEL (JTEL 2014 Workshop)
Basics of Paper Writing and Publishing in TEL (JTEL 2014 Workshop)
 
[PythonPH] Transforming the call center with Text mining and Deep learning (C...
[PythonPH] Transforming the call center with Text mining and Deep learning (C...[PythonPH] Transforming the call center with Text mining and Deep learning (C...
[PythonPH] Transforming the call center with Text mining and Deep learning (C...
 
Mb0050 research methodology (1)
Mb0050   research methodology (1)Mb0050   research methodology (1)
Mb0050 research methodology (1)
 
Mining Opinion Features in Customer Reviews
Mining Opinion Features in Customer ReviewsMining Opinion Features in Customer Reviews
Mining Opinion Features in Customer Reviews
 
Information overload in emergency management
Information overload in emergency managementInformation overload in emergency management
Information overload in emergency management
 
Information overload for communities of practice
Information overload for communities of practiceInformation overload for communities of practice
Information overload for communities of practice
 
SUPPORT VECTOR MACHINE CLASSIFIER FOR SENTIMENT ANALYSIS OF FEEDBACK MARKETPL...
SUPPORT VECTOR MACHINE CLASSIFIER FOR SENTIMENT ANALYSIS OF FEEDBACK MARKETPL...SUPPORT VECTOR MACHINE CLASSIFIER FOR SENTIMENT ANALYSIS OF FEEDBACK MARKETPL...
SUPPORT VECTOR MACHINE CLASSIFIER FOR SENTIMENT ANALYSIS OF FEEDBACK MARKETPL...
 
Understanding voice of the member via text mining
Understanding voice of the member via text miningUnderstanding voice of the member via text mining
Understanding voice of the member via text mining
 

Más de Antonio Moreno

ECAI 2014 poster - Unsupervised semantic clustering of Twitter hashtags
ECAI 2014 poster - Unsupervised semantic clustering of Twitter hashtagsECAI 2014 poster - Unsupervised semantic clustering of Twitter hashtags
ECAI 2014 poster - Unsupervised semantic clustering of Twitter hashtagsAntonio Moreno
 
Artificial Intelligence Master URV-UPC-UB
Artificial Intelligence Master URV-UPC-UBArtificial Intelligence Master URV-UPC-UB
Artificial Intelligence Master URV-UPC-UBAntonio Moreno
 
URV Master on Computer Engineering: Computer Security and Inteligent Systems
URV Master on Computer Engineering: Computer Security and Inteligent SystemsURV Master on Computer Engineering: Computer Security and Inteligent Systems
URV Master on Computer Engineering: Computer Security and Inteligent SystemsAntonio Moreno
 
EnoSigTur: recomanació personalitzada d'activitats enoturístiques
EnoSigTur: recomanació personalitzada d'activitats enoturístiquesEnoSigTur: recomanació personalitzada d'activitats enoturístiques
EnoSigTur: recomanació personalitzada d'activitats enoturístiquesAntonio Moreno
 
On the application of multi-agent systems in Health Care
On the application of multi-agent systems in Health CareOn the application of multi-agent systems in Health Care
On the application of multi-agent systems in Health CareAntonio Moreno
 
Multi-agent systems applied in Health Care
Multi-agent systems applied in Health CareMulti-agent systems applied in Health Care
Multi-agent systems applied in Health CareAntonio Moreno
 
Artificial Intelligence techniques in Tourism at URV
Artificial Intelligence techniques in Tourism at URVArtificial Intelligence techniques in Tourism at URV
Artificial Intelligence techniques in Tourism at URVAntonio Moreno
 
MAS course Lect13 industrial applications
MAS course Lect13 industrial applicationsMAS course Lect13 industrial applications
MAS course Lect13 industrial applicationsAntonio Moreno
 
MAS course - Lect12 - URV health care applications
MAS course - Lect12 - URV health care applicationsMAS course - Lect12 - URV health care applications
MAS course - Lect12 - URV health care applicationsAntonio Moreno
 
MAS course - Lect11 - URV applications
MAS course - Lect11 - URV applicationsMAS course - Lect11 - URV applications
MAS course - Lect11 - URV applicationsAntonio Moreno
 
