Sign in

Michael Heseltine

@michaelheseltine.bsky.social
428 followers 270 following 50 posts

Post-Doc at University of Oxford. Congress, text-as-data, and political communications.

PostsRepliesMedia
Michael Heseltine @michaelheseltine.bsky.social · 23/09/2026
I can't unsee this as anything but At The Drive In headlining the event
010
Michael Heseltine @michaelheseltine.bsky.social · 09/09/2026
We classify across across multiple measures that we hope will be of interest to congress and communications scholars. We're also launching a public data portal so anyone can explore and download the classifications. More to follow on that soon!
000
Michael Heseltine @michaelheseltine.bsky.social · 09/09/2026
Excited to share our new @apsrjournal.bsky.social paper! We introduce the Scaled & Classified Congressional Communication (SCCC) dataset: 7M+ congressional communications across X, Facebook, and email, classified by topic, tone, and a range of core strategic measures. doi.org/10.1017/S000...
doi.org
Measuring Partisanship and Representation in Online Congressional Communications | American Political Science Review | Cambridge Core
Measuring Partisanship and Representation in Online Congressional Communications
131
Michael Heseltine @michaelheseltine.bsky.social · 09/09/2026
Admittedly I don't admit PhD students, but 150 feels a little low to be a positive signal. I seem to remember 160 being a decent benchmark (arguably higher verbal). Suppose they could always do it and not send it?
110
Reposted by Michael Heseltine
American Political Science Review @apsrjournal.bsky.social · 03/09/2026
From our FirstView: Measuring Partisanship and Representation in Online Congressional Communications by Michael Kistner @mkistner.bsky.social, Michael Heseltine @michaelheseltine.bsky.social, Robert Alvarez, Maya Fitch, Lucas Lothamer, and Elizabeth Simas @bethsimas.bsky.social buff.ly/Wlnc5LY
doi.org
Measuring Partisanship and Representation in Online Congressional Communications | American Political Science Review | Cambridge Core
Measuring Partisanship and Representation in Online Congressional Communications
063
Michael Heseltine @michaelheseltine.bsky.social · 17/06/2026
AI could never...
020
Reposted by Michael Heseltine
Christopher Barrie @cbarrie.bsky.social · 02/06/2026
📄 New paper: people choose AI models partly on political grounds This is joint work with @pettertornberg.com @chrisbail.bsky.social @michelleschimmel.bsky.social and led by @michaelheseltine.bsky.social
26227
Michael Heseltine @michaelheseltine.bsky.social · 20/05/2026
One thing I'll note here is that Trump has historically always been very influential the the primary stage. I think the dynamic of endorsing against incumbents may be ramped up and making things more high profile this cycle, but still in line with prior trends. www.sciencedirect.com/science/arti...
151
Reposted by Michael Heseltine
Jon Green @jongreen.bsky.social · 13/05/2026
now online! link.springer.com/article/10.1...
1114
Reposted by Michael Heseltine
Nate Persily @persily.bsky.social · 06/05/2026
The Draft Volume of the APSA AI Task Force, cochaired by Josh Tucker and me, is now available. ARTIFICIAL INTELLIGENCE, POLITICS, AND POLITICAL SCIENCE will be published by Cambridge Press later this year, but the draft chapters are available today: apsanet.org/wp-content/u...
03518
Reposted by Michael Heseltine
Petter Törnberg @pettertornberg.com · 08/04/2026
Like Grok and Attie, more and more social media platforms now integrate AI directly in online conversations. But how do these AI bots actually impact political discourse? We ran a series of experiments to find out. (Spoiler: the news are not altogether great.) osf.io/preprints/so...
osf.io
OSF
1226
Michael Heseltine @michaelheseltine.bsky.social · 12/03/2026
Dream content for @reuning.bsky.social ...
120
Reposted by Michael Heseltine
Michael Heseltine @michaelheseltine.bsky.social · 07/01/2026
🚨NEW PAPER Going Local? Localized Rhetoric in Congressional Communications Is congressional comms really nationalized? Analyzing 9M+ social media posts from Members of Congress, I show that local messaging is still common & strategic. New ML + domain sharing data www.tandfonline.com/doi/full/10....
tandfonline.com
Going Local? Localized Rhetoric in Congressional Communications
In the face of the purported nationalization of political discourse in the United States, to what extent do congressional representatives still engage locally through their public communications? B...
1117
Michael Heseltine @michaelheseltine.bsky.social · 07/01/2026
This is my favorite project that I have worked on and I think the findings have important implications for how we think about the nationalization of politics in the US. Members are still going local in comms. I hope Congress and comms scholars find this useful. #Polcomm @polcomm.bsky.social
020
Michael Heseltine @michaelheseltine.bsky.social · 07/01/2026
In general, Presidential control, ideological extremity, electoral safety predict the use of localized messaging by Members. As does, in perhaps my favorite finding, Member seniority/freshman status - newer Members strategically engage more locally with their districts!
