home.social

#recommendersystems — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #recommendersystems, aggregated by home.social.

fetched live
  1. Learn how AI recommendation engines power Spotify, Amazon, YouTube, and more without relying on magic or black-box mystique. hackernoon.com/how-recommender #recommendersystems

  2. Learn how AI recommendation engines power Spotify, Amazon, YouTube, and more without relying on magic or black-box mystique. hackernoon.com/how-recommender #recommendersystems

  3. RE: curia.social-network.europa.eu

    Well. A lot of digital rights lawyers seem very excited about this ruling from the Court of Justice today - in particular, the final paragraph 122:

    ⚡️a website that controls what viewers see via an algorithm is liable for the content⚡️

    Full judgment (in French): eur-lex.europa.eu/legal-conten

    Case refs:

    C-188/24 WebGroup Czech Republic and NKL Associates

    and

    C-190/24 Coyote System

    #DigitalRights #bigtech #algorithms #InfiniteScroll #SurveillanceCapitalism #RecommenderSystems #EU #AI #Law

  4. RE: curia.social-network.europa.eu

    Well. A lot of digital rights lawyers seem very excited about this ruling from the Court of Justice today - in particular, the final paragraph 122:

    ⚡️a website that controls what viewers see via an algorithm is liable for the content⚡️

    Full judgment (in French): eur-lex.europa.eu/legal-conten

    Case refs:

    C-188/24 WebGroup Czech Republic and NKL Associates

    and

    C-190/24 Coyote System

    #DigitalRights #bigtech #algorithms #InfiniteScroll #SurveillanceCapitalism #RecommenderSystems #EU #AI #Law

  5. Noch eine Woche bis zum Bewerbungsschluss:

    Projektkoordinator:in Gutachter:innen-Empfehlungssystem für Zeitschriften (m/w/d), 24 Monate, 75% E13, ab 1.10.

    tib.eu/de/die-tib/karriere-und

    Aufstockungsoptionen prüfen wir gerne. Das wird ein spannendes Projekt - gerne anschauen, weiterleiten. Stehe für Nachfragen zur Verfügung.

  6. Noch eine Woche bis zum Bewerbungsschluss:

    Projektkoordinator:in Gutachter:innen-Empfehlungssystem für Zeitschriften (m/w/d), 24 Monate, 75% E13, ab 1.10.

    tib.eu/de/die-tib/karriere-und

    Aufstockungsoptionen prüfen wir gerne. Das wird ein spannendes Projekt - gerne anschauen, weiterleiten. Stehe für Nachfragen zur Verfügung.

    #OpenAccess #RecommenderSystems #ScholarlyCommunication

  7. A Job I Like or a Job I Can Get: Designing Job #RecommenderSystems Using Field Experiments d.repec.org/n?u=RePEc:arx:pape
    "… welfare-optimal RSs rank vacancies by an expected-surplus index, and shows why rankings based solely on utility, #hiring probabilities, or observed application behavior are generically suboptimal
    … Algorithms informed by the model-implied optimal ranking substantially outperform existing approaches and perform close to the welfare-optimal benchmark.

    While the joint application-and-hiring probability is not welfare-optimal in theory, it emerges as a strong empirical benchmark in our setting. This result is structural rather than algorithmic: application probabilities are empirically small and remain so even under recommendation rules designed to stimulate applications
    … rankings based solely on application behavior are theoretically fragile
    … Machine-learning tools can substantially improve matching outcomes, but only when embedded in a framework that defines the economic objective and disciplines behavioral assumptions with experimental evidence. Without such a framework, RSs optimized for observable behaviors may perform well on predictive metrics yet remain misaligned with welfare-relevant outcomes."
    #LaborMarkets #jobtech #socialWelfare #ExperimentalEcon

  8. A Job I Like or a Job I Can Get: Designing Job #RecommenderSystems Using Field Experiments d.repec.org/n?u=RePEc:arx:pape
    "… welfare-optimal RSs rank vacancies by an expected-surplus index, and shows why rankings based solely on utility, #hiring probabilities, or observed application behavior are generically suboptimal
    … Algorithms informed by the model-implied optimal ranking substantially outperform existing approaches and perform close to the welfare-optimal benchmark.

