Login

Recent searches

No recent searches

Search options

Not available on writing.exchange.
writing.exchange is one of the many independent Mastodon servers you can use to participate in the fediverse.
A small, intentional community for poets, authors, and every kind of writer.

Administered by:

Server stats:

336
active users

writing.exchange: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

#RecommenderSystems

0 posts0 participants0 posts today
Replied in thread
Public
Data School

🔗 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

impact.dataschool.nlMaking a Difference: Societal Impact through Collaborative Research | Impact Conference07/04/2025 - 08/04/2025 @ All Day - <p>Two-day Workshopping Conference for collaborative research experts and those who want to get onto the game!</p> <p>Collaborating with external partners enables university researchers to study phenomena “up close” while supporting effective interventions and knowledge transfer. As universities increasingly seek ways to engage with societal sectors, collaborative research practices are gaining attention. One pressing area that demands more collaboration is the digital transition across the public sector and media industries. Organizations in each domain face different challenges posed by the growing use of data and algorithms in daily practice and their implications for building relationships with the public.</p>
#RecommenderSystems#Conference#Collaboration
Continued thread
Public
Killian Mangan🇮🇪

On top of banning all Recommender Systems on social media, we must change from being powerless users of Tech giant services into having democratic collective control of algorithms on all services we use!

Tech platform co-ops creating apps and services which users can democratically and collectively control 🙌

#AI#Algorithm#Internet
Public
Philipp Müller

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

Screenshot of the article title and abstract of the study which is linked in the post.
Public
AlgorithmWatch

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.

Public *
Jannis

Are you working on #personalization, #recommenderSystems, or #adaptiveInterfaces in the fields of #HCI, #CSCW, and/or #XR?

Consider submitting to our workshop ABIS 2024 – International Workshop on Personalized Human-Computer Interaction and Recommender Systems held at Mensch und Computer 2024! 🚀

Submissions: 23.06.2024 (AoE) NEW!
Notification: Early July 2024
Camera-Ready: 23.07.2024
Workshop day: 01.09.2024 (Karlsruhe, Germany)

Find more information here: fg-abis.gi.de/veranstaltung/ab

fg-abis.gi.deDetail - FG ABIS
Public
David Chavalarias - EN

#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

Journal of Artificial Societies and Social SimulationCan a Single Line of Code Change Society? Optimizing Engagement in Recommender Systems Necessarily Entails Systemic Risks for Global Information Flows, Opinion Dynamics and Social Structuresby David Chavalarias, Paul Bouchaud and Maziyar Panahi
Continued thread
Public
Panoptykon

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
Public
Christos Argyropoulos MD, PhD

I wonder if anyone has bothered to look into the mathematics of #recommendersystems , because it is really embarrassing that papers with with 0000s of citations end up mapping to some very banal conventional #statistical models.
OTH, the latter have missed tremendous opportunities to entrench themselves (and create job opportunities for statisticians) by forgetting special cases that powered applications before the era of cheap computing that started in the 1980s.
It is #pagerank all over again

Public
Victoria Stuart 🇨🇦 🏳️‍⚧️

Systematic Review of Filter Bubbles in Recommender Systems: Fact or Fallacy
arxiv.org/abs/2307.01221

* filter bubble: phenomenon where individuals are isolated f. diverse opinions or materials resulting in exposure to select content, leading to reinforcement of existing attitudes, beliefs, or conditions