110
Michael Heseltine @michaelheseltine.bsky.social · 07/01/2026
I analyze multiple platforms (Twitter and Facebook) and multiple modes (messages and link sharing) to get a multi-faceted look at localized messaging. This inlcudes a local/national classification of over 45,000 shared web domains. The ML text classifier also performs really well.
110
Michael Heseltine @michaelheseltine.bsky.social · 07/01/2026
Centrally, the use of localized messaging varies by party based on partisan control of the White House (and congressional chamber). Governing parties use messaging on localized benefits, opposition focuses more on national political developments. This results in a visually pleasing back and forth.
100
Michael Heseltine @michaelheseltine.bsky.social · 07/01/2026
🚨NEW PAPER Going Local? Localized Rhetoric in Congressional Communications Is congressional comms really nationalized? Analyzing 9M+ social media posts from Members of Congress, I show that local messaging is still common & strategic. New ML + domain sharing data www.tandfonline.com/doi/full/10....
tandfonline.com
Going Local? Localized Rhetoric in Congressional Communications
In the face of the purported nationalization of political discourse in the United States, to what extent do congressional representatives still engage locally through their public communications? B...
1117
Michael Heseltine @michaelheseltine.bsky.social · 14/12/2025
I'm not writing that chapter, so it'll be not the worst!
010
Michael Heseltine @michaelheseltine.bsky.social · 14/12/2025
There's a apsa presidential taskforce on AI which will release a report next year with teaching being a chapter
120
Michael Heseltine @michaelheseltine.bsky.social · 21/11/2025
An annoyingly good idea and well executed!
110
Michael Heseltine @michaelheseltine.bsky.social · 20/11/2025
I recently reviewed a paper that had not 3 but 5 reviewers on it, so seems to be some inefficiencies in the market here! Maybe Europeans just say yes more?
010
Reposted by Michael Heseltine
British Journal of Political Science @bjpols.bsky.social · 07/10/2025
#OpenAccess - Believing What Politicians Communicate: Ideological Presentation of Self and Voters’ Perceptions of Politician Ideology - cup.org/4gTSToM - @hjghassell.bsky.social, @michaelheseltine.bsky.social & @reuning.bsky.social ‬ #FirstView
BJPolS abstract which discusses the relationship between politicians' communication and voter perceptions through social media content analysis between 2012 and 2022.
065
Michael Heseltine @michaelheseltine.bsky.social · 03/10/2025
🥳 Our new paper is out at the British Journal of Political Science. We find a strong link between the ideology of candidate messaging and the perceived ideology of these candidates among voters. Evidence that voters can differentiate between candidates and are attuned to what candidates say.
0196
Michael Heseltine @michaelheseltine.bsky.social · 26/08/2025
And here's Facebook. Really does seem to be a Covid term!
130
Michael Heseltine @michaelheseltine.bsky.social · 12/08/2025
Size matters: LLama 3.1/3.3 70b perform best, along with Qwen2/2.5 72b. Gemma2 and Phi4 stand out as strong mid-sized models. Many smaller models produce poor results. Model selection can have a huge impact on your results!
000
Michael Heseltine @michaelheseltine.bsky.social · 12/08/2025
📜Preprint!📜 GPT5 replacing GPT4 effectively renders a whole range of existing GPT-reliant research unreproduceable. Open-source LLMs offer a science-friendly alternative, but which to use? I test 28 different LLMS in 7 languages so you can pick the best models for your task. osf.io/preprints/os...
140
Michael Heseltine @michaelheseltine.bsky.social · 03/08/2025
Just started using atrrr for search and user post collection. Firehose would be a massive plus!
110
Michael Heseltine @michaelheseltine.bsky.social · 02/07/2025
113th congress starts in '13 is my go-to shorthand!
010
Michael Heseltine @michaelheseltine.bsky.social · 30/06/2025
Fresh email this morning: "an account has been created for you in ScholarOne", nooooo!
010
Reposted by Michael Heseltine
Kevin Reuning @reuning.bsky.social · 27/06/2025
I have a new paper forthcoming at BJPS with @hjghassell.bsky.social and @michaelheseltine.bsky.social looking at how social media messaging impacts perceptions of incumbent/candidate ideology. We find messaging ideology does relate to perceptions w/overtime changes Pre-print: osf.io/preprints/so...
1116
Michael Heseltine @michaelheseltine.bsky.social · 01/05/2025
Bit chicken and egg though, did researchers adjust to stargazer or did stargazer adjust its defaults to perceived research practices
000
Michael Heseltine @michaelheseltine.bsky.social · 01/05/2025
My hunch would be at least some creep after the rise of stargazer as a default tabulating method, with its default of * for 0.1.
110
Michael Heseltine @michaelheseltine.bsky.social · 25/03/2025
Accept it with arms wide open, Kevin...
