SlideShare a Scribd company logo
Recommender
Systems and
Misinformation:
The problem or the solution?
Miriam Fernández, Open University, United Kingdom
Alejandro Bellogín, Universidad Autónoma de Madrid, Spain
Examples of misinformation
https://languages.oup.com/word-of-the-year/2016/ 2
Examples of misinformation
https://www.bbc.com/news/stories-52731624 3
Factors that influence the spread of misinformation online:
● How information is constructed and presented
● Personality, values, and emotions of the users
● Characteristics of digital platforms
● Algorithms that power the recommendation of information in those platforms
Misinformation spread
4
Our goal
Explore the effect of existing algorithms on the recommendation of false and
misleading information
Understand which techniques are more prone to spread misinformation, and under which
circumstances.
How can their internal functioning be modified, or adapted, to counter this behaviour?
USER
SYSTEM
Preferences
Model
Interaction
Recommendation
5
https://edition.cnn.com/2019/03/22/tech/twitter-algorithm-political-rhetoric/index.html
Current solutions
https://www.cnbc.com/2017/12/21/facebook-found-a-better-way-to-fight-fake-news.html
6
https://edition.cnn.com/2019/03/22/tech/twitter-algorithm-political-rhetoric/index.html
Current “solutions”
https://www.cnbc.com/2017/12/21/facebook-found-a-better-way-to-fight-fake-news.html
7
Our approach
Problem Dimensions: which dimensions of
the misinformation problem affect the
behaviour of RS?
Analysis of Recommendation Algorithms:
analyse how existing algorithms improve
or worsen the spread of misinformation
Human-centred Evaluation: modify
existing evaluation methods and metrics
(dissonance vs. satisfaction)
Adaptation, Modification and Vigilance:
adapt existing algorithms and track their
impact over time (vigilance).
which recommendation algorithms are more
prone to spread misinformation, and under
which circumstances?
8
Content: Different forms (newspaper articles, blog posts, social media posts),
topics (health, elections), formats (text, images, videos), framing (false news,
rumours, conspiracy theories), origin (news outlets, social contacts, public
figures), time
Users: Different motivations, personalities, values, emotions and susceptibility
influence the spread of misinformation
Platform & Network Features: Platforms are designed differently (content
limitations, sharing permissions) & have different typology and topology of
network structure.
Others: global events, presence of malicious actors, presence of checked facts
Misinformation: Problem Dimensions
A global problem,
multiple dimensions
(human, sociological, technological)
Dimensions that intersect between recommendation and misinformation
9
Analysis of Recommendation Algorithms
Which recommendation techniques are more prone to suggest misinformative items to
users and why?
CF methods neglect any information about the items and their misinformative features.
They can help us to understand the impact of user-item interactions.
CB approaches use content and therefore require analysing NL and its inherent subtleties.
Hybrid methods combine content analysis with user-time interactions.
Are they therefore more prone to spread misinformation?
User & Item Profiles: Multiple representations can be considered.
How do these representations influence the spread of misinformation?
10
Human-centred Evaluation
Metrics that focus on computing a balanced degree of user satisfaction and discomfort
(introducing opposing views) may help to combat misperceptions.
Same information, opposing views ≠ diversity (novel information)
Datasets: We need users / items & information about their credibility + user-item ratings
- NELA-GT-2018 dataset (713 misinforming articles) → no user profiles / ratings
- COVID-19 Poynter dataset (603 misinforming articles/posts) → no user profiles / ratings
- NewsReel: users, articles and ratings → no information about item credibility
Measure: how can we evaluate when the task has been successfully addressed?
11
Adaptation, Modification, and Vigilance
Social Science and Psychology
studies: simply presenting people
with corrective information is
likely to fail in changing their
salient beliefs.
- Providing an explanation
rather than a simple refute
- Exposing users to related
but disconfirming stories
- Revealing similarities with
the opposing groups
Adaptation/Modification: the adaptation of existing algorithms
to counter the misinformation recommendation problem should
build on existing social science and psychology theory.
- Profile users to better capture motivations
- RS that introduce small degrees of opposing views
- RS focus on similarity and dissimilarity
- Explanations
Vigilance:
- Dynamics of misinformation captured over time
- Algorithms are adapted
- Proposed adaptations do not back-fire (ethics!)
12
Recommender systems are often accused of feeding and reinforcing the interaction cycle
BUT, they could be part of the solution, if we understand:
● How misinformation is spread
● How such mechanisms are reinforced
○ And to what extent, depending on the technique
● How we can adapt the algorithms to counter these effects
Our hypothesis: build on social science and psychology theories
Discussion
13
Current plan
14
Starting with a COVID-related Poynter dataset
It contains news items classified as reliable or not
We are collecting Twitter user profiles
Challenge 1: how many users can we collect for each news item? (cold items)
Challenge 2: how many items do user profiles actually contain? (cold users)
Challenge 3: what is a realistic ratio between misinformation/normal items?
Question: are there datasets with this information combined?
Next step: run and evaluate CF recommenders
Next challenges???
CREDITS: This presentation template was created by
Slidesgo, including icons by Flaticon, infographics &
images by Freepik and illustrations by Stories
Recommender Systems
and Misinformation:
The problem or the solution?
Miriam Fernández, Open University, United Kingdom
Alejandro Bellogín, Universidad Autónoma de Madrid, Spain
15

More Related Content

What's hot

Fedarated learning
Fedarated learningFedarated learning
Fedarated learning
VaishakhKP1
 
