Imperial Commoners in Brazil and West Africa (1640–1822): A Global History from a Correspondence Network Perspective

By Agata Bloch and Demival Vasques Filho

After a couple of attempts, we have finally received the exciting news that our project has been recommended for funding by the Polish National Science Center! Over the next four years, we will study the communication patterns of imperial commoners (non-elite actors) who developed similar characteristics, narratives, and thought strategies in different areas of the vast Atlantic Portuguese Empire. We are interested not only in how these commoners generally behaved and displayed attitudes that transcended class and gender, but also in how imperial authorities responded to them.

The project draws on a unique dataset that we created based on the catalogs of the Portuguese Overseas Archives (AHU) in Lisbon, especially the Projeto Barão do Rio Branco and Atlantic catalogs. The dataset includes administrative correspondence-nearly 170,000 records-between the metropolis of Lisbon and its Atlantic overseas colonies. We used natural language processing (NLP) techniques to identify and extract structured data from otherwise unstructured free-text data. We extracted information such as the sender and recipient of these documents, the occupation of the actors in the administration (e.g., king, governor, secretary, etc.) and in society at large, their gender, institutional affiliation, and geographic location. We have described this process – the transformation of archival data into network data (Fig. 1) – in our article published in the journal Social Networks (Bloch, Vasques Filho, and Bojanowski, 2022).

Fig. 1. Process of converting unstructured archive data into network data. Figures extracted from Bloch, Vasques Filho & Bojanowski, 2022.

These documents, now in a structured format, allow us to trace, for example, the histories and practices of Indigenous and Black peoples as actors who have used their negotiation skills (Mattoso, 1990), their dialog with authorities (Russell-Wood, 1995), their participation in critical historical moments (Barr, 2017; Calloway, 2018), struggle for rights (Fought, 2017), and integration politics (Domingues, 2000). That is, the dataset allows us to explore empire as a dynamic space based on networks that also emerge through bottom-up communication. It opens new perspectives on the dynamics of the colonial social fabric based on how marginalized people struggled for their individual and collective survival and how they were sociable despite all the administrative and legal apparatuses that sought to objectify and subordinate them.

To do this, however, more work needs to be done with the data set. In this context, we will develop a dictionary of entities (people, organizations, places) and apply topic models to extract semantic information from the correspondence. The idea is to find out what topic – political, administrative, economic, religious, or otherwise – the senders and recipients of these administrative letters are concerned about. That is, this large dataset of official correspondence provides a unique opportunity to examine how global events reverberated and how local individuals gained attention through the communication channels of the empire.

Fig. 2. Example of a petition from enslaved woman Joana Correia requesting, directly to the king, her rights to buy her freedom.

We, therefore, assume that global events influenced the communication patterns of imperial commoners. These, in turn, led to similar characteristics, shared ideas, narratives, and thought strategies on both sides of the Atlantic coast. In this sense, Commoners did not operate as a particular social group (Indigenous, black, women) but exhibited attitudes that transcended class and gender. However, the Empire may have responded differently depending on its relationships with each area of the colonies. Therefore, analysis of this unprecedented historical dataset using natural language processing and network science will examine communication patterns between these people and government officials in both the colonies and the metropolis. We will use the relational data to reconstruct prosopographic networks and examine the relationships between imperial citizens and government officials by topic, time, and space.

Some initial questions we will seek to answer: what events and themes were expressed in the correspondence documents and how variable they were in space and time? How large is the volume of correspondence that can be attributed to the various topics of the documents identified with topic models? How does this volume vary by place and time? What were the interests and experiences of the imperial citizens of the Portuguese Empire, and how did they change?

Following the ideas of Francois et al. (2016), we aim to create a “macroscope” of the societies of the Atlantic colonies based on the information available in the correspondence. This will allow us to understand better commoners’ characteristics, interactions, shared experiences, narratives, dreams, aspirations, and specific patterns or dynamics. Using prosopographic networks, we will conduct a collective study of the social characteristics of imperial commoners, known as “group biography” (Abbott 2009), which goes beyond individual biographies.

We are also interested in a top-down perspective on the roles and functions of the officials of the Portuguese Empire. We will examine their involvement and responsibilities in various issues mentioned in the documents, as well as their network positions in the network of correspondence and how their participation and resulting network roles changed over time.