    While the joint application-and-hiring probability is not welfare-optimal in theory, it emerges as a strong empirical benchmark in our setting. This result is structural rather than algorithmic: application probabilities are empirically small and remain so even under recommendation rules designed to stimulate applications
    … rankings based solely on application behavior are theoretically fragile
    … Machine-learning tools can substantially improve matching outcomes, but only when embedded in a framework that defines the economic objective and disciplines behavioral assumptions with experimental evidence. Without such a framework, RSs optimized for observable behaviors may perform well on predictive metrics yet remain misaligned with welfare-relevant outcomes."
    #LaborMarkets #jobtech #socialWelfare #ExperimentalEcon

  9. 📢 Fantastic news from the Digital Science Center! 📢

    The open‑access paper “Maximal Transparency for Online Recommender Systems” is out in Philosophy & Technology. A truly interdisciplinary effort across philosophy, bioinformatics, mathematics, computer science, and law.

    Read the full article here: link.springer.com/article/10.1

    #RecommenderSystems #Transparency #AIEthics #OpenAccess #InterdisciplinaryResearch #Philosophy #Technology #EUAIAct
    1/5

  10. 📢 Fantastic news from the Digital Science Center! 📢

    The open‑access paper “Maximal Transparency for Online Recommender Systems” is out in Philosophy & Technology. A truly interdisciplinary effort across philosophy, bioinformatics, mathematics, computer science, and law.

    Read the full article here: link.springer.com/article/10.1

    #RecommenderSystems #Transparency #AIEthics #OpenAccess #InterdisciplinaryResearch #Philosophy #Technology #EUAIAct
    1/5

  11. Two teams from LIPN will present their joined work at IPMU 2026 👏.
    Congratulations to Amal Beldi and Louenas Bounia for their work on Uncertainty-Aware Contextual Recommendation under Possible Worlds Semantics!
    This paper proposes a probabilistic framework for uncertainty-aware contextual recommendation grounded in probabilistic database semantics.
    #LIPN #RecommenderSystems #DecisionMaking

  12. Future recommendation infrastructures must integrate evaluation protocols, fairness metrics, and reproducible pipelines as first-class design principles—not afterthoughts.
    The paper “WarpRec” proposes a framework that unifies academic rigor with industrial-scale recommendation systems, aiming for responsibility, reproducibility, and efficiency at scale.
    arxiv.org/abs/2602.17442v1
    #RecommenderSystems #ResponsibleAI #MachineLearning

  13. Future recommendation infrastructures must integrate evaluation protocols, fairness metrics, and reproducible pipelines as first-class design principles—not afterthoughts.
    The paper “WarpRec” proposes a framework that unifies academic rigor with industrial-scale recommendation systems, aiming for responsibility, reproducibility, and efficiency at scale.
    arxiv.org/abs/2602.17442v1
    #RecommenderSystems #ResponsibleAI #MachineLearning

  14. Paige Saunders @paige (rather than Dawn Walker @dawn as I erroneously wrote earlier!) has this great video, 'We Have An Algorithm Problem' at video.fedihost.co/w/a1522517-7, where he says that fediverse users' suspicion of algorithms is completely warranted, but now that we have been able to opt out of algorithmic content where we had zero agency, we need a conversation about what it means to opt in with algorithms under our own control.

    #ContentAlgorithms #RecommenderSystems

  15. Paige Saunders @paige (rather than Dawn Walker @dawn as I erroneously wrote earlier!) has this great video, 'We Have An Algorithm Problem' at video.fedihost.co/w/a1522517-7, where he says that fediverse users' suspicion of algorithms is completely warranted, but now that we have been able to opt out of algorithmic content where we had zero agency, we need a conversation about what it means to opt in with algorithms under our own control.

    #ContentAlgorithms #RecommenderSystems

  16. "Banning #socialmedia for young people will ignore the incredibly harmful societal effects of modern social media for most of the population…
    The most immediate solution is to ban companies from using #recommendersystems entirely (outside a few specific cases); that would restore our freedom to choose what we see online, and at least pause our descent into the years-long spiral towards increased extremism, misinformation, social media addiction & polarisation."
    thejournal.ie/readme/opinion-s

  17. "Banning #socialmedia for young people will ignore the incredibly harmful societal effects of modern social media for most of the population…
    The most immediate solution is to ban companies from using #recommendersystems entirely (outside a few specific cases); that would restore our freedom to choose what we see online, and at least pause our descent into the years-long spiral towards increased extremism, misinformation, social media addiction & polarisation."
    thejournal.ie/readme/opinion-s

  18. I love it when recommender systems are so chronically off that it just confirms the coming automated dystopian future we have built will be 90% Brazil and 10% LOTF.

    #recommendersystems #researchgate #academia #academicchatter

  19. I love it when recommender systems are so chronically off that it just confirms the coming automated dystopian future we have built will be 90% Brazil and 10% LOTF.

