SlideShare a Scribd company logo
1 of 44
A simple survey of Diversity and
novelty metrics for recommender
systems



                              Reporter: 孙建凯
                                   2012.07.11
Move beyond accuracy metrics
 while the majority of algorithms proposed in
  recommender systems literature have focused on
  improving recommendation accuracy
 other important aspects of recommendation
  quality, such as the diversity of recommendations,
  have often been overlooked.
 The recommendations that are most accurate
  according to the standard metrics are sometimes
  not the recommendations that are most useful to
  users[1]

                                                   2
                   Copyright © 2012 by IRLAB@SDU
Diversity and Novelty

 Accurate is not always good: How Accuracy
  Metrics have hurt Recommender Systems
   GroupLensResearch,CHI'06 




                       Copyright © 2012 by IRLAB@SDU
Accuracy does not tell the whole story




              Copyright © 2012 by IRLAB@SDU
Diversity


 Individual Diversity               Aggregate Diversity




                    Copyright © 2012 by IRLAB@SDU
Individual Diversity
 Diversity Difficulty[3]
 Average dissimilarity between all pairs of items
  recommended to a given user(intra-list similarity)
  [2,4]




                   Copyright © 2012 by IRLAB@SDU
Diversity Difficulty
 What We Talk About When We Talk About
  Diversity [DDR’12 Northeastern University USA]
 Like query difficulty in IR
 For a specific query and corpus, query difficulty is
  a measure of how successful the average search
  engine should be at ad-hoc retrieval.




                    Copyright © 2012 by IRLAB@SDU
Diversity Difficulty
 Diversity Difficulty is defined with respect to a
  query and a corpus.
 Describes diversity-the number of subtopics which
  are covered by a list;
 Describes novelty-which is inversely proportional
  to the number of times a list repeats a subtopic




                   Copyright © 2012 by IRLAB@SDU
Finding needles in the haystack
 Imagine a query with 10 subtopics ,1000 documents
  relevant to only the first subtopic, and each of the
  remaining subtopics covered by a single, unique
  document.
 On the other hand ,if there are large numbers of
  documents relevant to multiple subtopics, it would
  be easy to produce a diversity list.




                    Copyright © 2012 by IRLAB@SDU
Diversity Difficulty function
 The maximum amount of diversity achievable by
  any ranked list-dmax
 The ease with a system can produce a diverse
  ranked list.-dmean
 Harmonic function




                  Copyright © 2012 by IRLAB@SDU
Examples




           Copyright © 2012 by IRLAB@SDU
Improving Recommendation Lists Through
Topic Diversification

 Introduce the intra-list similarity metric to access
  the topic diversification of recommendation lists
  and the topic diversification approach for
  decreasing the intra-list similarity
 Average dissimilarity between all pairs of items
  recommended to a given user




                    Copyright © 2012 by IRLAB@SDU
Intra-list Similarity




              Copyright © 2012 by IRLAB@SDU
Taxonomy-based similarity Metrics
 Instantiate c with their metric for taxonomy-
  driven filtering.[5]




                 Copyright © 2012 by IRLAB@SDU
Topic Diversification Algorithm
Algorithm                     A brief textual sketch




              Copyright © 2012 by IRLAB@SDU
Experiments

 precision       diversity
Aggregate Diversity
 improving recommendation Diversity using ranking-
  based techniques[IEEE transaction’12]
 Use the total number of distinct items
  recommended across all users as an aggregate
  diversity measure, define as follows:




                   Copyright © 2012 by IRLAB@SDU
General overview of ranking-based
approaches for improving diversity




              Copyright © 2012 by IRLAB@SDU
Re-Ranking Approach




              Copyright © 2012 by IRLAB@SDU
Other Re-ranking Approach




              Copyright © 2012 by IRLAB@SDU
Other Re-ranking Approach




              Copyright © 2012 by IRLAB@SDU
Other Re-ranking Approach




              Copyright © 2012 by IRLAB@SDU
Other Re-ranking Approach




              Copyright © 2012 by IRLAB@SDU
Other Re-ranking Approach




              Copyright © 2012 by IRLAB@SDU
Other Re-ranking Approach




              Copyright © 2012 by IRLAB@SDU
Combining Ranking Approaches
 Many possible ways to combine several ranking
  functions
 In this paper , linear combination
 Open issue: letor ? Neural network?




