Flyer für PoliCorp
Wir sehen uns in Hannover mit #PoliCorp im Gepäck
policorp.pollux-fid.de 🤗
#Methoden #TextAsData #Textkorpora
Latest posts tagged with #textAsData on Bluesky
Flyer für PoliCorp
Wir sehen uns in Hannover mit #PoliCorp im Gepäck
policorp.pollux-fid.de 🤗
#Methoden #TextAsData #Textkorpora
Mental model sketch to visualize the trade-off function to consider when choosing tools from the text-as-data toolbox. The plot shows each method’s capability range: the vertical span indicates the task complexity each method can handle, while the horizontal position shows the resources required to implement that method for tasks within its capability. The areas overlap because more sophisticated methods can also solve simpler tasks: LLMs can do everything dictionaries can do, just at higher cost. The “optimal method line” represents the most efficient choice: the least resource-intensive method capable of handling a given task complexity.
After showing it in several presentations already, the publication is where my mental model for choosing a #textasdata method finally found a home. Not perfect, but it has proven useful.
Today, 10th febuary, 11 AM, webinar on "Open Political Corpora. Structured search and analysis of political text collections with [#PoliCorp](policorp.pollux-fid.de)." (in english) 🏛️ #GermaParl #StateParl #TextasData #politicalscience #polsci
▶️ registration: uni-bremen.zoom-x.de/meeting/regi...
🚨 Happening tomorrow!
On Jan 16, join the #AMLEDS webinar w/ @amanela.bsky.social (WashU) on Lookahead Bias with #LLMs.
If you use LLMs on historical data, this talk shows how to detect and fix lookahead bias .
🕚 11am ET · 5pm CET
#AI #DataScience #Economics #TextAsData #Forecasting #EconSky
AMLEDS webinar on Look-Ahead bias with LLMs: Measurement and Mitigation Techniques with Asaf Manela (Washington University in St. Louis) and Andreas Joseph (Bank of England) as moderator! Jan 16, 2026!
🚨 LLMs+research=beware of #lookahead #bias 🚨
On Jan 16, 2026, join the #AMLEDS webinar w/ @amanela.bsky.social (WashU) on Lookahead Bias with #LLMs!
How do we do credible #forecasting or #TextAsData analysis when models have seen the future?
🕚 11am ET-5pm CET
#AI #EconTwitter #EconSky #NLP #ML
If you do research with/about LLMs, image or audio models, or classic NLP methods, you should check out this call 👇
#textasdata #NLP #llm #commsky #polsky
Correct link: sites.google.com/view/dariia-...
Many thanks to @dariia.bsky.social for organizing this amazing workshop series. The lineup has been fantastic. Great to be in such company!
#WorkshopForUkraine #TextAsData #Python #AcademicSolidarity
#WorkshopForUkraine 🇺🇦 I’ll run a hands-on session on Text Data in Python. We will show showing how to turn messy documents (PDFs, Word files, scraped text) into usable data.
sites.google.com/.../main/r-w....
Join if you’re curious, or share with others. Proceeds go to Ukraine.
#TextAsData #Python
This scales corruption measurement to the universe of audited municipalities. It's transparent, replicable, & cost-effective (unlike hand-coding or LLMs).
📄 Paper: papers.ssrn.com/sol3/papers....
#TextAsData #Corruption #NLP #MachineLearning #Research #Methodology #OpenScience End/
➡️ Predoctoral Research Fellow / PhD Candidate
👉 75%, 3 years, @wzb.bsky.social
👉 Focus: Quantitative text analysis ( #NLP | #CSS | #TextAsData ) on global crisis perceptions and dissertation research
👉 Full job call: www.wzb.eu/en/jobs/pred...
➡️ Predoctoral Research Fellow / PhD Candidate
👉 75%, 3 years, @WZB Berlin
👉 Focus: Quantitative text analysis ( #NLP | #CSS | #TextAsData ) on global crisis perceptions and dissertation research
👉 Full job call: www.wzb.eu/en/jobs/pred...
Anmeldung noch bis kurz vor 11 Uhr geöffnet: Parlamentsdebatten auf Weboberfläche strukturiert durchsuchen: Wie das mit PoliCorp geht, zeigen wir jetzt gleich, live: uni-bremen.zoom-x.de/meeting/regi...
#StateParl #GermaParl #TextAsData #PoWi #Polsci
Pollux-Webinar Grafik
📣7.10., 11-12 Uhr, PoliCorp-Webinar. Anmelden hier: uni-bremen.zoom-x.de/meeting/regi...
