Summer School in Quantitative Analysis of Textual Data (7th edition)

Host Institution: University of Padua
Website: https://www.fisppa.unipd.it/giat-en/summer%20school

Dates: 08-Sep-2025 - 12-Sep-2025
Location: University of Padua, Italy

Minimum Education Level: bachelor's and master's graduates, PhD students

Focus: This edition's topic is the challenges that artificial intelligence (AI) and the use of large language models (LLMs) have posed to traditional methods of textual data analysis. The guiding question for the 2025 edition is "Large Language Models: Does AI Challenge Traditional Methods?"

The School is designed for bachelor's and master's graduates, PhD students, post-docs, researchers, and scholars (both academic and non-academic) from all disciplines within the humanities and social sciences who are interested in tools for studying large digital text corpora, including newspapers, social media, documents, novels, and interviews.
The activities of the School are designed to stimulate critical reflection on the advantages and limitations of methods, and to engage participants in an interdisciplinary context to discuss the potential, challenges, and opportunities of different approaches. The interdisciplinarity of the School is ensured both by the presence of speakers from various scientific fields and by the diverse backgrounds of the participants.

The School aims to share knowledge on methods, software, corpora, scientific literature, and research
outcomes; promote dialogue among disciplines on a timely issue such as the use of LLMs in text analysis;

develop innovative analytical tools and integrated research methods; introduce young researchers to high-
quality research environments.

Description:

Active since 2013 and now in its seventh edition, the IQLA-GIAT International Summer School in Quantitative Analysis of Textual Data is a distinguished training opportunity in the fields of computational text analysis and digital humanities. Methods for the quantitative analysis of textual data are an object of research in linguistics, computer science, social sciences, mathematics, and statistics but they also serve as valuable research tools across further disciplines, such as psychology, philosophy, sociology, sociolinguistics, education, history, political studies, literary studies, communication, and media studies.
Digital sources that provide archives of books, documents, and journals or disseminate information, such as newspapers and social media, now constitute an essential foundation for many research studies. Recent developments in computational methods and large language models have not only transformed how research is conducted in the humanities and social sciences but also reshaped how it is conceived and designed. The demand for data scientists is growing in all disciplines, both in academia and in productive and commercial sectors, and a new generation of researchers must be trained to apply data science methods to a wider range of applications.

The IQLA-GIAT Summer School is defined by three main elements:
1. A general section dedicated to quantitative methods for text analysis.
2. A distinctive methodological topic that has changed in each edition.
2025: Large Language Models: Does AI Challenge Traditional Methods?
2023: Language Variation and Change from a Computational Perspective
2021: Quality of Texts quality of News (online edition)
2019: Data Science and Data scientists in Humanities and Social Sciences
2017: Topic detection and authorship attribution in Elena Ferrante's case-study
2015: Measuring style and computational stylistics
2013: Measures and methods in authorship attribution
3. Lab-tutorials dedicated to case studies and computer-aided analysis of textual data.
- Would you like to analyse large volumes of text, such as novels, transcriptions of open-ended interviews, scientific literature, or social media comments, to identify patterns and trends in language usage? Are there simply too many texts for any scholar to read in a lifetime?
- Why not let a computer do the work?
- While software can’t perform close reading, mathematical and statistical tools can be used for distant reading, collecting data, extracting relevant information, summarizing features, and identifying patterns. Instead of reading a limited number of texts, why not work with thousands, upload them to a computer, and let software generate analyses and results?

Linguistic Field(s): Computational Linguistics
Text/Corpus Linguistics

Subject Language(s): English (eng)

Registration Open until 31-May-2025

Apply by Email: [email protected]

Registration Instructions:
The IQLA-GIAT Summer School is open to 20 participants including researchers, scholars and postgraduate students.

Applicants must send a file in pdf format including:
1. curriculum vitae
2. personal mission statement and research interests (max 500 words)
Applications should be sent to the following address: [email protected]

Please note that there is no selection procedure and that the limited seats will be sold on a "first-come, first-served" basis.

Deadline: May, 31st
Tuition fee: 300€
The first 20 applicants will receive information to complete their registration with the payment of the tuition fee. The tuition fee includes coffee breaks, lunches and the social dinner.