                    Copyright © 2012 by IRLAB@SDU
Entropy
 A study of Heterogeneity in Recommendations for
  a social Music Service[6]




                  Copyright © 2012 by IRLAB@SDU
Open issue:probability




              Copyright © 2012 by IRLAB@SDU
Entropy
Aggregate Entropy:                   Individual Entropy:
 Item         popularity             subtopic popularity?
  between lists?




                     Copyright © 2012 by IRLAB@SDU
Bipartite network
 Bipartite network projection and personal
  recommendation[Tao Zhou, Physical Review]
 Solving the apparent diversity-accuracy dilemma of
  recommender systems[Tao Zhou]




                   Copyright © 2012 by IRLAB@SDU
Illustration of resource-allocation
process in bipartite network




              Copyright © 2012 by IRLAB@SDU
Solving the apparent diversity-accuracy
dilemma
heats                         probs




              Copyright © 2012 by IRLAB@SDU
Hybrid Methods
weight                           hybrid




                 Copyright © 2012 by IRLAB@SDU
Diversity Measure




              Copyright © 2012 by IRLAB@SDU
Surprisal/novelty




              Copyright © 2012 by IRLAB@SDU
Results-why better?




              Copyright © 2012 by IRLAB@SDU
Surprise me
 Tangent: A novel, ‘surprise me’, recommendation
  algorithm [kdd’09]




                  Copyright © 2012 by IRLAB@SDU
Framework of Tangent Algorithm
 Suggest items which are not only relevant to user
  preference but also have a large connectivity to
  other groups.
 Consisting three parts as follows:
 1 Calculate relevance score(RS) for each node
 2 Calculate bridging score(BRS) for each node
 3 Compute the Tangent score by somehow merging
  two criteria above



                    Copyright © 2012 by IRLAB@SDU
Case study




             Copyright © 2012 by IRLAB@SDU
Case study




             Copyright © 2012 by IRLAB@SDU
Call for papers
 September 20, 2012




                 Copyright © 2012 by IRLAB@SDU
Reference
 1. Accurate is not always good: How Accuracy
  Metrics have hurt Recommender Systems
 2.improving   recommendation                    Diversity     using
  ranking-based techniques
 3. What We Talk About When We Talk About
  Diversity
 4. Improving Recommendation Lists Through Topic
  Diversification
 5. Taxonomy-driven           computation            of      product
  recommendations

                  Copyright © 2012 by IRLAB@SDU
Reference
 6. A study of Heterogeneity in Recommendations
  for a social Music Service
 7. Bipartite network projection and personal
  recommendation
 8.Solving the apparent diversity-accuracy dilemma
  of recommender systems
 9. Tangent: A novel, ‘surprise me’, recommendation
  algorithm




                   Copyright © 2012 by IRLAB@SDU
 thanks




           Copyright © 2012 by IRLAB@SDU

More Related Content

What's hot

Personalizing "The Netflix Experience" with Deep Learning
Personalizing "The Netflix Experience" with Deep LearningPersonalizing "The Netflix Experience" with Deep Learning
Personalizing "The Netflix Experience" with Deep LearningAnoop Deoras
 
Déjà Vu: The Importance of Time and Causality in Recommender Systems
Déjà Vu: The Importance of Time and Causality in Recommender SystemsDéjà Vu: The Importance of Time and Causality in Recommender Systems
Déjà Vu: The Importance of Time and Causality in Recommender SystemsJustin Basilico
 
Recommendation system
Recommendation systemRecommendation system
Recommendation systemRishabh Mehta
 
Deep Learning for Recommender Systems
Deep Learning for Recommender SystemsDeep Learning for Recommender Systems
Deep Learning for Recommender SystemsJustin Basilico
 
Tutorial on Deep Learning in Recommender System, Lars summer school 2019
Tutorial on Deep Learning in Recommender System, Lars summer school 2019Tutorial on Deep Learning in Recommender System, Lars summer school 2019
Tutorial on Deep Learning in Recommender System, Lars summer school 2019Anoop Deoras
 
Fairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Fairness and Popularity Bias in Recommender Systems: an Empirical EvaluationFairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Fairness and Popularity Bias in Recommender Systems: an Empirical EvaluationCataldo Musto
 
Deep Learning for Recommender Systems
Deep Learning for Recommender SystemsDeep Learning for Recommender Systems
Deep Learning for Recommender SystemsYves Raimond
 
Replicable Evaluation of Recommender Systems
Replicable Evaluation of Recommender SystemsReplicable Evaluation of Recommender Systems
Replicable Evaluation of Recommender SystemsAlejandro Bellogin
 
Past, present, and future of Recommender Systems: an industry perspective
Past, present, and future of Recommender Systems: an industry perspectivePast, present, and future of Recommender Systems: an industry perspective
Past, present, and future of Recommender Systems: an industry perspectiveXavier Amatriain
 
Adversarial Attacks for Recommender Systems
Adversarial Attacks for Recommender SystemsAdversarial Attacks for Recommender Systems
Adversarial Attacks for Recommender SystemsWQ Fan
 
Calibrated Recommendations
Calibrated RecommendationsCalibrated Recommendations
Calibrated RecommendationsHarald Steck
 
Recent Trends in Personalization: A Netflix Perspective
Recent Trends in Personalization: A Netflix PerspectiveRecent Trends in Personalization: A Netflix Perspective
Recent Trends in Personalization: A Netflix PerspectiveJustin Basilico
 
Knowledge Graph Embeddings for Recommender Systems
Knowledge Graph Embeddings for Recommender SystemsKnowledge Graph Embeddings for Recommender Systems
Knowledge Graph Embeddings for Recommender SystemsEnrico Palumbo
 
Collaborative Filtering using KNN
Collaborative Filtering using KNNCollaborative Filtering using KNN
Collaborative Filtering using KNNŞeyda Hatipoğlu
 
Tutorial on Sequence Aware Recommender Systems - ACM RecSys 2018
Tutorial on Sequence Aware Recommender Systems - ACM RecSys 2018Tutorial on Sequence Aware Recommender Systems - ACM RecSys 2018
Tutorial on Sequence Aware Recommender Systems - ACM RecSys 2018Massimo Quadrana
 
Recommendation System Explained
Recommendation System ExplainedRecommendation System Explained
Recommendation System ExplainedCrossing Minds
 
Sequential Decision Making in Recommendations
Sequential Decision Making in RecommendationsSequential Decision Making in Recommendations
Sequential Decision Making in RecommendationsJaya Kawale
 
Joint Multisided Exposure Fairness for Search and Recommendation
Joint Multisided Exposure Fairness for Search and RecommendationJoint Multisided Exposure Fairness for Search and Recommendation
Joint Multisided Exposure Fairness for Search and RecommendationBhaskar Mitra
 

What's hot (20)

Personalizing "The Netflix Experience" with Deep Learning
Personalizing "The Netflix Experience" with Deep LearningPersonalizing "The Netflix Experience" with Deep Learning
Personalizing "The Netflix Experience" with Deep Learning
 
Déjà Vu: The Importance of Time and Causality in Recommender Systems
Déjà Vu: The Importance of Time and Causality in Recommender SystemsDéjà Vu: The Importance of Time and Causality in Recommender Systems
Déjà Vu: The Importance of Time and Causality in Recommender Systems
 
Recommender Systems
Recommender SystemsRecommender Systems
Recommender Systems
 
Recommendation system
Recommendation systemRecommendation system
Recommendation system
 
Deep Learning for Recommender Systems
Deep Learning for Recommender SystemsDeep Learning for Recommender Systems
Deep Learning for Recommender Systems
 
Tutorial on Deep Learning in Recommender System, Lars summer school 2019
Tutorial on Deep Learning in Recommender System, Lars summer school 2019Tutorial on Deep Learning in Recommender System, Lars summer school 2019
Tutorial on Deep Learning in Recommender System, Lars summer school 2019
 
Fairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Fairness and Popularity Bias in Recommender Systems: an Empirical EvaluationFairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
Fairness and Popularity Bias in Recommender Systems: an Empirical Evaluation
 