Approaches to Sentiment Analysis
Approaches to Sentiment AnalysisApproaches to Sentiment Analysis
Approaches to Sentiment Analysis
Nihar Suryawanshi
 
CounterFactual Explanations.pdf
CounterFactual Explanations.pdfCounterFactual Explanations.pdf
CounterFactual Explanations.pdf
Bong-Ho Lee
 
[4차]넷플릭스 알고리즘 분석(151106)
[4차]넷플릭스 알고리즘 분석(151106)[4차]넷플릭스 알고리즘 분석(151106)
[4차]넷플릭스 알고리즘 분석(151106)
고려대학교 정보기술경영학회 : ITS
 
Fairness and Bias in Machine Learning
Fairness and Bias in Machine LearningFairness and Bias in Machine Learning
Fairness and Bias in Machine Learning
Surya Dutta
 
Generative AI and Security (1).pptx.pdf
Generative AI and Security (1).pptx.pdfGenerative AI and Security (1).pptx.pdf
Generative AI and Security (1).pptx.pdf
Priyanka Aash
 
Generative models
Generative modelsGenerative models
Generative models
Birger Moell
 
Recommender systems: Content-based and collaborative filtering
Recommender systems: Content-based and collaborative filteringRecommender systems: Content-based and collaborative filtering
Recommender systems: Content-based and collaborative filtering
Viet-Trung TRAN
 
OpenAI’s GPT 3 Language Model - guest Steve Omohundro
OpenAI’s GPT 3 Language Model - guest Steve OmohundroOpenAI’s GPT 3 Language Model - guest Steve Omohundro
OpenAI’s GPT 3 Language Model - guest Steve Omohundro
Numenta
 
What Is GPT-3 And Why Is It Revolutionizing Artificial Intelligence?
What Is GPT-3 And Why Is It Revolutionizing Artificial Intelligence?What Is GPT-3 And Why Is It Revolutionizing Artificial Intelligence?
What Is GPT-3 And Why Is It Revolutionizing Artificial Intelligence?
Bernard Marr
 
Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)
Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)
Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)
Sergey Karayev
 
An introduction to Recommender Systems
An introduction to Recommender SystemsAn introduction to Recommender Systems
An introduction to Recommender Systems
David Zibriczky
 
Prompting is an art / Sztuka promptowania
Prompting is an art / Sztuka promptowaniaPrompting is an art / Sztuka promptowania
Prompting is an art / Sztuka promptowania
Michal Jaskolski
 
Federated Learning
Federated LearningFederated Learning
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
David Talby
 
Social Media Sentiment Analysis
Social Media Sentiment AnalysisSocial Media Sentiment Analysis
Social Media Sentiment Analysis
Mehmet Burak Akgün
 
Build a Recommendation Engine using Amazon Machine Learning in Real-time
Build a Recommendation Engine using Amazon Machine Learning in Real-timeBuild a Recommendation Engine using Amazon Machine Learning in Real-time
Build a Recommendation Engine using Amazon Machine Learning in Real-time
Amazon Web Services
 
chatgpt-privacy and security.pptx
chatgpt-privacy and security.pptxchatgpt-privacy and security.pptx
chatgpt-privacy and security.pptx
Deepak Kumar
 
Large Language Models Bootcamp
Large Language Models BootcampLarge Language Models Bootcamp
Large Language Models Bootcamp
Data Science Dojo
 
Building NLP applications with Transformers
Building NLP applications with TransformersBuilding NLP applications with Transformers
Building NLP applications with Transformers
Julien SIMON
 

What's hot (20)

Fedarated learning
Fedarated learningFedarated learning
Fedarated learning
 
Approaches to Sentiment Analysis
Approaches to Sentiment AnalysisApproaches to Sentiment Analysis
Approaches to Sentiment Analysis
 
CounterFactual Explanations.pdf
CounterFactual Explanations.pdfCounterFactual Explanations.pdf
CounterFactual Explanations.pdf
 
[4차]넷플릭스 알고리즘 분석(151106)
[4차]넷플릭스 알고리즘 분석(151106)[4차]넷플릭스 알고리즘 분석(151106)
[4차]넷플릭스 알고리즘 분석(151106)
 
Fairness and Bias in Machine Learning
Fairness and Bias in Machine LearningFairness and Bias in Machine Learning
Fairness and Bias in Machine Learning
 
Generative AI and Security (1).pptx.pdf
Generative AI and Security (1).pptx.pdfGenerative AI and Security (1).pptx.pdf
Generative AI and Security (1).pptx.pdf
 
Generative models
Generative modelsGenerative models
Generative models
 
Recommender systems: Content-based and collaborative filtering
Recommender systems: Content-based and collaborative filteringRecommender systems: Content-based and collaborative filtering
Recommender systems: Content-based and collaborative filtering
 
OpenAI’s GPT 3 Language Model - guest Steve Omohundro
OpenAI’s GPT 3 Language Model - guest Steve OmohundroOpenAI’s GPT 3 Language Model - guest Steve Omohundro
OpenAI’s GPT 3 Language Model - guest Steve Omohundro
 
What Is GPT-3 And Why Is It Revolutionizing Artificial Intelligence?
What Is GPT-3 And Why Is It Revolutionizing Artificial Intelligence?What Is GPT-3 And Why Is It Revolutionizing Artificial Intelligence?
What Is GPT-3 And Why Is It Revolutionizing Artificial Intelligence?
 
Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)
Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)
Lecture 6: Infrastructure & Tooling (Full Stack Deep Learning - Spring 2021)
 
An introduction to Recommender Systems
An introduction to Recommender SystemsAn introduction to Recommender Systems
An introduction to Recommender Systems
 
Prompting is an art / Sztuka promptowania
Prompting is an art / Sztuka promptowaniaPrompting is an art / Sztuka promptowania
Prompting is an art / Sztuka promptowania
 
Federated Learning
Federated LearningFederated Learning
Federated Learning
 
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
Large Language Models, No-Code, and Responsible AI - Trends in Applied NLP in...
 
Social Media Sentiment Analysis
Social Media Sentiment AnalysisSocial Media Sentiment Analysis
Social Media Sentiment Analysis
 
Build a Recommendation Engine using Amazon Machine Learning in Real-time
Build a Recommendation Engine using Amazon Machine Learning in Real-timeBuild a Recommendation Engine using Amazon Machine Learning in Real-time
Build a Recommendation Engine using Amazon Machine Learning in Real-time
 
chatgpt-privacy and security.pptx
chatgpt-privacy and security.pptxchatgpt-privacy and security.pptx
chatgpt-privacy and security.pptx
 
Large Language Models Bootcamp
Large Language Models BootcampLarge Language Models Bootcamp
Large Language Models Bootcamp
 
Building NLP applications with Transformers
Building NLP applications with TransformersBuilding NLP applications with Transformers
Building NLP applications with Transformers
 

Similar to Recommender Systems and Misinformation: The Problem or the Solution?

Mitigating Influence of Disinformation Propagation Using Uncertainty-Based Op...
Mitigating Influence of Disinformation Propagation Using Uncertainty-Based Op...Mitigating Influence of Disinformation Propagation Using Uncertainty-Based Op...
Mitigating Influence of Disinformation Propagation Using Uncertainty-Based Op...
Shakas Technologies
 
'Humans still needed' - research project reveals impact of artificial intelli...
'Humans still needed' - research project reveals impact of artificial intelli...'Humans still needed' - research project reveals impact of artificial intelli...
'Humans still needed' - research project reveals impact of artificial intelli...
Chartered Institute of Public Relations
 
IPS poster 2014
IPS poster 2014IPS poster 2014
IPS poster 2014
Steven Chan, MD MBA
 
Social media risks guide
Social media risks guideSocial media risks guide
Social media risks guide
AstalapulosListestos
 
Social Media Anlytics
Social Media AnlyticsSocial Media Anlytics
Social Media Anlytics
Marcus Estanislao
 
Webinar Social Media Analytics - Using KNIME
Webinar Social Media Analytics - Using KNIMEWebinar Social Media Analytics - Using KNIME
Webinar Social Media Analytics - Using KNIME
Estanislao Training & Solution
 
IRJET- Big Data Driven Information Diffusion Analytics and Control on Social ...
IRJET- Big Data Driven Information Diffusion Analytics and Control on Social ...IRJET- Big Data Driven Information Diffusion Analytics and Control on Social ...
IRJET- Big Data Driven Information Diffusion Analytics and Control on Social ...
IRJET Journal
 
FakeNewsDetector.pptx
FakeNewsDetector.pptxFakeNewsDetector.pptx
FakeNewsDetector.pptx
SANDEEPMISHRA607554
 
Prepare a 2-page interprofessional staff update on HIPAA and appropr
Prepare a 2-page interprofessional staff update on HIPAA and approprPrepare a 2-page interprofessional staff update on HIPAA and appropr
Prepare a 2-page interprofessional staff update on HIPAA and appropr
LilianaJohansen814
 
ifib Lunchbag: CHI2018 Highlights - Algorithms in (Social) Practice and more
ifib Lunchbag: CHI2018 Highlights - Algorithms in (Social) Practice and moreifib Lunchbag: CHI2018 Highlights - Algorithms in (Social) Practice and more
ifib Lunchbag: CHI2018 Highlights - Algorithms in (Social) Practice and more
hen_drik
 
Trust & Predictive Technologies 2016
Trust & Predictive Technologies 2016Trust & Predictive Technologies 2016
Trust & Predictive Technologies 2016
Edelman
 
Mission: Possible! Your cognitive future in government
Mission: Possible! Your cognitive future in governmentMission: Possible! Your cognitive future in government
Mission: Possible! Your cognitive future in government
IBM Government
 
Pharma Social Media Listening: Unlocking Hidden Insights | Whitepaper
Pharma Social Media Listening: Unlocking Hidden Insights | WhitepaperPharma Social Media Listening: Unlocking Hidden Insights | Whitepaper
Pharma Social Media Listening: Unlocking Hidden Insights | Whitepaper
RNayak3
 
Unlocking Hidden Insights for Pharma with Social Media Listening
Unlocking Hidden Insights for Pharma with Social Media ListeningUnlocking Hidden Insights for Pharma with Social Media Listening
Unlocking Hidden Insights for Pharma with Social Media Listening
RNayak3
 
Data Collection Tool Used For Information About Individuals
Data Collection Tool Used For Information About IndividualsData Collection Tool Used For Information About Individuals
Data Collection Tool Used For Information About Individuals
Christy Hunt
 
Make sure it is in APA 7 format and at least 3-4 paragraphs and refe.docx
Make sure it is in APA 7 format and at least 3-4 paragraphs and refe.docxMake sure it is in APA 7 format and at least 3-4 paragraphs and refe.docx
Make sure it is in APA 7 format and at least 3-4 paragraphs and refe.docx
endawalling
 