MAS Course - Lect10 - coordination
MAS Course - Lect10 - coordinationMAS Course - Lect10 - coordination
MAS Course - Lect10 - coordinationAntonio Moreno
 
Lect6-An introduction to ontologies and ontology development
Lect6-An introduction to ontologies and ontology developmentLect6-An introduction to ontologies and ontology development
Lect6-An introduction to ontologies and ontology developmentAntonio Moreno
 
Lecture 5 - Agent communication
Lecture 5 - Agent communicationLecture 5 - Agent communication
Lecture 5 - Agent communicationAntonio Moreno
 
Lecture 4- Agent types
Lecture 4- Agent typesLecture 4- Agent types
Lecture 4- Agent typesAntonio Moreno
 
Introduction to agents and multi-agent systems
Introduction to agents and multi-agent systemsIntroduction to agents and multi-agent systems
Introduction to agents and multi-agent systemsAntonio Moreno
 

Más de Antonio Moreno (20)

ECAI 2014 poster - Unsupervised semantic clustering of Twitter hashtags
ECAI 2014 poster - Unsupervised semantic clustering of Twitter hashtagsECAI 2014 poster - Unsupervised semantic clustering of Twitter hashtags
ECAI 2014 poster - Unsupervised semantic clustering of Twitter hashtags
 
Artificial Intelligence Master URV-UPC-UB
Artificial Intelligence Master URV-UPC-UBArtificial Intelligence Master URV-UPC-UB
Artificial Intelligence Master URV-UPC-UB
 
URV Master on Computer Engineering: Computer Security and Inteligent Systems
URV Master on Computer Engineering: Computer Security and Inteligent SystemsURV Master on Computer Engineering: Computer Security and Inteligent Systems
URV Master on Computer Engineering: Computer Security and Inteligent Systems
 
EnoSigTur: recomanació personalitzada d'activitats enoturístiques
EnoSigTur: recomanació personalitzada d'activitats enoturístiquesEnoSigTur: recomanació personalitzada d'activitats enoturístiques
EnoSigTur: recomanació personalitzada d'activitats enoturístiques
 
On the application of multi-agent systems in Health Care
On the application of multi-agent systems in Health CareOn the application of multi-agent systems in Health Care
On the application of multi-agent systems in Health Care
 
Multi-agent systems applied in Health Care
Multi-agent systems applied in Health CareMulti-agent systems applied in Health Care
Multi-agent systems applied in Health Care
 
Artificial Intelligence techniques in Tourism at URV
Artificial Intelligence techniques in Tourism at URVArtificial Intelligence techniques in Tourism at URV
Artificial Intelligence techniques in Tourism at URV
 
MAS course Lect13 industrial applications
MAS course Lect13 industrial applicationsMAS course Lect13 industrial applications
MAS course Lect13 industrial applications
 
MAS course - Lect12 - URV health care applications
MAS course - Lect12 - URV health care applicationsMAS course - Lect12 - URV health care applications
MAS course - Lect12 - URV health care applications
 
MAS course - Lect11 - URV applications
MAS course - Lect11 - URV applicationsMAS course - Lect11 - URV applications
MAS course - Lect11 - URV applications
 
MAS Course - Lect10 - coordination
MAS Course - Lect10 - coordinationMAS Course - Lect10 - coordination
MAS Course - Lect10 - coordination
 
MAS course - Lect 9
MAS course - Lect 9 MAS course - Lect 9
MAS course - Lect 9
 
Lect 8-auctions
Lect 8-auctionsLect 8-auctions
Lect 8-auctions
 
Lect7MAS-Coordination
Lect7MAS-CoordinationLect7MAS-Coordination
Lect7MAS-Coordination
 
Lect6-An introduction to ontologies and ontology development
Lect6-An introduction to ontologies and ontology developmentLect6-An introduction to ontologies and ontology development
Lect6-An introduction to ontologies and ontology development
 
Lecture 5 - Agent communication
Lecture 5 - Agent communicationLecture 5 - Agent communication
Lecture 5 - Agent communication
 
Lecture 4- Agent types
Lecture 4- Agent typesLecture 4- Agent types
Lecture 4- Agent types
 
