Web Science and Digital Libraries Research Group

  Sometimes, all it takes is a trip to Norway to confirm that everything is connected. From June 2 to June 11, I traveled with my faculty advisors from Storymodelers to Kristiansand, Norway, to participate in a workshop on the use of modeling as a method for teaching and learning. This workshop was part of an ongoing project at the University of Agder  titled "Modeling for Histories", which is currently in the early stages of testing and has not yet been publicly disseminated. The project is led by Dr. Apostolos Spanos (University of Agder) in collaboration with Dr. Alexandra Lazareva (University of Agder), Dr. Jose J. Padilla ( Old Dominion University ) and Dr. Erika Frydenlund (Old Dominion University). The goal is to explore how model thinking can support history education by helping students move beyond traditional linear narratives and develop a deeper understanding of complex relationships, actors, and processes that shape historical events. This blog is a summary ...

Image Generated by DALL-E The utility of Large Language Models (LLMs) across diverse tasks raises important questions about the role of AI in web archive contexts, particularly in facilitating change analysis tasks. For instance, can LLMs effectively detect and analyze changes in webpages? How can this be achieved? What advantages and limitations do AI approaches have compared to traditional methods?.  In this blog post, I summarize our paper  “Exploring Large Language Models for Analyzing Changes in Web Archive Content: A Retrieval-Augmented Generation Approach”  ( Jhon G. Botello ,  Lesley Frew ,  Jose J. Padilla ,  Michele C. Weigle ) published at the  9th Computational Archival Science (CAS) Workshop 2024  (check Lesley Frew's trip report for more details about the workshop). The paper represents our first step in determining the ability of LLMs and the extent to which they can assist with change analysis tasks. Motivation As we interact...

Traditionally, historians have relied on conventional methods to uncover the details of our past. These methods include qualitative text analysis, translations, and transliterations, among other approaches. Such techniques have been essential for understanding historical events, cultures, and societies. However, the advent of digital tools and methodologies has significantly transformed the field, enabling more detailed analysis and visualization of historical data. New techniques, such as mapping and spatial analysis software, social network analysis tools, and digital databases, have not only facilitated the efficient storage and access to large volumes of information but also allowed historians to explore historical mobilities—meaning the movement of people and communities, as well as societal changes across different regions and time periods. The workshop “ Digital Methods for the Study of Mobilities ,” held  June 25-26, 2024, at the higher education and research institution IN...

Dr. Erika Frydenlund , Melissa Miller-Felton and I attended the Air Force Office of Scientific Research ( @AFOSR ) 2024 Trust and Influence Program Review on August 12-16, 2024 in Dayton, Ohio. We were invited because of our Minerva Research Initiative Grant, “ What's Missing? Innovating Interdisciplinary Methods for Hard-to-Reach Environments ” awarded by the U.S. Department of Defense in 2022 (described in a previous blog post by Dr. Erika Frydenlund when this grant was first awarded). Although the research conducted is public, this meeting was not recorded.   On the first day, the afternoon keynote was given by Dr. Samuel Segun , senior researcher at Global Center on AI Governance . He spoke on the topic “Building responsible & trustworthy AI: Operationalizing Responsible Artificial Intelligence (RAI) Practice,” where he underscored the critical need for trust in AI systems. Dr. Segun motivated the importance of trusting AI systems by asking, 'Who is responsible?...