Social Media Datasets for Analysis and Modeling Drug Usage
Social Media Datasets for Analysis and Modeling Drug UsageSocial Media Datasets for Analysis and Modeling Drug Usage
Social Media Datasets for Analysis and Modeling Drug Usage
ijtsrd
 
Univ. of IL Physicians Q Study
Univ. of IL Physicians Q StudyUniv. of IL Physicians Q Study
Univ. of IL Physicians Q Study
David Donohue
 
4040 2 Protected Health Information and Confidentiality Best Practices.docx
4040 2 Protected Health Information and Confidentiality Best Practices.docx4040 2 Protected Health Information and Confidentiality Best Practices.docx
4040 2 Protected Health Information and Confidentiality Best Practices.docx
write4
 
4040 2 Protected Health Information and Confidentiality Best Practices.docx
4040 2 Protected Health Information and Confidentiality Best Practices.docx4040 2 Protected Health Information and Confidentiality Best Practices.docx
4040 2 Protected Health Information and Confidentiality Best Practices.docx
write12
 

Similar to Recommender Systems and Misinformation: The Problem or the Solution? (20)

Mitigating Influence of Disinformation Propagation Using Uncertainty-Based Op...
Mitigating Influence of Disinformation Propagation Using Uncertainty-Based Op...Mitigating Influence of Disinformation Propagation Using Uncertainty-Based Op...
Mitigating Influence of Disinformation Propagation Using Uncertainty-Based Op...
 
'Humans still needed' - research project reveals impact of artificial intelli...
'Humans still needed' - research project reveals impact of artificial intelli...'Humans still needed' - research project reveals impact of artificial intelli...
'Humans still needed' - research project reveals impact of artificial intelli...
 
IPS poster 2014
IPS poster 2014IPS poster 2014
IPS poster 2014
 
Social media risks guide
Social media risks guideSocial media risks guide
Social media risks guide
 
Social Media Anlytics
Social Media AnlyticsSocial Media Anlytics
Social Media Anlytics
 
Webinar Social Media Analytics - Using KNIME
Webinar Social Media Analytics - Using KNIMEWebinar Social Media Analytics - Using KNIME
Webinar Social Media Analytics - Using KNIME
 
IRJET- Big Data Driven Information Diffusion Analytics and Control on Social ...
IRJET- Big Data Driven Information Diffusion Analytics and Control on Social ...IRJET- Big Data Driven Information Diffusion Analytics and Control on Social ...
IRJET- Big Data Driven Information Diffusion Analytics and Control on Social ...
 
FakeNewsDetector.pptx
FakeNewsDetector.pptxFakeNewsDetector.pptx
FakeNewsDetector.pptx
 
Prepare a 2-page interprofessional staff update on HIPAA and appropr
Prepare a 2-page interprofessional staff update on HIPAA and approprPrepare a 2-page interprofessional staff update on HIPAA and appropr
Prepare a 2-page interprofessional staff update on HIPAA and appropr
 
ifib Lunchbag: CHI2018 Highlights - Algorithms in (Social) Practice and more
ifib Lunchbag: CHI2018 Highlights - Algorithms in (Social) Practice and moreifib Lunchbag: CHI2018 Highlights - Algorithms in (Social) Practice and more
ifib Lunchbag: CHI2018 Highlights - Algorithms in (Social) Practice and more
 
Trust & Predictive Technologies 2016
Trust & Predictive Technologies 2016Trust & Predictive Technologies 2016
Trust & Predictive Technologies 2016
 
Mission: Possible! Your cognitive future in government
Mission: Possible! Your cognitive future in governmentMission: Possible! Your cognitive future in government
Mission: Possible! Your cognitive future in government
 
Pharma Social Media Listening: Unlocking Hidden Insights | Whitepaper
Pharma Social Media Listening: Unlocking Hidden Insights | WhitepaperPharma Social Media Listening: Unlocking Hidden Insights | Whitepaper
Pharma Social Media Listening: Unlocking Hidden Insights | Whitepaper
 
Unlocking Hidden Insights for Pharma with Social Media Listening
Unlocking Hidden Insights for Pharma with Social Media ListeningUnlocking Hidden Insights for Pharma with Social Media Listening
Unlocking Hidden Insights for Pharma with Social Media Listening
 
Data Collection Tool Used For Information About Individuals
Data Collection Tool Used For Information About IndividualsData Collection Tool Used For Information About Individuals
Data Collection Tool Used For Information About Individuals
 
Make sure it is in APA 7 format and at least 3-4 paragraphs and refe.docx
Make sure it is in APA 7 format and at least 3-4 paragraphs and refe.docxMake sure it is in APA 7 format and at least 3-4 paragraphs and refe.docx
Make sure it is in APA 7 format and at least 3-4 paragraphs and refe.docx
 
Social Media Datasets for Analysis and Modeling Drug Usage
Social Media Datasets for Analysis and Modeling Drug UsageSocial Media Datasets for Analysis and Modeling Drug Usage
Social Media Datasets for Analysis and Modeling Drug Usage
 
Univ. of IL Physicians Q Study
Univ. of IL Physicians Q StudyUniv. of IL Physicians Q Study
Univ. of IL Physicians Q Study
 
4040 2 Protected Health Information and Confidentiality Best Practices.docx
4040 2 Protected Health Information and Confidentiality Best Practices.docx4040 2 Protected Health Information and Confidentiality Best Practices.docx
4040 2 Protected Health Information and Confidentiality Best Practices.docx
 
4040 2 Protected Health Information and Confidentiality Best Practices.docx
4040 2 Protected Health Information and Confidentiality Best Practices.docx4040 2 Protected Health Information and Confidentiality Best Practices.docx
4040 2 Protected Health Information and Confidentiality Best Practices.docx
 

