This event, funded by Deutsche Forschungsgemeinschaft (DFG) brings together scholars from diverse fields, including history, digital humanities, and computer science, to delve into the fascinating world of historical textual analysis enabled by "big data" approaches.

At the heart of this workshop lies our commitment to harnessing cutting-edge methodologies, such as natural language processing and network analysis, to unveil the narratives embedded within a vast repository of digitized documentary sources. The collaborative partnership between National Library of Brazil Projeto Resgate Barão do Rio Branco and Portuguese Overseas Archives in Lisbon serves as the foundation for our exploration.

Workshop Objectives:

This workshop seeks to:

· Leverage Digital Humanities: Discuss how digital humanities tools (ex. social network analysis, natural language processing, handwriting recognition, named entity recognition, or topic modeling) can be employed to extract valuable insights from vast historical corpora.

· Dive into a Wealth of Digitized Sources: Immerse in a wealth of digitized resources, unveiling priceless insights concealed within.

· Promote Interdisciplinary Dialogue: Foster a rich exchange of ideas and methodologies to enhance our understanding of subaltern agency within the colonial context.

· Forging Links between De/Colonial Studies, Subaltern Protagonism and Global Methods: Intertwine the realms of colonial studies and subaltern protagonism through interdisciplinary conversations. 

Key Themes:

· Digital Humanities in Action: Demonstrate how digital tools can transform unstructured historical records into meaningful insights about the past.

· Heritage and Memory: Explore innovative ways to promote the right to information and preserve the cultural heritage.

·  Historical Databases: Discuss different collections of historical data

· Harnessing Machine Learning for Data Extraction: In order to analyze the wealth of historical corpora, which are predominantly unstructured and semi-structured textual records, we aim to discuss new methodologies and adapt existing machine learning tools. This includes techniques such as handwriting recognition, named entity recognition (NER), and topic modeling.

· Subaltern Agency: Understand how subaltern groups attributed meaning to their actions and interactions within the complex colonial administration.

· Resisting Colonial Oppression: Explore various strategies of resistance, including political practices, identity re-articulations, and cultural movements.