Stefano Menini will participate to the CLARIN-PLUS Workshop “Working with Parliamentary Records“. The workshop aims to discover the ways in which NLP technology would help for curating parliament records and for answering research questions in the field of Digital Humanities. Various perspectives will be taken into account: in particular, perspective of curators, researchers and developers.
Title: Ireland in the eyes of the UK Parliamentary
Abstract: We present our approach to the automated analysis of large collections of parliamentary debates, focusing as case study on how Ireland was represented in UK parliamentary discourses over the last two centuries. For the analysis we rely on the data form the Hansard Corpus, a collection of 7.6 million speeches uttered by the British Parliament form 1803 to 2005. We extracted a subcorpus of 52.000 documents, whose topic is related to Ireland, and we processed it with our pipeline called ALCIDE (Analysis of Language and Content In a Digital Environment). ALCIDE is a web platform implementing a completely automatic text processing pipeline. It allows the user to extract from text different typologies of information that are then presented through graphic representations in a web interface. All visualisations are interactive and allow users to shift smoothly from distant to close reading . We used the functionalities of ALCIDE to explore the Ireland-related content of the parliamentary debates focusing on both synchronic and diachronic aspects such as: the key-concepts more frequently related to Ireland and the broad topics emerging over time in connection with relevant events, the most frequently mentioned persons and the lexical expressions associated to specific topics.