More from Alejandro Bellogin

Revisiting neighborhood-based recommenders for temporal scenarios
Revisiting neighborhood-based recommenders for temporal scenariosRevisiting neighborhood-based recommenders for temporal scenarios
Revisiting neighborhood-based recommenders for temporal scenarios
Alejandro Bellogin
 
Evaluating decision-aware recommender systems
Evaluating decision-aware recommender systemsEvaluating decision-aware recommender systems
Evaluating decision-aware recommender systems
Alejandro Bellogin
 
Replicable Evaluation of Recommender Systems
Replicable Evaluation of Recommender SystemsReplicable Evaluation of Recommender Systems
Replicable Evaluation of Recommender Systems
Alejandro Bellogin
 
Implicit vs Explicit trust in Social Matrix Factorization
Implicit vs Explicit trust in Social Matrix FactorizationImplicit vs Explicit trust in Social Matrix Factorization
Implicit vs Explicit trust in Social Matrix Factorization
Alejandro Bellogin
 
RiVal - A toolkit to foster reproducibility in Recommender System evaluation
RiVal - A toolkit to foster reproducibility in Recommender System evaluationRiVal - A toolkit to foster reproducibility in Recommender System evaluation
RiVal - A toolkit to foster reproducibility in Recommender System evaluation
Alejandro Bellogin
 
HT2014 Tutorial: Evaluating Recommender Systems - Ensuring Replicability of E...
HT2014 Tutorial: Evaluating Recommender Systems - Ensuring Replicability of E...HT2014 Tutorial: Evaluating Recommender Systems - Ensuring Replicability of E...
HT2014 Tutorial: Evaluating Recommender Systems - Ensuring Replicability of E...
Alejandro Bellogin
 
CWI @ Contextual Suggestion track - TREC 2013
CWI @ Contextual Suggestion track - TREC 2013CWI @ Contextual Suggestion track - TREC 2013
CWI @ Contextual Suggestion track - TREC 2013
Alejandro Bellogin
 
CWI @ Federated Web Track - TREC 2013
CWI @ Federated Web Track - TREC 2013CWI @ Federated Web Track - TREC 2013
CWI @ Federated Web Track - TREC 2013
Alejandro Bellogin
 
Probabilistic Collaborative Filtering with Negative Cross Entropy
Probabilistic Collaborative Filtering with Negative Cross EntropyProbabilistic Collaborative Filtering with Negative Cross Entropy
Probabilistic Collaborative Filtering with Negative Cross Entropy
Alejandro Bellogin
 
Understanding Similarity Metrics in Neighbour-based Recommender Systems
Understanding Similarity Metrics in Neighbour-based Recommender SystemsUnderstanding Similarity Metrics in Neighbour-based Recommender Systems
Understanding Similarity Metrics in Neighbour-based Recommender Systems
Alejandro Bellogin
 
Artist popularity: do web and social music services agree?
Artist popularity: do web and social music services agree?Artist popularity: do web and social music services agree?
Artist popularity: do web and social music services agree?
Alejandro Bellogin
 
Improving Memory-Based Collaborative Filtering by Neighbour Selection based o...
Improving Memory-Based Collaborative Filtering by Neighbour Selection based o...Improving Memory-Based Collaborative Filtering by Neighbour Selection based o...
Improving Memory-Based Collaborative Filtering by Neighbour Selection based o...
Alejandro Bellogin
 
Performance prediction and evaluation in Recommender Systems: an Information ...
Performance prediction and evaluation in Recommender Systems: an Information ...Performance prediction and evaluation in Recommender Systems: an Information ...
Performance prediction and evaluation in Recommender Systems: an Information ...Alejandro Bellogin
 
Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...
Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...
Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...
Alejandro Bellogin
 
Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...
Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...
Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...
Alejandro Bellogin
 
Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...
Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...
Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...
Alejandro Bellogin
 
Predicting performance in Recommender Systems - Slides
Predicting performance in Recommender Systems - SlidesPredicting performance in Recommender Systems - Slides
Predicting performance in Recommender Systems - Slides
Alejandro Bellogin
 
Predicting performance in Recommender Systems - Poster slam
Predicting performance in Recommender Systems - Poster slamPredicting performance in Recommender Systems - Poster slam
Predicting performance in Recommender Systems - Poster slam
Alejandro Bellogin
 
Predicting performance in Recommender Systems - Poster
Predicting performance in Recommender Systems - PosterPredicting performance in Recommender Systems - Poster
Predicting performance in Recommender Systems - Poster
Alejandro Bellogin
 
Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...
Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...
Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...
Alejandro Bellogin
 

More from Alejandro Bellogin (20)

Revisiting neighborhood-based recommenders for temporal scenarios
Revisiting neighborhood-based recommenders for temporal scenariosRevisiting neighborhood-based recommenders for temporal scenarios
Revisiting neighborhood-based recommenders for temporal scenarios
 
Evaluating decision-aware recommender systems
Evaluating decision-aware recommender systemsEvaluating decision-aware recommender systems
Evaluating decision-aware recommender systems
 
Replicable Evaluation of Recommender Systems
Replicable Evaluation of Recommender SystemsReplicable Evaluation of Recommender Systems
Replicable Evaluation of Recommender Systems
 
Implicit vs Explicit trust in Social Matrix Factorization
Implicit vs Explicit trust in Social Matrix FactorizationImplicit vs Explicit trust in Social Matrix Factorization
Implicit vs Explicit trust in Social Matrix Factorization
 
RiVal - A toolkit to foster reproducibility in Recommender System evaluation
RiVal - A toolkit to foster reproducibility in Recommender System evaluationRiVal - A toolkit to foster reproducibility in Recommender System evaluation
RiVal - A toolkit to foster reproducibility in Recommender System evaluation
 
HT2014 Tutorial: Evaluating Recommender Systems - Ensuring Replicability of E...
HT2014 Tutorial: Evaluating Recommender Systems - Ensuring Replicability of E...HT2014 Tutorial: Evaluating Recommender Systems - Ensuring Replicability of E...
HT2014 Tutorial: Evaluating Recommender Systems - Ensuring Replicability of E...
 