Deep Learning for Recommender Systems
Deep Learning for Recommender SystemsDeep Learning for Recommender Systems
Deep Learning for Recommender Systems
 
Replicable Evaluation of Recommender Systems
Replicable Evaluation of Recommender SystemsReplicable Evaluation of Recommender Systems
Replicable Evaluation of Recommender Systems
 
Recommender system
Recommender systemRecommender system
Recommender system
 
Past, present, and future of Recommender Systems: an industry perspective
Past, present, and future of Recommender Systems: an industry perspectivePast, present, and future of Recommender Systems: an industry perspective
Past, present, and future of Recommender Systems: an industry perspective
 
Adversarial Attacks for Recommender Systems
Adversarial Attacks for Recommender SystemsAdversarial Attacks for Recommender Systems
Adversarial Attacks for Recommender Systems
 
Calibrated Recommendations
Calibrated RecommendationsCalibrated Recommendations
Calibrated Recommendations
 
Recent Trends in Personalization: A Netflix Perspective
Recent Trends in Personalization: A Netflix PerspectiveRecent Trends in Personalization: A Netflix Perspective
Recent Trends in Personalization: A Netflix Perspective
 
Knowledge Graph Embeddings for Recommender Systems
Knowledge Graph Embeddings for Recommender SystemsKnowledge Graph Embeddings for Recommender Systems
Knowledge Graph Embeddings for Recommender Systems
 
Collaborative Filtering using KNN
Collaborative Filtering using KNNCollaborative Filtering using KNN
Collaborative Filtering using KNN
 
Tutorial on Sequence Aware Recommender Systems - ACM RecSys 2018
Tutorial on Sequence Aware Recommender Systems - ACM RecSys 2018Tutorial on Sequence Aware Recommender Systems - ACM RecSys 2018
Tutorial on Sequence Aware Recommender Systems - ACM RecSys 2018
 
Recommendation System Explained
Recommendation System ExplainedRecommendation System Explained
Recommendation System Explained
 
Sequential Decision Making in Recommendations
Sequential Decision Making in RecommendationsSequential Decision Making in Recommendations
Sequential Decision Making in Recommendations
 
Joint Multisided Exposure Fairness for Search and Recommendation
Joint Multisided Exposure Fairness for Search and RecommendationJoint Multisided Exposure Fairness for Search and Recommendation
Joint Multisided Exposure Fairness for Search and Recommendation
 

Similar to Diversity and novelty for recommendation system

Modeling Difficulty in Recommender Systems
Modeling Difficulty in Recommender SystemsModeling Difficulty in Recommender Systems
Modeling Difficulty in Recommender Systemskib_83
 
Ideal-Analytics - Introduction to Version 3.3
Ideal-Analytics - Introduction to Version 3.3Ideal-Analytics - Introduction to Version 3.3
Ideal-Analytics - Introduction to Version 3.3Yamika Mehra
 
Design Patterns Explained: From Analysis through Implementation
Design Patterns Explained: From Analysis through ImplementationDesign Patterns Explained: From Analysis through Implementation
Design Patterns Explained: From Analysis through ImplementationTechWell
 
The Outlook is Cloudy
The Outlook is CloudyThe Outlook is Cloudy
The Outlook is CloudyEduserv
 
Determining Relevance Rankings from Search Click Logs
Determining Relevance Rankings from Search Click LogsDetermining Relevance Rankings from Search Click Logs
Determining Relevance Rankings from Search Click LogsInderjeet Singh
 
Max diff scaling for research access(4)
Max diff scaling for research access(4)Max diff scaling for research access(4)
Max diff scaling for research access(4)QuestionPro
 
Toward the next generation of recommender systems
Toward the next generation of recommender systemsToward the next generation of recommender systems
Toward the next generation of recommender systemsAravindharamanan S
 
CAN I USE THIS? - A Mnemonic for Usability Testing
CAN I USE THIS? - A Mnemonic for Usability TestingCAN I USE THIS? - A Mnemonic for Usability Testing
CAN I USE THIS? - A Mnemonic for Usability TestingDavid Greenlees
 