Agent properties
Agent propertiesAgent properties
Agent properties
 
Agent architectures
Agent architecturesAgent architectures
Agent architectures
 
Introduction to agents and multi-agent systems
Introduction to agents and multi-agent systemsIntroduction to agents and multi-agent systems
Introduction to agents and multi-agent systems
 

Último

Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
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
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
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
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
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
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
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
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
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
 
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
 

Último (20)

Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
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...
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
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...
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
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
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
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
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
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
 
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
 

Dynamic learning of keyword-based preferences for news recommendation (WI-2014)

  • 1. Dynamic learning of keyword-based preferences for news recommendation A.Moreno, L.Marin, D.Isern, D.Perelló ITAKA-Intelligent Tech. for Advanced Knowledge Acquisition Departament d’Enginyeria Informàtica i Matemàtiques Universitat Rovira i Virgili, Tarragona http://deim.urv.cat/~itaka
  • 2. Outline of the talk  Introduction: motivation of the problem  User profile management  Automatic learning of user interests  Evaluation  Conclusions
  • 3. Outline of the talk  Introduction: motivation of the problem  User profile management  Automatic learning of user interests  Evaluation  Conclusions
  • 4. Introduction: preference learning  Important issue in recommender systems: discover the user interests to provide accurate recommendations.  User preferences may be explicitly given by the user or may be inferred through the analysis of his/her actions.  We focus our attention on the case in which the objects to be recommended are purely textual (e.g. News).
  • 5.
  • 6. Outline of the talk  Introduction: motivation of the problem  User profile management  Automatic learning of user interests  Evaluation  Conclusions
  • 7. Representation of preferences  The user profile will store a dynamic set of keywords. Each of them will have a positive/negative level of preference, in the range [-100, 100] Manchester United +80 Angela Merkel -90 tennis 0
  • 8. Representation of a textual object  Given a corpus of textual documents, an object (news) will be represented by a set of n relevant keywords, determined by the standard TF-IDF measure.
  • 9. Evaluation of a textual object  Given a user profile P and a document d, the score assigned to the document in the first ranking phase is the addition of the user preferences on the document’s keywords Keywords of the document Preference value of keyword w
  • 10. Outline of the talk  Introduction: motivation of the problem  User profile management  Automatic learning of user interests  Evaluation  Conclusions
  • 11. Selected / Over-ranked alternatives Over-ranked alternatives
  • 13. Smaller increase of preference value
  • 15. Summary of learning algorithm (I)  Increase the preference value of the keywords of the selected news that do not appear in the over-ranked alternatives.  The more over-ranked alternatives, the greater the increase  Increase (in a smaller degree) the preference value of the keywords of the selected news that appear in the over-ranked alternatives.  The more repetitions on the over-ranked alternatives, the smaller the increase.
  • 16. Summary of learning algorithm (II)  Decrease the preference value of the keywords of the over-ranked alternatives that do not appear in the selected news.  The more repetitions on the over-ranked alternatives, the greater the decrease. The amounts of increase/decrease were determined empirically, and the details may be found in the paper.
  • 17. Outline of the talk  Introduction: motivation of the problem  User profile management  Automatic learning of user interests  Evaluation  Conclusions
  • 18. Evaluation framework  Retrieval of 6000 news from The Guardian.  Definition of an ideal profile to be learnt.  Random generation of 10 initial profiles.  A single test consists in a series of 400 recommendations over 6000 alternatives, considering 15 alternatives at each step and 30 keywords/news  After each recommendation, the normalised distance between the current profile P and the ideal one I is calculated
  • 19.
  • 20.
  • 21. Outline of the talk  Introduction: motivation of the problem  User profile management  Automatic learning of user interests  Evaluation  Conclusions
  • 22. Conclusions  User preferences on textual documents may be efficiently learned in an implicit way if the user has a frequent interaction with the system.  In the future work we intend to introduce semantic information in the learning process  If a user likes tennis/football/golf, the system could infer a general interest on sports.  Treat natural language phenomena like synonymity and polysemy.
  • 23. Dynamic learning of keyword-based preferences for news recommendation A.Moreno, L.Marin, D.Isern, D.Perelló ITAKA-Intelligent Tech. for Advanced Knowledge Acquisition Departament d’Enginyeria Informàtica i Matemàtiques Universitat Rovira i Virgili, Tarragona http://deim.urv.cat/~itaka