CWI @ Contextual Suggestion track - TREC 2013
CWI @ Contextual Suggestion track - TREC 2013CWI @ Contextual Suggestion track - TREC 2013
CWI @ Contextual Suggestion track - TREC 2013
 
CWI @ Federated Web Track - TREC 2013
CWI @ Federated Web Track - TREC 2013CWI @ Federated Web Track - TREC 2013
CWI @ Federated Web Track - TREC 2013
 
Probabilistic Collaborative Filtering with Negative Cross Entropy
Probabilistic Collaborative Filtering with Negative Cross EntropyProbabilistic Collaborative Filtering with Negative Cross Entropy
Probabilistic Collaborative Filtering with Negative Cross Entropy
 
Understanding Similarity Metrics in Neighbour-based Recommender Systems
Understanding Similarity Metrics in Neighbour-based Recommender SystemsUnderstanding Similarity Metrics in Neighbour-based Recommender Systems
Understanding Similarity Metrics in Neighbour-based Recommender Systems
 
Artist popularity: do web and social music services agree?
Artist popularity: do web and social music services agree?Artist popularity: do web and social music services agree?
Artist popularity: do web and social music services agree?
 
Improving Memory-Based Collaborative Filtering by Neighbour Selection based o...
Improving Memory-Based Collaborative Filtering by Neighbour Selection based o...Improving Memory-Based Collaborative Filtering by Neighbour Selection based o...
Improving Memory-Based Collaborative Filtering by Neighbour Selection based o...
 
Performance prediction and evaluation in Recommender Systems: an Information ...
Performance prediction and evaluation in Recommender Systems: an Information ...Performance prediction and evaluation in Recommender Systems: an Information ...
Performance prediction and evaluation in Recommender Systems: an Information ...
 
Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...
Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...
Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...
 
Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...
Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...
Using Graph Partitioning Techniques for Neighbour Selection in User-Based Col...
 
Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...
Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...
Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...
 
Predicting performance in Recommender Systems - Slides
Predicting performance in Recommender Systems - SlidesPredicting performance in Recommender Systems - Slides
Predicting performance in Recommender Systems - Slides
 
Predicting performance in Recommender Systems - Poster slam
Predicting performance in Recommender Systems - Poster slamPredicting performance in Recommender Systems - Poster slam
Predicting performance in Recommender Systems - Poster slam
 
Predicting performance in Recommender Systems - Poster
Predicting performance in Recommender Systems - PosterPredicting performance in Recommender Systems - Poster
Predicting performance in Recommender Systems - Poster
 
Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...
Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...
Precision-oriented Evaluation of Recommender Systems: An Algorithmic Comparis...
 

Recently uploaded

THEMATIC APPERCEPTION TEST(TAT) cognitive abilities, creativity, and critic...
THEMATIC  APPERCEPTION  TEST(TAT) cognitive abilities, creativity, and critic...THEMATIC  APPERCEPTION  TEST(TAT) cognitive abilities, creativity, and critic...
THEMATIC APPERCEPTION TEST(TAT) cognitive abilities, creativity, and critic...
Abdul Wali Khan University Mardan,kP,Pakistan
 
SAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdfSAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdf
KrushnaDarade1
 
Eukaryotic Transcription Presentation.pptx
Eukaryotic Transcription Presentation.pptxEukaryotic Transcription Presentation.pptx
Eukaryotic Transcription Presentation.pptx
RitabrataSarkar3
 
The binding of cosmological structures by massless topological defects
The binding of cosmological structures by massless topological defectsThe binding of cosmological structures by massless topological defects
The binding of cosmological structures by massless topological defects
Sérgio Sacani
 
20240520 Planning a Circuit Simulator in JavaScript.pptx
20240520 Planning a Circuit Simulator in JavaScript.pptx20240520 Planning a Circuit Simulator in JavaScript.pptx
20240520 Planning a Circuit Simulator in JavaScript.pptx
Sharon Liu
 
aziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobelaziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobel
İsa Badur
 
Sciences of Europe journal No 142 (2024)
Sciences of Europe journal No 142 (2024)Sciences of Europe journal No 142 (2024)
Sciences of Europe journal No 142 (2024)
Sciences of Europe
 
23PH301 - Optics - Optical Lenses.pptx
23PH301 - Optics  -  Optical Lenses.pptx23PH301 - Optics  -  Optical Lenses.pptx
23PH301 - Optics - Optical Lenses.pptx
RDhivya6
 
Micronuclei test.M.sc.zoology.fisheries.
Micronuclei test.M.sc.zoology.fisheries.Micronuclei test.M.sc.zoology.fisheries.
Micronuclei test.M.sc.zoology.fisheries.
Aditi Bajpai
 
Sharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Sharlene Leurig - Enabling Onsite Water Use with Net Zero WaterSharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Sharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Texas Alliance of Groundwater Districts
 
