#recommendersystems — Public Fediverse posts

A Job I Like or a Job I Can Get: Designing Job #RecommenderSystems Using Field Experiments https://d.repec.org/n?u=RePEc:arx:papers:2603.21699&r=&r=exp
"… 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

📢 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: https://link.springer.com/article/10.1007/s13347-026-01084-7

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

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

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

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

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.

https://doi.org/10.1080/1369118X.2024.2435998

@commodon @communicationscholars #PoliticalCommunication #SocialMedia

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: https://buff.ly/3ZoByO9 #MLEngineer #RecommenderSystems

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: https://buff.ly/3ZoByO9 #MLEngineer #RecommenderSystems

#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

https://www.jasss.org/27/1/9.html

#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 : https://www.jasss.org/27/1/9.html

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: https://open.hpi.de/courses/knowledgegraphs2023/items/34xP0k99EEweSJmbUqi5lQ
youtube video: https://www.youtube.com/watch?v=CbBtM05IBWE&list=PLNXdQl4kBgzubTOfY5cbtxZCgg9UTe-uF&index=66
slides: https://zenodo.org/records/10185305
#knowledgegraphs #exploratorysearch #scifi #sparql #recommendersystems @tabea @sashabruns @MahsaVafaie @fiz_karlsruhe @fizise

New paper out in #humancomputerinteraction journal: A sensemaking system for grouping and suggesting stories from multiple affective viewpoints in #museums 50 days free access: https://www.tandfonline.com/eprint/AHINMIJGM93A9EM4IQFU/full?target=10.1080/07370024.2023.2242355

#hci #recommendersystems #recsys #affectivecomputing #storytelling #culturalAI

@academicchatter
@cscw @digitalhumanities

https://tandfonline.com/doi/full/10.1080/07370024.2023.2242355

#NVIDIA Announces #DGX GH200 #AI #Supercomputer | NVIDIA Newsroom

"New Class of AI Supercomputer Connects 256 #GraceHopper Superchips Into Massive, 1-#Exaflop, 144TB #GPU for Giant Models Powering #GenerativeAI, #RecommenderSystems, #DataProcessing"

https://nvidianews.nvidia.com/news/nvidia-announces-dgx-gh200-ai-supercomputer

Fancy working with me? The Faculty of Science and Engineering at the University of Wolverhampton offers, among others, a PhD studentship on Large Language Models for Academic Search. Please get in touch with me if you’re interested. Look for the LASER project at https://www.wlv.ac.uk/schools-and-institutes/faculty-of-science-and-engineering/research/phd-studentships/

#phd #ai #informationRetrieval #studentship #largeLanguageModels #chatgpt #chatgpt4 #bard #nlp #computationalLinguistics #search #academicSearch #recommendersystems #university #research

H2: I have also dealt with the problem of #commonsensereasoning by proposing, with G. Pozzato, the #logic TCL (typicality-based compositional logic) the first logic-based account able to model - with a unique formalism - the problem of both human-like NOUN-NOUN commonsense conceptual combination & the one of #conceptualblending. TCL has been applied to applications ranging from #cognitivemodelling to #computationalcreativity & #recommendersystems.

Info @: https://www.antoniolieto.net/tcl_logic.htm