Elektrine lite

← Feed

Manoel Horta Ribeiro

manoel@hci.social

<p>CS PhD student @ EPFL </p><p>Keywords: Computational Social Science, Platforms, Communities, Moderation</p>

Posts

  • View post

    This cool new preprint argues that third-party bot detection tools generalize poorly due to the lack of robust high-quality data. 📰: https://arxiv.org/abs/2301.07015

  • View post

    Our paper on the effects of automated content moderation on Facebook (w @justincheng@twitter.com &amp;amp; @cervisiarius@twitter.com) was accepted at The Web Conference 2023! Will make a detailed thread soon, but you can already read the pre-print! See you in Texas yeehaw (?) 📰: https://arxiv.org/abs/2210.10454

  • View post

    Twitter hivemind, what are two algorithmic changes that allegedly impacted platforms greatly? E.g., In 2016, Twitter changed its feed to show content using a ranking algorithm.

  • View post

    🚨LLMs outdebate humans when given access to opponents&amp;#39; personal Information!🚨 In a pre-reg study (N=820), participants who debated ChatGPT had 81.7% (p&amp;lt;0.01) higher odds of agreeing with their opponents after the debate (compared to a human baseline) 📜: https://arxiv.org/abs/2403.14380

  • View post

    Audience capture is understudied IMO. I find it fascinating because the term comes from IDW folks close to audience-captured influencers (somehow, they reinvented Rebecca Lewis&amp;#39;s report). Plus, it is well aligned with findings that the algorithm is not radicalizing people.

  • View post

    ➡ Can large language models (LLMs) recognize convincing arguments? Kind of. We propose evaluating LLMs&amp;#39; persuasiveness capabilities by measuring their ability to recognize whether an argument would convince a user with specific demographics. 📜 :arxiv.org/abs/2404.00750

  • View post

    In this new blog post, I argue that to improve online platforms, we need to study content curation practices. That is pretty hard to do, but we should do it anyway :) https://doomscrollingbabel.manoel.xyz/p/content-curation-in-online-platforms

  • View post

    In a new blog post, I argue that discourse on social media&amp;#39;s (potentially harmful) impact is entirely ~vibes based~. https://doomscrollingbabel.manoel.xyz/p/discourse-on-social-media-is-vibes

  • View post

    This ACM CSCW paper shows that online groups requiring active participation commitments (i.e., that you post regularly) see double the contributions and retain users 4 times more (compared to groups with passive reminders). Prob very useful to OSS and Wiki folks. https://dl.acm.org/doi/10.1145/3687027