Nir Grinberg

Can social media detect economic shocks before official data does? A new PNAS Nexus study led by @grinbergnir and @spfraib shows that AI models tracking job-loss disclosures on social media can predict U.S. unemployment insurance claims up to two weeks early, often

New paper out in @PNASNexus We show how skewed social media data can still be used to reliably estimate unemployment, not just nationally but down to the city level. 📈 doi.org/10.1093/pnasne… 1/N

ICYMI, our DomainDemo dataset, which describes how different demographic groups share domains on Twitter, is now available to download! 📄 Data descriptor: doi.org/10.1038/s41597… 📈 Interactive app to explore the data: domaindemo.info 💽 Dataset: doi.org/10.5281/zenodo…

@yoavgo כדי למנוע self-plagiarism 🤣 או כדי לתת לנו את האפשרות למחוק את השטויות שאנחנו כותבים לפני שמודלי שפה לומדים את זה ומציעים לנו את זה בחזרה.

מישהו מבין את הפיצ׳ר ״למחוק את ההודעה הזו אבל רק עבורי״ בשיחות ווטסאפ? מתי זה שימושי ולמה הכניסו את זה?

Also check out the @BenGurionU news story about the study, which reminded me to write this 🧵🤦bgu.ac.il/en/news-and-ar…

This work wouldn't have been possible without the amazing work of Maor Reuben, @Ldfriedl & @PPuzis. Some of the intuition for looking at this problem came from past work done w/ @_kenny_joseph and @davidlazer.

A belated 🧵 about our latest #KDD2024 paper. We developed a novel machine-learning approach for identifying fake news *sources* by leveraging network info and active learning 👇 doi.org/10.1145/363752…

Among registered voters matched to Twitter, just 2k voters accounted for 80% of misinformation URLs on Twitter in the 2020 US Election; these "supersharers" are older, female, Republican, and less educated, finds Baribi-Bartov, @Briony_Swire & @grinbergnir doi.org/10.1126/scienc…

Very excited to finally share our preprint after three years in the making! With @rubenarslan @AnaSKozyreva @Briony_Swire @michael_geers_ @stefanmherzog and Ralph Hertwig @arc_mpib, we assessed the motives of very active users for posting content. (1/x) osf.io/preprints/psya…

@j2bryson @davidlazer @_kenny_joseph @mccabe_s @jennifer_oser @oren_data @Shugars @EDMO_EUI @VHeddesheimer @paulrauwolf @ylelkes that is an suiting image on so many levels! Good catch!!

@grinbergnir @davidlazer @_kenny_joseph @mccabe_s @jennifer_oser @oren_data @Shugars @EDMO_EUI ha ha what a GREAT issue / cover to have your fake news science article in!! #fakeOffspring cc @VHeddesheimer @paulrauwolf @ylelkes

Happy to announce our new paper, just out this minute in @sciencemagazine, which examined Supersharers of Fake News on Twitter during the 2020 election w/ Sahar Baribi and @Briony_Swire science.org/doi/10.1126/sc… 1/N

“The average supersharer [of fake news] was 58 years old, 17 years older than the average user in the study, and almost 60% were women. They were also far more likely to be registered Republicans (64%) than Democrats (16%)” science.org/content/articl…

This research wouldn't have been possible without the work of @davidlazer, @Ldfriedl @_kenny_joseph, @mccabe_s and helpful comments from @jennifer_oser, @oren_data, @Shugars and numerous others. 9/fin

Our results cast supersharers as influential members of local communities where misinformation is prevalent. As such, supersharers may provide a window into the social dynamics in parts of society where a shared political reality is eroding. 8/N