010
Michael Heseltine @michaelheseltine.bsky.social · 14/03/2025
Worked in three reps offices. Member 1 was given weekly tally of calls, never saw emails. Member 2 given no information on either. Member 3 informal updates on calls, never saw emails. 99% is just fielded by interns. Up to the individual Member whether they care to receive any of it.
020
Michael Heseltine @michaelheseltine.bsky.social · 11/03/2025
An extra 128gb ram and any 16gb or 24gb Nvidia gpu ... Alternatively, an absolute tonne of gaudy strobe rgb fans
110
Michael Heseltine @michaelheseltine.bsky.social · 11/03/2025
@sysilviakim.bsky.social Coming to a JOP issue near you!
230
Michael Heseltine @michaelheseltine.bsky.social · 26/02/2025
I think @jbgruber.bsky.social is the expert on this?
110
Michael Heseltine @michaelheseltine.bsky.social · 09/02/2025
Science!
010
Reposted by Michael Heseltine
Research & Politics @respol.bsky.social · 11/01/2025
R&P editors' collection 2024 (2/4) @michaelheseltine.bsky.social & B. C. von Hohenberg find that GPT-4 coding of political text is highly accurate for shorter texts, but performance drops for longer ones, suggesting consideration should be given to task complexity when using LLM-assisted coding.
doi.org
Sage Journals: Discover world-class research
Subscription and open access journals from Sage, the world's leading independent academic publisher.
131
Michael Heseltine @michaelheseltine.bsky.social · 07/01/2025
🚨New at AJPS to start off the year! Do partisans change their news consumption based on daily news sentiment about their team? Democrats read more news on bad days for Republicans and less on bad days for Dems. Republicans turn to more conservative news on bad days for Republicans.
onlinelibrary.wiley.com
American Journal of Political Science | MPSA Journal | Wiley Online Library
We assess the phenomenon of partisan temporal selective avoidance, or individuals dynamically altering their news consumption when news is negative toward their in- and out-party. Using nine months o...
040
Reposted by Michael Heseltine
Matt Grossmann @mattgrossmann.bsky.social · 07/01/2025
Democrats reduce news consumption when daily news sentiment is negative toward Democrats & increase it when it is negative toward Republicans. Republicans respond to negative Republican sentiment by increasing consumption at conservative news outlets. onlinelibrary.wiley.com/doi/10.1111/...
onlinelibrary.wiley.com
American Journal of Political Science | MPSA Journal | Wiley Online Library
We assess the phenomenon of partisan temporal selective avoidance, or individuals dynamically altering their news consumption when news is negative toward their in- and out-party. Using nine months o....
34313
Michael Heseltine @michaelheseltine.bsky.social · 20/12/2024
My article "Asymmetric Polarization in Online Media Engagement in the United States Congress" is published in the latest edition of IJPP. Republican media engagement and sharing on social media has increased in extremity over time, but not Democratic. Clear Trump effect. doi.org/10.1177/1940...
000
Michael Heseltine @michaelheseltine.bsky.social · 05/12/2024
Also... the social sciences have absolutely destroyed the respondent pool in convenience sample pools around the world through the over-proliferation of survey research. Not sure how to fix that, but running even more surveys not likely the answer.
120
Michael Heseltine @michaelheseltine.bsky.social · 05/12/2024
Very feasible scenario is: 1) grad student begs for some money and runs survey and writes paper. 2) reviewer or journal policy says "that's nice, now run it again so I believe you" 3) grad student goes back to begging, or pulls paper? Massive chunk of the discipline is priced out of experiments atm.
240
Michael Heseltine @michaelheseltine.bsky.social · 27/11/2024
Does every self-citation I've ever done count?
010
Michael Heseltine @michaelheseltine.bsky.social · 27/11/2024
Having one of the top-tier generalist journals in the discipline being almost unusable for early career scholars is sub-optimal for the discipline, to put it mildly.
150
Michael Heseltine @michaelheseltine.bsky.social · 27/11/2024
Added unseen impact on junior scholars as well... I have not submitted to JoP in at least 3 years because the time suck does not seem worth the calculated risk of having the paper sitting there. I suspect many opt to underplace papers just to have them out rather than take the risk...
170
Michael Heseltine @michaelheseltine.bsky.social · 20/11/2024
Technically gpt can search the web, so prompting based on referencing latest documentation could alleviate some of this. I ask it to look up packages on github and it's very proficient. But also yes...
010
Michael Heseltine @michaelheseltine.bsky.social · 15/11/2024
✏️New in Political Communication ✏️ w/ great coauthors. We examine perceived polarization in the US and Poland. Both exposure to partisan news and exposure to general coverage with polarization reporting frames increase perceived personal distance from other side. www.tandfonline.com/doi/full/10....
tandfonline.com
Effects of Over-Time Exposure to Partisan Media and Coverage of Polarization on Perceived Polarization
America is said to be more polarized than ever before, and extensive research examines the causes and effects of political polarization. A less studied but more pronounced trend is that citizens pe...
053