Fifty years of European history through the Lens of Computational Linguistics: the De Gasperi Project
Italian Journal of Computational Linguistics
In 2013 a collaboration was started between the Digital Humanities research unit and the Italian-German Historical institute at Fondazione Bruno Kessler, whose goal was to develop tools and strategies to give new insight into the public documents written by Alcide De Gasperi. Through the analysis of textual occurrences, semantic structures, and temporal patterns, the project, ending in 2017, has investigated the formation and evolution of De Gasperi's political action and the rhetorical
... e that accompanied its developments. Research of this kind has contributed to better understanding De Gasperi's thoughts, the links between his language and his political views and culture, and the instruments of his communication. On the other hand, it allows the design and development of automated research tools for the political domain. This is a distinctly interdisciplinary research project, in which historical inquiry interacts with methods of linguistic analysis and with information and communication technologies. Volume 2, Number 2 what are the rules of political language? How does communication between politicians and society work? To what extent are politicians' words influenced by citizens? And more generally, what are the strategies by which we build consensus? In recent years, studies in this area have benefited from new methods and techniques offered by Digital Humanities research. This includes, for example, the possibility to process large amounts of data, analyse them from different perspectives and display such analyses following data visualisation principles. The inter-disciplinary project on De Gasperi's public documents, which is currently ongoing at Fondazione Bruno Kessler (FBK) in Trento, is part of this trend. The project is in fact a collaboration between the Italian-German Historical Institute and the Digital Humanities research unit at FBK. Its goal is to give new insight into De Gasperi's communication strategy with the help of innovative tools for text analysis. This project represents one of the few attempts to overcome the gap between lexical and rhetorical studies in the political domain, and to our knowledge is the first one that covers the whole public life of an Italian politician, also thanks to the availability of the complete collection of De Gasperi's public documents. Furthermore, most works on Italian political discourse have focused on politicians from the Second Republic (i.e. after 1994), and the few studies related to De Gasperi (Desideri 1984; Vinciguerra 2016) have approached his discourse with traditional methods, without the help of computational tools, considering only documents from a specific time period. In this project, we apply for the first time close and distant reading (Moretti 2013) to the study of Italian political communication. We believe that this multi-faceted analysis of De Gasperi's public documents will give new insight into the main phases of Italian recent history. The paper is structured as follows: in Section 2 we provide an overview of projects dealing with political communication in the Digital Humanities area. In Section 3 the De Gasperi project and the creation of the corpus are briefly presented. In Section 4 the first project phase is detailed, with a discussion about the performance of NLP modules and a preliminary set of corpus-based findings. Then, we describe in Section 5 the ongoing work and the plans for future research inside the project. Finally, we draw some conclusions and comment the project findings in Section 6.