Our review reveals evidence of filter bubbles in recommendation systems, highlighting several biases that contribute to their existence

arXiv.orgFilter Bubbles in Recommender Systems: Fact or Fallacy -- A Systematic ReviewA filter bubble refers to the phenomenon where Internet customization effectively isolates individuals from diverse opinions or materials, resulting in their exposure to only a select set of content. This can lead to the reinforcement of existing attitudes, beliefs, or conditions. In this study, our primary focus is to investigate the impact of filter bubbles in recommender systems. This pioneering research aims to uncover the reasons behind this problem, explore potential solutions, and propose an integrated tool to help users avoid filter bubbles in recommender systems. To achieve this objective, we conduct a systematic literature review on the topic of filter bubbles in recommender systems. The reviewed articles are carefully analyzed and classified, providing valuable insights that inform the development of an integrated approach. Notably, our review reveals evidence of filter bubbles in recommendation systems, highlighting several biases that contribute to their existence. Moreover, we propose mechanisms to mitigate the impact of filter bubbles and demonstrate that incorporating diversity into recommendations can potentially help alleviate this issue. The findings of this timely review will serve as a benchmark for researchers working in interdisciplinary fields such as privacy, artificial intelligence ethics, and recommendation systems. Furthermore, it will open new avenues for future research in related domains, prompting further exploration and advancement in this critical area.
#InternetSearch#FilterBubbles#bias
Public
Cheng Soon Ong

Content moderation and #RecommenderSystems are the most widely deployed #MachineLearning based action taking systems. By action taking, I mean an algorithm that suggests a particular decision that impacts human actions. Using this view of recommender systems, we can consider how to increase the #diversity of online content by re-ranking recommended items to encourage creation of diverse content in the long term.

arxiv.org/abs/2302.04336

arXiv.orgPerformative Recommendation: Diversifying Content via Strategic IncentivesThe primary goal in recommendation is to suggest relevant content to users, but optimizing for accuracy often results in recommendations that lack diversity. To remedy this, conventional approaches such as re-ranking improve diversity by presenting more diverse items. Here we argue that to promote inherent and prolonged diversity, the system must encourage its creation. Towards this, we harness the performative nature of recommendation, and show how learning can incentivize strategic content creators to create diverse content. Our approach relies on a novel form of regularization that anticipates strategic changes to content, and penalizes for content homogeneity. We provide analytic and empirical results that demonstrate when and how diversity can be incentivized, and experimentally demonstrate the utility of our approach on synthetic and semi-synthetic data.
Public
John Leonard

Social media: what happens when AI takes over?

AI is about to make recommender algorithms a whole lot more effective, and potentially more dangerous, but it doesn't have to be that way.

Researchers @alasaarela and @lukethorburn are separately working on recommender algorithms that optimise for trust rather than attention and conflict. [Reg wall]

computing.co.uk/analysis/40744

www.computing.co.ukSocial media: what happens when AI takes over? AI is about to make recommender algorithms a whole lot more effective, and potentially more dangerous, but it doesn't have to be that way, say researchers
#technews#ai#algorithms
Replied in thread
Public
Kee Hinckley

@clive That’s really interesting. (Someone better tell Meta. :)

I would argue though that there *is* an algorithm they might be doing better than other platforms, and that’s in classifying the video content. I could see that having a multiplier effect on any recommendation algorithm.

But I found it interesting reading this right after reading Cory Doctorow’s essay on social quitting; particularly the part about the willingness to throw in wildcards because they aren’t focused on high profile influencers.

What I wonder is if they can afford to continue doing that in the long run, or will the economics lead them down the same path as Instagram, where ads and influencers start to dominate, and the things that make them unique go away?

doctorow.medium.com/social-qui

MediumSocial Quitting - Cory Doctorow - MediumBy Cory Doctorow
#recommendersystems#imagerecognition
Continued thread
Public
Lucas Bechberger

I had the pleasure of cofounding the interdisciplinary #CARLA workshop on #concept research: conceptresearch.github.io/CARL
We also published an edited volume on the topic (open access): link.springer.com/book/10.1007

I recently transitioned to an industry position, where I work as machine learning engineer on #RecommenderSystems.

Switching to Mastodon for the obvious reasons (this weird guy, who bought twitter and who is posting and doing weird stuff)... Looking forward to reading about your insights!

CARLACARLAConcepts in Action: Representation, Learning and Application
ExploreLive feeds
About