Equivariant neural networks and representation theory
Equivariant neural networks and representation theoryEquivariant neural networks and representation theory
Equivariant neural networks and representation theory
Daniel Tubbenhauer
 
The debris of the ‘last major merger’ is dynamically young
The debris of the ‘last major merger’ is dynamically youngThe debris of the ‘last major merger’ is dynamically young
The debris of the ‘last major merger’ is dynamically young
Sérgio Sacani
 
Immersive Learning That Works: Research Grounding and Paths Forward
Immersive Learning That Works: Research Grounding and Paths ForwardImmersive Learning That Works: Research Grounding and Paths Forward
Immersive Learning That Works: Research Grounding and Paths Forward
Leonel Morgado
 
Compexometric titration/Chelatorphy titration/chelating titration
Compexometric titration/Chelatorphy titration/chelating titrationCompexometric titration/Chelatorphy titration/chelating titration
Compexometric titration/Chelatorphy titration/chelating titration
Vandana Devesh Sharma
 
Bob Reedy - Nitrate in Texas Groundwater.pdf
Bob Reedy - Nitrate in Texas Groundwater.pdfBob Reedy - Nitrate in Texas Groundwater.pdf
Bob Reedy - Nitrate in Texas Groundwater.pdf
Texas Alliance of Groundwater Districts
 
molar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptxmolar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptx
Anagha Prasad
 
Katherine Romanak - Geologic CO2 Storage.pdf
Katherine Romanak - Geologic CO2 Storage.pdfKatherine Romanak - Geologic CO2 Storage.pdf
Katherine Romanak - Geologic CO2 Storage.pdf
Texas Alliance of Groundwater Districts
 
Direct Seeded Rice - Climate Smart Agriculture
Direct Seeded Rice - Climate Smart AgricultureDirect Seeded Rice - Climate Smart Agriculture
Direct Seeded Rice - Climate Smart Agriculture
International Food Policy Research Institute- South Asia Office
 
Basics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different formsBasics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different forms
MaheshaNanjegowda
 
Shallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptxShallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptx
Gokturk Mehmet Dilci
 

Recently uploaded (20)

THEMATIC APPERCEPTION TEST(TAT) cognitive abilities, creativity, and critic...
THEMATIC  APPERCEPTION  TEST(TAT) cognitive abilities, creativity, and critic...THEMATIC  APPERCEPTION  TEST(TAT) cognitive abilities, creativity, and critic...
THEMATIC APPERCEPTION TEST(TAT) cognitive abilities, creativity, and critic...
 
SAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdfSAR of Medicinal Chemistry 1st by dk.pdf
SAR of Medicinal Chemistry 1st by dk.pdf
 
Eukaryotic Transcription Presentation.pptx
Eukaryotic Transcription Presentation.pptxEukaryotic Transcription Presentation.pptx
Eukaryotic Transcription Presentation.pptx
 
The binding of cosmological structures by massless topological defects
The binding of cosmological structures by massless topological defectsThe binding of cosmological structures by massless topological defects
The binding of cosmological structures by massless topological defects
 
20240520 Planning a Circuit Simulator in JavaScript.pptx
20240520 Planning a Circuit Simulator in JavaScript.pptx20240520 Planning a Circuit Simulator in JavaScript.pptx
20240520 Planning a Circuit Simulator in JavaScript.pptx
 
aziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobelaziz sancar nobel prize winner: from mardin to nobel
aziz sancar nobel prize winner: from mardin to nobel
 
Sciences of Europe journal No 142 (2024)
Sciences of Europe journal No 142 (2024)Sciences of Europe journal No 142 (2024)
Sciences of Europe journal No 142 (2024)
 
23PH301 - Optics - Optical Lenses.pptx
23PH301 - Optics  -  Optical Lenses.pptx23PH301 - Optics  -  Optical Lenses.pptx
23PH301 - Optics - Optical Lenses.pptx
 
Micronuclei test.M.sc.zoology.fisheries.
Micronuclei test.M.sc.zoology.fisheries.Micronuclei test.M.sc.zoology.fisheries.
Micronuclei test.M.sc.zoology.fisheries.
 
Sharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Sharlene Leurig - Enabling Onsite Water Use with Net Zero WaterSharlene Leurig - Enabling Onsite Water Use with Net Zero Water
Sharlene Leurig - Enabling Onsite Water Use with Net Zero Water
 
Equivariant neural networks and representation theory
Equivariant neural networks and representation theoryEquivariant neural networks and representation theory
Equivariant neural networks and representation theory
 
The debris of the ‘last major merger’ is dynamically young
The debris of the ‘last major merger’ is dynamically youngThe debris of the ‘last major merger’ is dynamically young
The debris of the ‘last major merger’ is dynamically young
 
Immersive Learning That Works: Research Grounding and Paths Forward
Immersive Learning That Works: Research Grounding and Paths ForwardImmersive Learning That Works: Research Grounding and Paths Forward
Immersive Learning That Works: Research Grounding and Paths Forward
 
Compexometric titration/Chelatorphy titration/chelating titration
Compexometric titration/Chelatorphy titration/chelating titrationCompexometric titration/Chelatorphy titration/chelating titration
Compexometric titration/Chelatorphy titration/chelating titration
 
Bob Reedy - Nitrate in Texas Groundwater.pdf
Bob Reedy - Nitrate in Texas Groundwater.pdfBob Reedy - Nitrate in Texas Groundwater.pdf
Bob Reedy - Nitrate in Texas Groundwater.pdf
 
molar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptxmolar-distalization in orthodontics-seminar.pptx
molar-distalization in orthodontics-seminar.pptx
 
