Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
Please note that all times are shown in the time zone of the conference. The current conference time is: 14th June 2025, 06:41:03pm WEST
Session Chair: Raffaele Viglianti, University of Maryland
Location:Aud B2 (TB)
152 places
Presentations
CodeFlow: Automating the Flow of Code with LLMs
Erik Bran Marino1, Davide Bassi2, Suso Baleato2, Renata Vieira1
1Universidade de Évora, Portugal; 2Universidade de Santiago de Compostela, Spain
Social scientists increasingly use NLP for large-scale text analysis but face programming challenges. CodeFlow automates code generation and optimization via LLMs, translating research goals into functional code. It achieved 0.95 accuracy in sentiment analysis with a BERT-based classifier, allowing researchers to focus on questions while ensuring computational rigor.
Pandore: automating text-processing workflows for humanities researchers
Pandore is a user-friendly toolkit for humanities and social sciences, enabling data collection, preparation, analysis, and visualization without advanced coding skills. Recent updates include bug fixes, interface enhancements, integration of modular Python scripts, a connection to Gallica, and deployment on a GPU-equipped server.
‘Flow Filter’: Introducing an upstream exploratory visualisation and filtering of large and detailed datasets.
Andrew Richardson1, Alex Butterworth2
1Northumbria University, United Kingdom; 2University of Sussex, United Kingdom
This paper is a presentation of Flow Filter - a generalisable exploratory visualisation tool and query builder designed to aid serendipitous discovery of large data sets and aid hypothesis formation. It will present the concept and rationale and illustrate its use and effectiveness via three case studies of historical datasets.
Open Science Literacy in the Context of the Digital Humanities
Elis Gabriela Copa dos Santos1, Maria Manuel Borges2, Viviane Santos de Oliveira Veiga3
1Divisão de Biblioteca, Arquivo e Cultura, Faculdade de Ciências e Tecnologia, Universidade Nova de Lisboa (NOVA FCT); 2Faculdade de Letras, Universidade de Coimbra (FLUC); 3Instituto de Comunicação e Informação Científica e Tecnológica, Fundação Oswaldo Cruz (FIOCRUZ)
Open Science requires the development of specific skills, that can be named as Open Science Literacy (OSL), already described in a previous research. This new study intends to identify a set of elements that could fit the presented OSL scheme and propose a Digital Humanities OSL chart of competencies.
Leveraging LLMs for NER Task on Historical Literary Data in Urdu as a Low-Resource Right-to-Left Language
Saniya Irfan, Arjun Ghosh, Sumeet Agarwal
Indian Institute of Technology Delhi, India
This study evaluates Large Language Models (LLMs) for Named Entity Recognition (NER) on a poetic form i.e., Marisya in the right to left Urdu script. The scarcity of annotated Urdu datasets by creating a human-annotated corpus is addressed and the performance of LLMs against the human-annotated corpus is evaluated.