    #recommendersystems #researchgate #academia #academicchatter

  20. For the past couple of weeks I have turned off my home feed on youtube and am only using the subscriptions button which behaves like an RSS feed.

    Without dopamine optimising suggestions I am saving so much time! Highly recommended :D

    #UsersAreFodder #RecommenderSystems #DopamineCulture #youtube #rss #SiValleyGrift

  21. For the past couple of weeks I have turned off my home feed on youtube and am only using the subscriptions button which behaves like an RSS feed.

    Without dopamine optimising suggestions I am saving so much time! Highly recommended :D

    #UsersAreFodder #RecommenderSystems #DopamineCulture #youtube #rss #SiValleyGrift

  22. Explore how #recommenderSystems shape the #public in deliberative #democracies. This recently published whitepaper by Melusina offers a solid foundation for policymakers navigating digital transformation. Read more: doi.org/10.26298/1981-5982-euo #DigitalEthics

  23. 🔗 Whether you're a researcher, data scientist, journalist, or industry professional, this workshop will spark meaningful conversations about how we can collaborate to advance technology responsibly and ethically.

    👉 𝗗𝗼𝗻’𝘁 𝗺𝗶𝘀𝘀 𝗼𝘂𝘁! 𝗟𝗲𝗮𝗿𝗻 𝗺𝗼𝗿𝗲 𝗮𝗻𝗱 𝗿𝗲𝗴𝗶𝘀𝘁𝗲𝗿 𝘁𝗼𝗱𝗮𝘆: impact.dataschool.nl/events/ma

    #RecommenderSystems #Conference #Collaboration #Algorithms #AI #Ethics

  24. NEW STUDY OUT IN IC&S

    Putting #FilterBubble Effects to the Test

    In an experimental survey study with real #news #recommendersystems (#NRS), we find **limited** support for #polarization effects of #algorithms inducing "filter bubble" like information environments.

    Data also show how balanced algorithms may promote #depolarization.

    doi.org/10.1080/1369118X.2024.

    @commodon @communicationscholars #PoliticalCommunication #SocialMedia

  25. Still trying to figure out how to scratch your #recsys itch after this year's @Recsys? Have a look at the #ACMTORS Call for papers for the Special Issue on #RecommenderSystems for Good. Will you be be submitting a paper as an xmas gift to the RecSys community? // @Nava et al.
    dl.acm.org/pb-assets/static_jo

  26. Graph Convolutional Networks (GCNs) are revolutionizing recommender systems! 🔍📊 Learn how GCNs improve recommendation accuracy by understanding complex relationships in data. Ready to dive into the future of AI-driven recommendations? 👇 #AI #GCN #RecommenderSystems #MachineLearning

    pupuweb.com/how-do-graph-convo

  27. Measuring Bias in Job #RecommenderSystems: Auditing the Algorithms d.repec.org/n?u=RePEc:nbr:nber
    "…recommender systems show different jobs to identical male & female job seekers, though most of the jobs overlap
    …women are steered towards jobs that pay less, are in smaller firms, & require less experience, suggesting a lower rank in firms’ hierarchies
    …steer men & women towards job ads that contain words that are stereotypical for their gender"
    #LaborMarkets

  28. Measuring Bias in Job #RecommenderSystems: Auditing the Algorithms d.repec.org/n?u=RePEc:nbr:nber
    "…recommender systems show different jobs to identical male & female job seekers, though most of the jobs overlap
    …women are steered towards jobs that pay less, are in smaller firms, & require less experience, suggesting a lower rank in firms’ hierarchies
    …steer men & women towards job ads that contain words that are stereotypical for their gender"
    #LaborMarkets

  29. What’s the most common question in an ML Design interview? Hint: it’s not about fancy algorithms. It’s about recommender systems. Watch to learn more: buff.ly/3ZoByO9 #MLEngineer #RecommenderSystems

  30. The next round of our Algorithmic Accountability Reporting Fellowship is just around the corner! 🚀

    Got questions? Join us for a Q&A session with Naiara Bellio from our Journalism team TODAY at 6 pm: algorithmwatch.org/en/apply-fe

    In this round, we're diving deep into the political economy of AI, exploring crucial topics like #generativeAI and #recommenderSystems. Our aim? To unravel the AI value chain and its far-reaching impact on society, particularly on specific population groups.