Katherine Romanak - Geologic CO2 Storage.pdf
Katherine Romanak - Geologic CO2 Storage.pdfKatherine Romanak - Geologic CO2 Storage.pdf
Katherine Romanak - Geologic CO2 Storage.pdf
 
Direct Seeded Rice - Climate Smart Agriculture
Direct Seeded Rice - Climate Smart AgricultureDirect Seeded Rice - Climate Smart Agriculture
Direct Seeded Rice - Climate Smart Agriculture
 
Basics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different formsBasics of crystallography, crystal systems, classes and different forms
Basics of crystallography, crystal systems, classes and different forms
 
Shallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptxShallowest Oil Discovery of Turkiye.pptx
Shallowest Oil Discovery of Turkiye.pptx
 

Recommender Systems and Misinformation: The Problem or the Solution?

  • 1. Recommender Systems and Misinformation: The problem or the solution? Miriam Fernández, Open University, United Kingdom Alejandro Bellogín, Universidad Autónoma de Madrid, Spain
  • 4. Factors that influence the spread of misinformation online: ● How information is constructed and presented ● Personality, values, and emotions of the users ● Characteristics of digital platforms ● Algorithms that power the recommendation of information in those platforms Misinformation spread 4
  • 5. Our goal Explore the effect of existing algorithms on the recommendation of false and misleading information Understand which techniques are more prone to spread misinformation, and under which circumstances. How can their internal functioning be modified, or adapted, to counter this behaviour? USER SYSTEM Preferences Model Interaction Recommendation 5
  • 8. Our approach Problem Dimensions: which dimensions of the misinformation problem affect the behaviour of RS? Analysis of Recommendation Algorithms: analyse how existing algorithms improve or worsen the spread of misinformation Human-centred Evaluation: modify existing evaluation methods and metrics (dissonance vs. satisfaction) Adaptation, Modification and Vigilance: adapt existing algorithms and track their impact over time (vigilance). which recommendation algorithms are more prone to spread misinformation, and under which circumstances? 8
  • 9. Content: Different forms (newspaper articles, blog posts, social media posts), topics (health, elections), formats (text, images, videos), framing (false news, rumours, conspiracy theories), origin (news outlets, social contacts, public figures), time Users: Different motivations, personalities, values, emotions and susceptibility influence the spread of misinformation Platform & Network Features: Platforms are designed differently (content limitations, sharing permissions) & have different typology and topology of network structure. Others: global events, presence of malicious actors, presence of checked facts Misinformation: Problem Dimensions A global problem, multiple dimensions (human, sociological, technological) Dimensions that intersect between recommendation and misinformation 9
  • 10. Analysis of Recommendation Algorithms Which recommendation techniques are more prone to suggest misinformative items to users and why? CF methods neglect any information about the items and their misinformative features. They can help us to understand the impact of user-item interactions. CB approaches use content and therefore require analysing NL and its inherent subtleties. Hybrid methods combine content analysis with user-time interactions. Are they therefore more prone to spread misinformation? User & Item Profiles: Multiple representations can be considered. How do these representations influence the spread of misinformation? 10
  • 11. Human-centred Evaluation Metrics that focus on computing a balanced degree of user satisfaction and discomfort (introducing opposing views) may help to combat misperceptions. Same information, opposing views ≠ diversity (novel information) Datasets: We need users / items & information about their credibility + user-item ratings - NELA-GT-2018 dataset (713 misinforming articles) → no user profiles / ratings - COVID-19 Poynter dataset (603 misinforming articles/posts) → no user profiles / ratings - NewsReel: users, articles and ratings → no information about item credibility Measure: how can we evaluate when the task has been successfully addressed? 11
  • 12. Adaptation, Modification, and Vigilance Social Science and Psychology studies: simply presenting people with corrective information is likely to fail in changing their salient beliefs. - Providing an explanation rather than a simple refute - Exposing users to related but disconfirming stories - Revealing similarities with the opposing groups Adaptation/Modification: the adaptation of existing algorithms to counter the misinformation recommendation problem should build on existing social science and psychology theory. - Profile users to better capture motivations - RS that introduce small degrees of opposing views - RS focus on similarity and dissimilarity - Explanations Vigilance: - Dynamics of misinformation captured over time - Algorithms are adapted - Proposed adaptations do not back-fire (ethics!) 12
  • 13. Recommender systems are often accused of feeding and reinforcing the interaction cycle BUT, they could be part of the solution, if we understand: ● How misinformation is spread ● How such mechanisms are reinforced ○ And to what extent, depending on the technique ● How we can adapt the algorithms to counter these effects Our hypothesis: build on social science and psychology theories Discussion 13
  • 14. Current plan 14 Starting with a COVID-related Poynter dataset It contains news items classified as reliable or not We are collecting Twitter user profiles Challenge 1: how many users can we collect for each news item? (cold items) Challenge 2: how many items do user profiles actually contain? (cold users) Challenge 3: what is a realistic ratio between misinformation/normal items? Question: are there datasets with this information combined? Next step: run and evaluate CF recommenders Next challenges???
  • 15. CREDITS: This presentation template was created by Slidesgo, including icons by Flaticon, infographics & images by Freepik and illustrations by Stories Recommender Systems and Misinformation: The problem or the solution? Miriam Fernández, Open University, United Kingdom Alejandro Bellogín, Universidad Autónoma de Madrid, Spain 15