Seminarium PAN-Metrics

Zapraszamy na nowy cykl seminariów organizowany przez Zakład Obliczeniowych Nauk Społecznych (kierownik: prof. Artur Pokropek)!

Seminaria PAN-Metrics będą poruszać tematykę metodologii i pomiaru w szeroko pojętych naukach społecznych. Dokładny opis seminarium w załączonym pliku.

Pierwsze spotkanie odbędzie się online, 18 listopada o godz. 16:00. 

Prelegentem będzie dr Maciej Pankiewicz (University of Pennsylvania), który zaprezentuje prezentację pt. Innovative Applications of Large Language Models in Research: A Focus on Education

Streszczenie wystąpienia:

In this presentation, I will explore the transformative role of Large Language Models (LLMs) in educational research. I’ll begin by discussing LLM techniques used in my research, such as prompt engineering, few-shot learning, Retrieval-Augmented Generation (RAG), and embeddings, highlighting how these methods enhance data analysis and interpretation. I’ll introduce examples using diverse data sources—including video recordings, discussion forums, and programming datasets—to demonstrate the flexibility and breadth of LLM applications. Through projects like JeepyTA, I’ll show how LLMs may be used to impact learning processes, enabling personalized learning experiences, and opening new avenues for data-driven educational studies.

Prosimy o kontakt celem uzyskania linku do Zoom na mail marek.muszynski@ifispan.edu.

PAN-Metrics Seminar

We would like to invite you to a new series of seminars organized by the Department of Computational Social Sciences (head: Prof. Artur Pokropek). PAN-Metrics seminars will cover the topics of methodology and measurement in the broadly defined social sciences. Please find a detailed description of the seminar attached to this email.

The first meeting will be held online on November 18 at 4 p.m. (16:00).

The speaker will be Dr. Maciej Pankiewicz (University of Pennsylvania), who will give a presentation entitled: Innovative Applications of Large Language Models in Research: A Focus on Education.

Abstract:

In this presentation, I will explore the transformative role of Large Language Models (LLMs) in educational research. I’ll begin by discussing LLM techniques used in my research, such as prompt engineering, few-shot learning, Retrieval-Augmented Generation (RAG), and embeddings, highlighting how these methods enhance data analysis and interpretation. I’ll introduce examples using diverse data sources—including video recordings, discussion forums, and programming datasets—to demonstrate the flexibility and breadth of LLM applications. Through projects like JeepyTA, I’ll show how LLMs may be used to impact learning processes, enabling personalized learning experiences, and opening new avenues for data-driven educational studies.

Please contact us to receive the Zoom link.

PAN-Metrics Seminar on Novel Measurement Problems in Social Sciences Seminar Topics

The seminar explores measurement challenges within the broad scope of the social sciences, particularly focusing on sociology, psychology, and educational sciences. Its primary topics include:

1. Measurement distortions and response biases, such as response styles, careless or inattentive responding, social desirability effects, and related phenomena. Exploration of statistical methods and tools to identify and adjust for various types of response biases in data.
2. The collection, processing, and analytical utilisation of process data (log data) and other paradata to improve measurement precision in social sciences.
3. Technological innovations in measurement, including the application of computers, machine learning methods, and large language models (“artificial intelligence”), as well as their impact on measurement development, analysis, and validation.
4. Statistical modelling of latent variables, addressing new response models, measurement invariance, and related issues.
5. Additional measurement and modelling challenges in social sciences, encompassing psychometric, statistical, and methodological considerations (including applied settings).

Discussions will cover both cognitive (e.g., tests) and non-cognitive measures (surveys and questionnaires), with an emphasis on measurement processes mediated by new technologies such as computers, smartphones, and online research methodologies. Innovative measurement approaches that extend beyond traditional tools and leverage new technologies are particularly welcome.

Organisational Details: The seminar sessions are organised by members of the Computational Social Science Department, led by Prof. Artur Pokropek, under the auspices of the Institute of Philosophy and Sociology of the Polish Academy of Sciences. Sessions are scheduled monthly, primarily online, featuring one or two guest speakers and lasting approximately one hour.

For suggestions regarding invited speakers, topics, or any other organisational matters, please contact: marek.muszynski@ifispan.edu.

classic-editor-remember:

block-editor