Mixed Recommendation Algorithm Based on Content, Demographic and Collaborativ...
Mixed Recommendation Algorithm Based on Content, Demographic and Collaborativ...Mixed Recommendation Algorithm Based on Content, Demographic and Collaborativ...
Mixed Recommendation Algorithm Based on Content, Demographic and Collaborativ...IRJET Journal
 
Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)IJERD Editor
 
Ideal-Analytics Product Training
Ideal-Analytics Product TrainingIdeal-Analytics Product Training
Ideal-Analytics Product TrainingYamika Mehra
 
ITS835 enterprise risk managementChapter 3ERM at Mars, Incor.docx
ITS835 enterprise risk managementChapter 3ERM at Mars, Incor.docxITS835 enterprise risk managementChapter 3ERM at Mars, Incor.docx
ITS835 enterprise risk managementChapter 3ERM at Mars, Incor.docxvrickens
 
Rob peglar introduction_analytics _big data_hadoop
Rob peglar introduction_analytics _big data_hadoopRob peglar introduction_analytics _big data_hadoop
Rob peglar introduction_analytics _big data_hadoopGhassan Al-Yafie
 
II-SDV 2014 The Road to Federated Text Mining: Are we there yet? (Guy Singh -...
II-SDV 2014 The Road to Federated Text Mining: Are we there yet? (Guy Singh -...II-SDV 2014 The Road to Federated Text Mining: Are we there yet? (Guy Singh -...
II-SDV 2014 The Road to Federated Text Mining: Are we there yet? (Guy Singh -...Dr. Haxel Consult
 
A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...
A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...
A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...ijfcstjournal
 
A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...
A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...
A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...ijfcstjournal
 
09 introduction to_modeling
09 introduction to_modeling09 introduction to_modeling
09 introduction to_modelingMajong DevJfu
 
ENHANCING THE PERFORMANCE OF E-COMMERCE SOLUTIONS BY FRIENDS RECOMMENDATION S...
ENHANCING THE PERFORMANCE OF E-COMMERCE SOLUTIONS BY FRIENDS RECOMMENDATION S...ENHANCING THE PERFORMANCE OF E-COMMERCE SOLUTIONS BY FRIENDS RECOMMENDATION S...
ENHANCING THE PERFORMANCE OF E-COMMERCE SOLUTIONS BY FRIENDS RECOMMENDATION S...IJCI JOURNAL
 
Measuring the Quality of Web Content using Factual Information
Measuring the Quality of Web Content using Factual InformationMeasuring the Quality of Web Content using Factual Information
Measuring the Quality of Web Content using Factual InformationElisabeth Lex
 

Similar to Diversity and novelty for recommendation system (20)

Modeling Difficulty in Recommender Systems
Modeling Difficulty in Recommender SystemsModeling Difficulty in Recommender Systems
Modeling Difficulty in Recommender Systems
 
Ideal-Analytics - Introduction to Version 3.3
Ideal-Analytics - Introduction to Version 3.3Ideal-Analytics - Introduction to Version 3.3
Ideal-Analytics - Introduction to Version 3.3
 
Design Patterns Explained: From Analysis through Implementation
Design Patterns Explained: From Analysis through ImplementationDesign Patterns Explained: From Analysis through Implementation
Design Patterns Explained: From Analysis through Implementation
 
The Outlook is Cloudy
The Outlook is CloudyThe Outlook is Cloudy
The Outlook is Cloudy
 
Determining Relevance Rankings from Search Click Logs
Determining Relevance Rankings from Search Click LogsDetermining Relevance Rankings from Search Click Logs
Determining Relevance Rankings from Search Click Logs
 
Max diff scaling for research access(4)
Max diff scaling for research access(4)Max diff scaling for research access(4)
Max diff scaling for research access(4)
 
Toward the next generation of recommender systems
Toward the next generation of recommender systemsToward the next generation of recommender systems
Toward the next generation of recommender systems
 
CAN I USE THIS? - A Mnemonic for Usability Testing
CAN I USE THIS? - A Mnemonic for Usability TestingCAN I USE THIS? - A Mnemonic for Usability Testing
CAN I USE THIS? - A Mnemonic for Usability Testing
 
Mixed Recommendation Algorithm Based on Content, Demographic and Collaborativ...
Mixed Recommendation Algorithm Based on Content, Demographic and Collaborativ...Mixed Recommendation Algorithm Based on Content, Demographic and Collaborativ...
Mixed Recommendation Algorithm Based on Content, Demographic and Collaborativ...
 
Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)Welcome to International Journal of Engineering Research and Development (IJERD)
Welcome to International Journal of Engineering Research and Development (IJERD)
 
44 49
44 4944 49
44 49
 
Ideal-Analytics Product Training
Ideal-Analytics Product TrainingIdeal-Analytics Product Training
Ideal-Analytics Product Training
 
ITS835 enterprise risk managementChapter 3ERM at Mars, Incor.docx
ITS835 enterprise risk managementChapter 3ERM at Mars, Incor.docxITS835 enterprise risk managementChapter 3ERM at Mars, Incor.docx
ITS835 enterprise risk managementChapter 3ERM at Mars, Incor.docx
 
Rob peglar introduction_analytics _big data_hadoop
Rob peglar introduction_analytics _big data_hadoopRob peglar introduction_analytics _big data_hadoop
Rob peglar introduction_analytics _big data_hadoop
 
II-SDV 2014 The Road to Federated Text Mining: Are we there yet? (Guy Singh -...
II-SDV 2014 The Road to Federated Text Mining: Are we there yet? (Guy Singh -...II-SDV 2014 The Road to Federated Text Mining: Are we there yet? (Guy Singh -...
II-SDV 2014 The Road to Federated Text Mining: Are we there yet? (Guy Singh -...
 
A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...
A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...
A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...
 
A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...
A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...
A NOVEL APPROACH FOR PERFORMANCE ENHANCEMENT OF E-COMMERCE SOLUTIONS BY FRIEN...
 
09 introduction to_modeling
09 introduction to_modeling09 introduction to_modeling
09 introduction to_modeling
 
ENHANCING THE PERFORMANCE OF E-COMMERCE SOLUTIONS BY FRIENDS RECOMMENDATION S...
ENHANCING THE PERFORMANCE OF E-COMMERCE SOLUTIONS BY FRIENDS RECOMMENDATION S...ENHANCING THE PERFORMANCE OF E-COMMERCE SOLUTIONS BY FRIENDS RECOMMENDATION S...
ENHANCING THE PERFORMANCE OF E-COMMERCE SOLUTIONS BY FRIENDS RECOMMENDATION S...
 
Measuring the Quality of Web Content using Factual Information
Measuring the Quality of Web Content using Factual InformationMeasuring the Quality of Web Content using Factual Information
Measuring the Quality of Web Content using Factual Information
 

Recently uploaded

Salient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functionsSalient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functionsKarakKing
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.MaryamAhmad92
 
Food safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfFood safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfSherif Taha
 
Micro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfMicro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfPoh-Sun Goh
 
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdfUnit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdfDr Vijay Vishwakarma
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...ZurliaSoop
 
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptxHMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptxEsquimalt MFRC
 
How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17Celine George
 
SOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning PresentationSOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning Presentationcamerronhm
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxheathfieldcps1
 
Towards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptxTowards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptxJisc
 
This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.christianmathematics
 
Fostering Friendships - Enhancing Social Bonds in the Classroom
Fostering Friendships - Enhancing Social Bonds  in the ClassroomFostering Friendships - Enhancing Social Bonds  in the Classroom
Fostering Friendships - Enhancing Social Bonds in the ClassroomPooky Knightsmith
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxVishalSingh1417
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfAdmir Softic
 
Graduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - EnglishGraduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - Englishneillewis46
 
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptxMaritesTamaniVerdade
 
Interdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptxInterdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptxPooja Bhuva
 

Recently uploaded (20)

Salient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functionsSalient Features of India constitution especially power and functions
Salient Features of India constitution especially power and functions
 
ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.
 
Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
Food safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfFood safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdf
 
Micro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdfMicro-Scholarship, What it is, How can it help me.pdf
Micro-Scholarship, What it is, How can it help me.pdf
 
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdfUnit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdf
 
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
Jual Obat Aborsi Hongkong ( Asli No.1 ) 085657271886 Obat Penggugur Kandungan...
 