PoliCorp (demo-pollux.gesis.org) bietet Forschenden einen strukturierten und durchsuchbaren Zugang zu verarbeiteten Textkorpora, derzeit 76 Jahre Parlamentsdebatten. #Germaparl #textasdata #Polsci #Powi
📡 In this new paper, we show how framing #climate change linkages helps or slows the spread of those linkages on social media. Big thanks to my co-author @karinashyrokykh.bsky.social! @scgg-official.bsky.social @stockholm-uni.bsky.social #textasdata #polisky @esg-journal.bsky.social
Yes. #textasdata
"Trust me, Bro!": You should read this working paper if you consider using commercial #LLM endpoints for annotating #TextAsData
arthurspirling.org/documents/Ba...
🤔 The #EU 🇪🇺 aspires to be a global actor 🌍 — but do other states recognize it as such?
My new study in @intlinteractions.bsky.social develops targeted #NLP / #TextAsData tools to analyze 50 years of foreign policy discourse in the annual #UN General Debate (1970–2020).
A thread (1/n)
#computationalsocialsciences, #jobsjobsjobs, #textasdata, für mein DFG-Projekt zur Fragmentierung digitaler Nachrichtenpublika mit Frank Mangold @gesis.org suche ich eine*n Doktorand*in mit Interesse an den neuesten (KI-gestützten) Methoden der Inhaltsanalyse
www.uni-hamburg.de/stellenangeb...
Framing the Domestic Economy: Media, Policy, and Public Perception Time: Friday, 25/Apr/2025: 10:45am - 12:15pm · Location: SR 04 Session Chair: Matilde Ceron, University of Salzburg Discussant: Hugo Subtil, University of Zurich Hidden barriers to open competition: Using text mining to uncover corrupt restrictions to competition in public procurement Eszter Katona1,3, Mihály Fazekas2,3 1Eötvös Loránd University, Hungary; 2Central European University; 3Government Transparency Institute From Prices to Politics: Framing the Causes of Inflation at the Federal Reserve (1970-2023) Benjamin Braun1, Jérôme Deyris2, Monica DiLeo3 1London School of Economics; 2Sciences Po, France; 3Hertie School, Berlin Salience and anti-elitism of wealth elites in UK newspapers Michael Kevin Vaughan London School of Economics and Political Science, United Kingdom Shifting Priorities: How the New Economic Reality Influences Youth Perspectives in Türkiye Ayşe Zeynep Zülfikar1, Ubeyd Öktem1,2 1Koç University, Türkiye; 2Bilgi University, Türkiye
Discourses On Group Identities and Their Measurement Time: Saturday, 26/Apr/2025: 4:30pm - 6:00pm · Location: SR 06 Session Chair: Marvin Stecker, University of Vienna Discussant: Camilo Cristancho, Universitat de Barcelona Politicians’ discursive use of social identities and citizens’ self-identification Naama Rivlin-Angert1, Yael R. Kaplan2, Guy Mor-Lan3 1The Hebrew University of Jerusalem, Israel; 2The Open University of Israel; 3The Hebrew University of Jerusalem, Israel Is social group construction susceptible to crises? Selma Sarenkapa Sciences Po Paris, France SocialNER - A general method to detect social groups in computational text analysis Jonas Buettner, Pascal Jürgens, Nils Schwager Trier University, Germany Using LLMs to Detect Group Appeals in Parties’ Election Manifestos Will Horne1, Alona O. Dolinsky2, Lena Maria Huber3 1Clemson University; 2VU Amsterdam; 3MZES, University of Mannheim
Politics in Data, oven-ready: A Showcase Of New Datasets Time: Friday, 25/Apr/2025: 5:00pm - 6:15pm · Location: BIG Hörsaal lecture hall Session Chair: Christian Rauh, WZB Berlin Social Science Center Analyzing Sentiments towards the European Union in Slovak Parliamentary Speeches (1994–2023) Jakub Szabo Comenius University in Bratislava, Slovak Republic EuroParlBase: A Linked Database of European Parliament Data Verena Kunz University of Mannheim & GESIS - Leibniz Institute for the Social Sciences, Germany ParlLawSpeech Jan Schwalbach1, Lukas Hetzer2, Proksch Sven-Oliver2, Rauh Christian3, Sebők Miklós4 1Gesis Cologne; 2University of Cologne; 3WZB Berlin, University of Potsdam; 4Centre for Social Sciences Budapest The US Congressional Speeches Dataset, 1879-2022 Segun Aroyehun University of Konstanz, Germany The Weimar Parliament Database Benjamin Rohr1, John Levi Martin2, Jan Kamlah1, Julius Diener1, David Schweizer1 1University of Mannheim, Germany; 2University of Chicago, USA Group Appeals in Historical Perspective—Comparing Over 50 Years of Parties’ Election Campaign Communication with Social Groups. Alona O. Dolinsky1, Lena Maria Huber2, Will Horne3 1VU Amsterdam; 2MZES, University of Mannheim; 3Clemson University PartySoMe: Measuring party behavior and issue attention in 25 countries on Facebook, Instagram, Twitter, and YouTube Luis Sattelmayer, Malo Jan SciencesPo Paris, France
