You can build a content set of up to 10,000 documents from any of the Gale primary text collections -- which range from newspaper archives including those of The Economist, The Independent, and The Mirror, through to manuscript collections including US Declassified Documents, Decolonisation: Politics and Independence in Former Colonial and Commonwealth Territories, and the Archives of Sexuality and Gender -- and upload manuscripts and files you have found elsewhere. You can then set options for cleaning up your dataset, and then run your data through one or more content analysis tools. These include both quantitative and qualitative approaches, including Ngrams, Named Entity Recognition, Sentiment Analysis (both in a given example and over time), Topic Modelling, and Document Clustering.

These tools can allow you to quickly produce and iterate data from a large array of primary resources without needing to manually transcribe large collections of individual primary resources. This is a fantastic opportunity to take your research to the next level, so join us for this masterclass with an expert from Gale. This should be of particular interest to postgraduates and researchers in the Faculty of Arts, Social Scientists, and those with an interest in the Digital Humanities and interdisciplinary methodologies.