Spatium Project Simulation student brief
Spatium Project Simulation student briefSpatium Project Simulation student brief
Spatium Project Simulation student brief
 
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptxHMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
 
How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17
 
SOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning PresentationSOC 101 Demonstration of Learning Presentation
SOC 101 Demonstration of Learning Presentation
 
The basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptxThe basics of sentences session 3pptx.pptx
The basics of sentences session 3pptx.pptx
 
Towards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptxTowards a code of practice for AI in AT.pptx
Towards a code of practice for AI in AT.pptx
 
This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.This PowerPoint helps students to consider the concept of infinity.
This PowerPoint helps students to consider the concept of infinity.
 
Fostering Friendships - Enhancing Social Bonds in the Classroom
Fostering Friendships - Enhancing Social Bonds  in the ClassroomFostering Friendships - Enhancing Social Bonds  in the Classroom
Fostering Friendships - Enhancing Social Bonds in the Classroom
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptx
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
Graduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - EnglishGraduate Outcomes Presentation Slides - English
Graduate Outcomes Presentation Slides - English
 
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
 
Interdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptxInterdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptx
 

Diversity and novelty for recommendation system

  • 1. A simple survey of Diversity and novelty metrics for recommender systems Reporter: 孙建凯 2012.07.11
  • 2. Move beyond accuracy metrics  while the majority of algorithms proposed in recommender systems literature have focused on improving recommendation accuracy  other important aspects of recommendation quality, such as the diversity of recommendations, have often been overlooked.  The recommendations that are most accurate according to the standard metrics are sometimes not the recommendations that are most useful to users[1] 2 Copyright © 2012 by IRLAB@SDU
  • 3. Diversity and Novelty  Accurate is not always good: How Accuracy Metrics have hurt Recommender Systems GroupLensResearch,CHI'06  Copyright © 2012 by IRLAB@SDU
  • 4. Accuracy does not tell the whole story Copyright © 2012 by IRLAB@SDU
  • 5. Diversity  Individual Diversity  Aggregate Diversity Copyright © 2012 by IRLAB@SDU
  • 6. Individual Diversity  Diversity Difficulty[3]  Average dissimilarity between all pairs of items recommended to a given user(intra-list similarity) [2,4] Copyright © 2012 by IRLAB@SDU
  • 7. Diversity Difficulty  What We Talk About When We Talk About Diversity [DDR’12 Northeastern University USA]  Like query difficulty in IR  For a specific query and corpus, query difficulty is a measure of how successful the average search engine should be at ad-hoc retrieval. Copyright © 2012 by IRLAB@SDU
  • 8. Diversity Difficulty  Diversity Difficulty is defined with respect to a query and a corpus.  Describes diversity-the number of subtopics which are covered by a list;  Describes novelty-which is inversely proportional to the number of times a list repeats a subtopic Copyright © 2012 by IRLAB@SDU
  • 9. Finding needles in the haystack  Imagine a query with 10 subtopics ,1000 documents relevant to only the first subtopic, and each of the remaining subtopics covered by a single, unique document.  On the other hand ,if there are large numbers of documents relevant to multiple subtopics, it would be easy to produce a diversity list. Copyright © 2012 by IRLAB@SDU
  • 10. Diversity Difficulty function  The maximum amount of diversity achievable by any ranked list-dmax  The ease with a system can produce a diverse ranked list.-dmean  Harmonic function Copyright © 2012 by IRLAB@SDU
  • 11. Examples Copyright © 2012 by IRLAB@SDU