  31. The next round of our Algorithmic Accountability Reporting Fellowship is just around the corner! 🚀

    Got questions? Join us for a Q&A session with Naiara Bellio from our Journalism team TODAY at 6 pm: algorithmwatch.org/en/apply-fe

    In this round, we're diving deep into the political economy of AI, exploring crucial topics like #generativeAI and #recommenderSystems. Our aim? To unravel the AI value chain and its far-reaching impact on society, particularly on specific population groups.

  32. Do you have any thoughts on where #recommendersystems are going? Should we be thinking about #recsys differently? Be sure to submit an extended abstract to the #INTROSPECTIVES2024 workshop at #recsys2024 introspectives.github.io/2024/ @Recsys

  33. Za każdym razem, gdy #UE wypuszcza nową regulację, komisarz Thierry Breton publikuje playlistę zatytułowaną jak ta regulacja.

    Dziś my* mamy playlistę dla komisarza. Dobrze byłoby żyć w świecie zdrowych algorytmów:
    open.spotify.com/playlist/34ym

    *sieć People vs. Big Tech

    #fixfeed
    #FixOurFeeds
    #TechRegulation
    #RecommenderSystems
    #RecSys
    #Algorithms

  34. Za każdym razem, gdy #UE wypuszcza nową regulację, komisarz Thierry Breton publikuje playlistę zatytułowaną jak ta regulacja.

    Dziś my* mamy playlistę dla komisarza. Dobrze byłoby żyć w świecie zdrowych algorytmów:
    open.spotify.com/playlist/34ym

    *sieć People vs. Big Tech

    #fixfeed
    #FixOurFeeds
    #TechRegulation
    #RecommenderSystems
    #RecSys
    #Algorithms

  35. #publication : Can a Single Line of Code Change Society? The Systemic Risks of Optimizing Engagement in Recommender Systems on Global Information Flow, Opinion Dynamics and Social Structures

    We demonstrate that engagement-maximizing algorithms necessarily lead to increased network toxicity and fragmentation of opinion space.

    Everything is calibrated on real data from the #Politoscope

    #systemicrisks #DSA #opiniondynamics #twitter #polarization #RecommenderSystems

    jasss.org/27/1/9.html

  36. #publication : Can a Single Line of Code Change Society? The Systemic Risks of Optimizing Engagement in Recommender Systems on Global Information Flow, Opinion Dynamics and Social Structures

    Où nous démontrons avec Paul Bouchaud et Maziyar Panahi que les algorithmes de maximization d'engagement sur Twitter et autres RS mènent nécessairement à une hausse de la toxicité du réseau, une fragmentation accrue de l'espace d'opinion.

    Tout est calibré sur des données réelles issues du #Politoscope

    #risquesystémiques #DSA #opiniondynamics #twitter #polarisation #RecommenderSystems

    L'article en libre accès : jasss.org/27/1/9.html

  37. Exploratory Search and Recommendation Systems are the topics of the very last section of our #kg2023 lecture. Learn how to create a simple similarity-based recommender system for books based on SPARQL and #dbpedia. .. but we have 2 more hands-on to come ;-)
    OpenHPI video: open.hpi.de/courses/knowledgeg
    youtube video: youtube.com/watch?v=CbBtM05IBW
    slides: zenodo.org/records/10185305
    #knowledgegraphs #exploratorysearch #scifi #sparql #recommendersystems @tabea @sashabruns @MahsaVafaie @fiz_karlsruhe @fizise

  38. NeMiG is a bilingual (en/de) news #dataset on the topic of #migration, which can be used, among others, to conduct controlled experiments on #polarization by news #recommendersystems. arxiv.org/abs/2309.00550 Joint work in the #ReNewRS project w/
    @dwsunima @fizise
    @kitkarlsruhe
    via HeikoPaulheim@twitter
    #knowledgegraph #recsys

  39. 4/5
    It won't be easy to fix recommender systems. Imagine transforming what evolved to be a ""casino"" into a public space, transforming ""users"" into citizens...Where to start? Panoptykon, ICCL and People vs BigTech investigated their most harmful features & call for change.

    Fixing Recommender Systems. From identification of risk factors to
    meaningful transparency and mitigation:
    panoptykon.org/fixing-rec-sys-

    #EU #TechRegulation #RecommenderSystems #RecSys #Algorithms

  40. Recommendation systems are useful, but sometimes we just want to discover new things by ourselves. In this article I present 6 alternatives to "the algorithm".

    blog.ddavo.me/posts/death-to-t

    #algorithm #youtube #radio #ethics #blog #recommendersystems #AI #datagovernance