Studying local and global events through the analysis of correspondence, reports, or information has gained attention in recent decades. Contemporary political scientists are seeking data and methods to learn about ongoing political events based on processing large volumes of local reports and local media. Examples include the GDELT Project and the ICEWS system (O’Brien 2010; 2013). The U.S. government created the latter as a kind of “early warning system” for major events in specific regions (e.g., the Middle East) to identify key actors (individuals and organizations), relationships among them (e.g., collusion or hostility), and events that could reach a global dimension. Other research-oriented projects of a similar nature include CAMEO (Gerner, Schrodt, Yilmaz, Abu-Jabr 2002) and SCAD (Salehyan et al. 2012). Our dataset has similar characteristics. Correspondence from different corners of the Portuguese Empire to Lisbon contains information about various local events and issues of varying importance. These local events manifested in the correspondence should be matched and compared with a calendar of known global events.

According to the ideas above, we look forward to providing valuable insights into the social history of the Portuguese Empire on a local and global scale!

Finally, we would like to take this opportunity to advertise the postdoctoral position we have to work on this project. We are looking for someone with a machine learning background to join our team. More information can be found here. Please spread the word!

Cite this article as: Agata Bloch and Demival Vasques Filho, "Imperial Commoners in Brazil and West Africa (1640–1822): A Global History from a Correspondence Network Perspective," in Digital Humanities Lab, 02/02/2023,

Featured image: “Imperial Commoners in Brazil and West Africa (1640–1822): A Global History from a Correspondence Network Perspective”, copyright by Agata Bloch.


  • Abbott, J. M. (2009). The Angel in the Office. British Sociological Association.
  • Barr, B. (2017). Peace comes in the form of a woman. Indians and Spaniards in the Texas Borderlands. The University of North Carolina Press.
  • Bloch, A., Vasques Filho, D., & Bojanowski, M. (2022). Networks from archives: Reconstructing networks of official correspondence in the early modern Portuguese empire. Social Networks, 69, p. 123-135.
  • Calloway, C. G. (2018). The Indian world of George Washington. The first president, first Americans, and the birth of the nation. New York: Oxford University Press.
  • Domingues, A. (2000). Quando os índios eram vassalos: colonização e relações de poder no Norte do Brasil na segunda metade do século XVIII. Comissão Nacional Comemorações dos Descobrimentos Portugueses.
  • Fought, L. (2017). Women in the world of Frederick Douglass. Oxford University Press.
  • Francois, P., Manning, J., Whitehouse, H., Brennan, R., Currie, T., Feeney, K., & Turchin, P. (2016). A macroscope for global history-Seshat global history databank: a methodological overview. Digital Humanities Quarterly.
  • Gerner, D. J., Schrodt, P. A., Yilmaz, O., & Abu-Jabr, R. (2002). The creation of CAMEO (Conflict and Mediation Event Observations): An event data framework for a post cold war world. In annual meeting of the American Political Science Association (Vol. 29).
  • Mattoso, K. (1990) Ser escravo no Brasil. Brasiliense.
  • O’Brien, S. P. (2010). Crisis early warning and decision support: Contemporary approaches and thoughts on future research. International Studies Review, 12(1), 87-104.
  • O’Brien, S. P. (2013). A multi-method approach for near real time conflict and crisis early warning. Handbook of Computational Approaches to Counterterrorism, 401-418.
  • Russell-Wood, A.J.R. (1995). Vassalo e soberano. Apelos extrajudiciais de Africanos e de indivíduos de origem africana na América Portuguesa. Cultura portuguesa na Terra de Santa Cruz edited by da Silva, M. B. N. Editorial Estampa.
  • Salehyan, I., Hendrix, C. S., Hamner, J., Case, C., Linebarger, C., Stull, E., & Williams, J. (2012). Social conflict in Africa: A new database. International Interactions, 38(4), 503-511.

Schreibe einen Kommentar

Deine E-Mail-Adresse wird nicht veröffentlicht.

Diese Website verwendet Akismet, um Spam zu reduzieren. Erfahre mehr darüber, wie deine Kommentardaten verarbeitet werden.

Suche in OpenEdition Search

Sie werden weitergeleitet zur OpenEdition Search