  • 12. Improving Recommendation Lists Through Topic Diversification  Introduce the intra-list similarity metric to access the topic diversification of recommendation lists and the topic diversification approach for decreasing the intra-list similarity  Average dissimilarity between all pairs of items recommended to a given user Copyright © 2012 by IRLAB@SDU
  • 13. Intra-list Similarity Copyright © 2012 by IRLAB@SDU
  • 14. Taxonomy-based similarity Metrics  Instantiate c with their metric for taxonomy- driven filtering.[5] Copyright © 2012 by IRLAB@SDU
  • 15. Topic Diversification Algorithm Algorithm A brief textual sketch Copyright © 2012 by IRLAB@SDU
  • 16. Experiments  precision  diversity
  • 17. Aggregate Diversity  improving recommendation Diversity using ranking- based techniques[IEEE transaction’12]  Use the total number of distinct items recommended across all users as an aggregate diversity measure, define as follows: Copyright © 2012 by IRLAB@SDU
  • 18. General overview of ranking-based approaches for improving diversity Copyright © 2012 by IRLAB@SDU
  • 19. Re-Ranking Approach Copyright © 2012 by IRLAB@SDU
  • 20. Other Re-ranking Approach Copyright © 2012 by IRLAB@SDU
  • 21. Other Re-ranking Approach Copyright © 2012 by IRLAB@SDU
  • 22. Other Re-ranking Approach Copyright © 2012 by IRLAB@SDU
  • 23. Other Re-ranking Approach Copyright © 2012 by IRLAB@SDU
  • 24. Other Re-ranking Approach Copyright © 2012 by IRLAB@SDU
  • 25. Other Re-ranking Approach Copyright © 2012 by IRLAB@SDU
  • 26. Combining Ranking Approaches  Many possible ways to combine several ranking functions  In this paper , linear combination  Open issue: letor ? Neural network? Copyright © 2012 by IRLAB@SDU
  • 27. Entropy  A study of Heterogeneity in Recommendations for a social Music Service[6] Copyright © 2012 by IRLAB@SDU
  • 28. Open issue:probability Copyright © 2012 by IRLAB@SDU
  • 29. Entropy Aggregate Entropy: Individual Entropy:  Item popularity  subtopic popularity? between lists? Copyright © 2012 by IRLAB@SDU
  • 30. Bipartite network  Bipartite network projection and personal recommendation[Tao Zhou, Physical Review]  Solving the apparent diversity-accuracy dilemma of recommender systems[Tao Zhou] Copyright © 2012 by IRLAB@SDU
  • 31. Illustration of resource-allocation process in bipartite network Copyright © 2012 by IRLAB@SDU
  • 32. Solving the apparent diversity-accuracy dilemma heats probs Copyright © 2012 by IRLAB@SDU
  • 33. Hybrid Methods weight hybrid Copyright © 2012 by IRLAB@SDU
  • 34. Diversity Measure Copyright © 2012 by IRLAB@SDU
  • 35. Surprisal/novelty Copyright © 2012 by IRLAB@SDU
  • 36. Results-why better? Copyright © 2012 by IRLAB@SDU
  • 37. Surprise me  Tangent: A novel, ‘surprise me’, recommendation algorithm [kdd’09] Copyright © 2012 by IRLAB@SDU
  • 38. Framework of Tangent Algorithm  Suggest items which are not only relevant to user preference but also have a large connectivity to other groups.  Consisting three parts as follows:  1 Calculate relevance score(RS) for each node  2 Calculate bridging score(BRS) for each node  3 Compute the Tangent score by somehow merging two criteria above Copyright © 2012 by IRLAB@SDU
  • 39. Case study Copyright © 2012 by IRLAB@SDU
  • 40. Case study Copyright © 2012 by IRLAB@SDU
  • 41. Call for papers  September 20, 2012 Copyright © 2012 by IRLAB@SDU
  • 42. Reference  1. Accurate is not always good: How Accuracy Metrics have hurt Recommender Systems  2.improving recommendation Diversity using ranking-based techniques  3. What We Talk About When We Talk About Diversity  4. Improving Recommendation Lists Through Topic Diversification  5. Taxonomy-driven computation of product recommendations Copyright © 2012 by IRLAB@SDU
  • 43. Reference  6. A study of Heterogeneity in Recommendations for a social Music Service  7. Bipartite network projection and personal recommendation  8.Solving the apparent diversity-accuracy dilemma of recommender systems  9. Tangent: A novel, ‘surprise me’, recommendation algorithm Copyright © 2012 by IRLAB@SDU
  • 44.  thanks Copyright © 2012 by IRLAB@SDU