@SapienzaRoma; previously @gesis_org, @VT_DAC & @UniPD
Italy
Joined February 2012
- Tweets146
- Following253
- Followers174
- Likes164
Mattia Samory retweeted
Delighted and thankful that our study "Election Polls on Social Media: Prevalence, Biases, and Voter Fraud Beliefs" (attached thread) received Best Paper Honorable Mention at @ICWSM'25! Congratulations @StephenAI @vijayalaks26304 @hide_yourself @yang3kc @junghwanyang! 🙏🎊
First paper🔬 on social polls!!!🗳️
Over 100k polls gauged support for 2020 US presidential candidates on @X, and gathered >20m votes. They favored Trump by >10% (on average). Many were used to reinforce voter fraud beliefs and were likely manipulated by bots and fake votes.
🧵1/5
Looking forward to new, original datasets!
Curating and sharing high-quality datasets is the foundation of good empirical science.
@ICWSM promotes dataset creation through a dedicated conference track published in the conference's regular proceedings.
Submit your dataset paper by Jan 15th!
CfP: icwsm.org/2025/submit/index.…
Mattia Samory retweeted
Our bias-corrected estimates of support for US presidential candidates based on @X polls were more accurate than traditional polls! 🎊🎉
We estimated 52% for Trump vs 48% for Harris. So far there are 72,641,564 votes for Trump (51.7%) and 67,957,895 for Harris (48.3%)!
Mattia Samory retweeted
Don't believe everything you see on social media.
Informal political polls conducted on X during both the 2016 and 2020 U.S. presidential elections were significantly skewed by questionable votes.
🔗 Details here: bit.ly/3VYVGTy
@manningcics
Mattia Samory retweeted
🚨New Pub Alert 📢
I’m excited to share our newest systematic review!
We analyzed the data quality of hateful communication datasets for automated detection, the targeted identities, linguistic diversity, and involved researchers. Check it out: doi.org/10.1177/089443932412…
Mattia Samory retweeted
First paper🔬 on social polls!!!🗳️
Over 100k polls gauged support for 2020 US presidential candidates on @X, and gathered >20m votes. They favored Trump by >10% (on average). Many were used to reinforce voter fraud beliefs and were likely manipulated by bots and fake votes.
🧵1/5
Mattia Samory retweeted
Our 3 submissions to @IC2S2 are accepted as talks/plenaries! (Topics: social polls, global news coverage, and scientific promotion.)
Looking forward to the conference in Philly!
Congrats @hide_yourself @junghwanyang @yang3kc @gonemelon @computermacgyve @david__jurgens @EthanZ @c_bagchi @ericmalmi! 🎑
Mattia Samory retweeted
Proud supervisor pic! Indira did an amazing job today! Congratulations Dr. Sen @indiiigosky
When @shruti_ph submits to ICWSM…
HT @shruti_ph @tanmit for the amazing collaboration over the years. This paper was completed at a difficult time and I am grateful for their support
Mattia Samory retweeted
📢Training on Counterfactually Augmented Data (CAD) improves out-of-domain performance of NLP models. ‼️ this may come at the cost of false positive bias. We explore this in our(w/ @hide_yourself @clauwa @IAugenstein) short paper: arxiv.org/pdf/2205.04238.pdf(to appear at #NAACL22) 1/
Mattia Samory retweeted
Do you use YouTube for getting your news and election information? Please take this survey to participate in running a Chrome browser extension for 9 days. bit.ly/3ILgyVZ. Please RT and pass along to other folks you think would be interested to participate!
(1/2) Paid Study Alert!
We are conducting a study to audit YouTube for news and election information.
Participants would require to run a Chrome browser extension for 9 days.
Compensation: $27
Fill out the screening survey to participate
bit.ly/3ILgyVZ
Please RT!
Mattia Samory retweeted
Do you ever get bored of seeing same recommendations from @YouTube? By developing OtherTube, @snaglee2401 @tanmit @carlosabauti and I studied how swapping recommendations with strangers can help burst algorithmic filters #CHI2022 arxiv.org/abs/2201.11709 youtu.be/Br4ZEVG_tsk
This has been on my mind a lot lately, and @asbruckman elucidated it better than I ever did
Nos decía @asbruckman hace unos meses: "We need more non-profit Internet side, based on values. I don't believe that a for profit company motivated by maximizing shareholder value can ever make the right decisions to either individuals or communities" youtube.com/watch?v=Rx3xesDk…
Mattia Samory retweeted
This NudgeCred paper took only 4 yrs to be published. Still one of my favorite papers! The idea was hatched in 2017, after 3 yrs of rejections, it finally found its home at CSCW this year. Today seems to be the day to talk about paper rejections turning into acceptances #CHI2022
Excited to present two #CSCW2021 papers with my co-authors @tanmit @snaglee2401 @mhorning in the Misinformation, Conspiracies, and Manipulations session today. Links to the pre-recorded presentations: youtube.com/watch?v=TQpeRpcD… and youtube.com/watch?v=oC9thtav…
Mattia Samory retweeted
👇I am looking for a postdoc. Know someone with interest or experience in online mis(dis)information/influence operations, competent in social media analytics & wants to work in a non-western context, like the Indian subcontinent. You can ping me directly
apply.interfolio.com/96175
The second postdoc position will work on a project with @UW_iSchool assistant professor and @uwcip faculty member @tanmit that will study how adversarial online influence looks like in the Indian Ocean Region ... Details: apply.interfolio.com/96175 (3/3)
Mattia Samory retweeted
"How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?" analyses reasons CAD is beneficial for social NLP tasks (sentiment, sexism, hate speech)
@indiiigosky @hide_yourself @ffloeck @clauwa @IAugenstein
arxiv.org/abs/2109.07022 #EMNLP2021 #NLProc
