Excited to share a pre-print about web scraping for research! We're happy to receive feedback on how we frame this issue and try to build some paths forward for researchers. w/ Andrew Gruen, @gmaldoff, @SolomonMg, @ZeveSanderson, & @michaelzimmer

✨ New work with wonderful coauthors @JosephineLukito @MG_Macdonald @bin_chen19 @m_dot_brown @stprochas @yangyunkang @j___greenfield @jiyoun_suk @rociozhong @borah

📢 Thrilled to share our new article introducing CampaignView—a comprehensive open-source dataset of congressional candidate campaign bios and policy platforms (2018–2022). Paper + data here: https://t.co/gUXMrmXZ4S & https://t.co/XMCbO6wjl7 🧵1/4

Can large language models (LLMs) fairly annotate data on contentious topics? Our new paper dives into this question—looking at whether LLM-generated labels reflect diverse viewpoints or skew toward majority perspectives. The results are surprisingly nuanced. 🧵

🧵 NEW PAPER - "Quantifying Narrative Similarity Across Languages" is live at SMR. We combine NLP w pairwise LLM evals to track ideas across media ecosystems and languages. We also figured out a way to eval unsupervised probs on widely understood supervised performance metrics.

[New WP] With the closure of major social media APIs and the new data access mandates under DSA, we entered what we call the "post-post-API" era. But have researchers obtained the data they need? Our recent survey (180) + interview (19) study suggests a stark reality. 1/2

So excited to finally see this out! It was the first paper I started during my postdoc at @CSMaP_NYU

Delighted to see this in print, six Septembers after I scribbled down an idea for a term paper, five Septembers after it tumbled out of the nest as a 2nd year paper! Read on if you’re interested in motivated reasoning, opinion backlash, BJP partisan identity, demonetization.

ever since i was a little girl i wanted to fill a gap in the literature

💯 Relatedly, @transparenttech and @GWIDDP has an ongoing survey & audit to understand (1) data access loss and (2) whether the DSA provides sufficient data to researchers. We're still fielding survey responses! https://t.co/eZs61Wa3p4 For more info: https://t.co/7ie3X5gmE3

🚨 Timely paper alert 🚨 Want to learn more about the political impacts of small-dollar donors in (congressional) elections? Check out our new working paper (with @MG_Macdonald and @m_dot_brown) and stay tuned for more on this project at APSA https://t.co/B4AyeYA25l

It was a treat to participate in a panel on research infrastructure and our ongoing work on the impact of data access on research at #ICA24 🐨🦘🇦🇺

@PhilKnopf @Kudusch @DubelRoeland @GijsSchumacher @MaaikeHoman @_d_peterson @bnbakker Although common automated transcription and computational phonology tools are accurate, small discrepancies in these tools can impact results. https://t.co/MG4m1T0KWE @JosephineLukito @j___greenfield @yangyunkang @Ross_Dahlke @m_dot_brown @beccalew @bin_chen19

Congrats to Megan Brown and co-authors on publishing a new article about Nextdoor communities. Brown is a student of proud co-advisors, ICPSR's Maggie Levenstein and Libby Hemphill https://t.co/nSBly8uGg1 @umsi

UMSI at #ICWSM24: Digital town square? Nextdoor's offline contexts and online discourse Megan A. Brown, Zeve Sanderson, Sarah Graham, Minjoo Kim, Joshua A. Tucker, Solomon Messing @m_dot_brown https://t.co/9LFvTGgjg1

Digital media research is changing, and it can make it that much harder to study elections, as @m_dot_brown and I argue in our new @techpolicypress piece. https://t.co/D37ECfWBJn

Excited to see this @journalqd ! The latest of several papers with @KirstenWidner and @annagunderson examining what interest groups do on social media 🐊🍾🍻

Super excited to see this paper in print! We show where Nextdoor neighborhoods are more likely to be and talk about what gets talked about on Nextdoor. We'll be presenting this on June 4 at 4:30p at @icwsm, so catch it if you're there! Paper🔗 and summary in 🧵👇

Social media research & reporting often focuses on large platforms. Much less is known about hyperlocal sites like @Nextdoor, used by 1/3 US households. In @journalqd, we help fill this gap w/new data exploring communities & conversations on the site. 1/ https://t.co/rI2nPoxzWb