Aleksandar Tomasevic (@atomasevic) 's Twitter Profile
Aleksandar Tomasevic

@atomasevic

Computational social science.

Assistant professor at University of Novi Sad.

🕸🐍🐧👨🏻‍💻 #RStats (random ordering).

ID: 27249987

linkhttp://www.atomasevic.com calendar_today28-03-2009 15:45:50

2,2K Tweet

984 Followers

1,1K Following

Hudson Golino (@golinohudson) 's Twitter Profile Photo

Tomorrow, from 9 to 10:15 am at Psychometric Society, join us for our symposium - Generative Psychometrics: Advancing Psychological Scale Development Through Large Language Models. Lara Russell-Lasalandra will (Lara Russell-Lasalandra) talk about AI-GENIE: A simulation study on the fully automatic

Tomorrow, from 9 to 10:15 am at <a href="/pmetricsoc/">Psychometric Society</a>, join us for our symposium - Generative Psychometrics: Advancing Psychological Scale Development Through Large Language Models. Lara Russell-Lasalandra will (<a href="/larafromUVA/">Lara Russell-Lasalandra</a>) talk about AI-GENIE: A simulation study on the fully automatic
Hudson Golino (@golinohudson) 's Twitter Profile Photo

Come learn with me and Lara Russell-Lasalandra how to automatically generate items and validate them (structural validity) using Large Language Models and Network Methods from Exploratory Graph Analysis!

Michiel ☁️ (@michielstock) 's Twitter Profile Photo

Are you a scientist who uses notebooks for learning, planning, organizing, etc? I am interested in collecting scans of scientists' lab notebooks, field journals, or personal notebooks. Please share some via this form. RT=🤟 docs.google.com/forms/d/e/1FAI…

Are you a scientist who uses notebooks for learning, planning, organizing, etc? I am interested in collecting scans of scientists' lab notebooks, field journals, or personal notebooks. Please share some via this form. 
RT=🤟
docs.google.com/forms/d/e/1FAI…
Observatory on Social Media (@osome_iu) 's Twitter Profile Photo

More and more papers are proposing to use LLMs to simulate human agents in agent-based models. I have strong reservations about attribution/causation/interpretability in this methodology, as I discuss in this article about one (excellent) such paper: 🧪 science.org/content/articl…

Bojana Dinić (@b_dinic) 's Twitter Profile Photo

💔 How do people break up? 🧵 We found that insecure attachment styles & dark traits (esp. secondary psychopathy) predict more toxic breakup strategies—ghosting, manipulation, escalation—while secure people lean toward healthier endings: authors.elsevier.com/c/1ldqFheKe07mm

💔 How do people break up? 🧵
We found that insecure attachment styles &amp; dark traits (esp. secondary psychopathy) predict more toxic breakup strategies—ghosting, manipulation, escalation—while secure people lean toward healthier endings:
authors.elsevier.com/c/1ldqFheKe07mm
Computers and Society Papers (@wgov) 's Twitter Profile Photo

Operational Validation of Large-Language-Model Agent Social Simulation: Evidence from Voat v/technology. arxiv.org/abs/2508.21740

Hudson Golino (@golinohudson) 's Twitter Profile Photo

How does OpenAI's OSS-120b, OSS-20b, and DeepSeek models compare to GPT-3.5, GPT-4o, Llama-3, Gemma-2, and Mixtral's models for automatic item generation and validation? How does the in-silica structural validity of items developed with GPT-3.5, GPT-4o, Llama-3, Gemma-2, and

Hudson Golino (@golinohudson) 's Twitter Profile Photo

New paper alert: A Systematic Evaluation of Wording Effects Modeling Under the Exploratory Structural Equation Modeling Framework. Led by Dr. Luis Garrido: Wording effects, the systematic method variance arising from the inconsistent responding to positively and negatively

New paper alert: A Systematic Evaluation of Wording Effects Modeling Under the Exploratory Structural Equation Modeling Framework. Led by Dr. Luis Garrido:

Wording effects, the systematic method variance arising from the inconsistent responding
to positively and negatively
Hudson Golino (@golinohudson) 's Twitter Profile Photo

Rethinking Personality: What if the Big Five isn't the full story? Our latest research using Topological Graph Analysis (TGA) has uncovered something remarkable, entirely new personality dimensions that challenge how we understand human traits. While traditional models give us

Rethinking Personality: What if the Big Five isn't the full story?
Our latest research using Topological Graph Analysis (TGA) has uncovered something remarkable, entirely new personality dimensions that challenge how we understand human traits.
While traditional models give us