Shaping Politics: Constituency Influence, Parliamentary Debates, and Voter Priorities through Data-Driven Insights Time: Saturday, 26/Apr/2025: 4:30pm - 6:00pm · Location: SR 04 Session Chair: Alex Hartland, University of Saarland Discussant: Nicolai Berk, ETH Zurich Representing Prestige and Debt: How Local Attributes Influence Saliency and Ideology in Higher Education Discourse Sarah King University College Dublin, Ireland Discourse about the Left and Right in a Postcommunist Context: The Czech Case Štěpán Jabůrek, Jan Vondráček, Vojtěch Pohanka, Tomáš Kremla Charles University, Czech Republic Different priorities, different phrasing: Exploring gender differences in open-text responses to the ‘most important issue’ question. Louise Luxton1, Ceri Fowler2 1University of Manchester; 2St Hilda's College, University of Oxford United We Stand, Divided We Fall: Mainstream Party Agreement and Vote Switching to Far Right Competitors Luis Sattelmayer SciencesPo Paris, France Meanings of "The West" in Central and Eastern European Party Rhetoric Silvia Porciuleanu European University Institute, Italy
3 young scholars from our centre present at #COMPTEXT2025 in Vienna on Fri & Sat:
@jdeyris.bsky.social on Fed discourses
@selmasarenkapa.bsky.social on social group constructions
@luissattelmayer.bsky.social on party positions
#TextAsData
cc @comptext.bsky.social @edr-sciencespo.bsky.social
Day 2 at the #TextAsData Spring School from @dhpotsdam.bsky.social and @dhssfau.bsky.social
Making sure y'all saw this CfP for the Special Issue on Digital Communication in Social Movements.
Timeline: 8.3.25 abstract; 7.8.25 full paper; end of year publication.
#AI #TextasData #ImageAsData #SocialMovement #ScienceRocks
journal.computationalcommunication.org/announcement...
🚨 #Data alert 📣 We just released #ParlLawSpeech – full texts of more than 40k bills, 28k laws, and 3 mio. parliamentary speeches from 7 countries (AT, CZ, DE, DK, ES, HR, HU) and the EU! If you study democracy with #TextAsData / #NLP methods, this is for you! A short 🧵 (1/3) #PoliSkyData #polisky
📣Neu bei Pollux: Pollux Political Corpora (PoliCorp)
umfangreiche politische Textsammlungen (Korpora) können hier strukturiert durchsucht und analysiert werden.
mehr Infos: pollux-fid.de/news/2025/79
Hier geht es zur Demo-Version: lnkd.in/eCb3cgx5
#GermaParl #textasdata #fürdiepolitikwissenschaft
Next year, we are organizing the second edition of the #textasdata workshop in hydrology, natural hazards, and climate change research. Looking forward to discussing ways to collaborate with others!
📅 28.03.2025
📍 Leipzig, Germany
Apply by 01.02.2025 here: docs.google.com/forms/d/e/1F...
Thinking about using #LLM for your #textasdata research? …Thinktwice! And join our panel tomorrow at #aoir2024
"Polizeibeamter", "Selbständig", "Angestellter" - meine kleine Analyse der Berufsbezeichnungen von Kandidant:innen zur österr. Nationalratswahl 2024, mit einem Fokus auf #FPOE #nrw2024 #politischesoziologie #textasdata
tinyurl.com/yc68tfu5
✍️ New article in the Journal of Social Policy! My research on the sense of injustice around pandemic economic relief is now out and open access! #deservingness #moraleconomy #coronahilfen #textasdata #sociology doi.org/10.1017/S004...
@ifswien.bsky.social
Very cool and useful resource also for #econsky — more and more economists are doing amazing research using #textAsData e.g. @essobecker.bsky.social @raschky.bsky.social
The Language of (Non)Replicable Social Science #MetaScience #TextAsData
journals.sagepub.com/doi/full/10.... There are systematic differences in the discussion of findings that were and were not replicable.
I was thinking that methods competence could be a confounder 1/
Excited to have led a workshop on validating text-as-data and topic models at COMPTEXT24! Ensuring that our analysis meets scientific standards is key & don't forget: validate, validate, validate! #textasdata #topicmodels #COMPTEXT24