Diachronic and diatopic word embeddings from newspapers digitised by the British Library (1830-1889): North and South England

<p>Diachronic&nbsp;word embeddings (decade-level) trained with Word2Vec (via Gensim) on different geographic subcorpora of the Heritage Made Digital British and the Living with Machines&nbsp;historical newspaper collections:</p> <p>- North England (north.zip)</p> <p>- South England (south.zip)</p> <p>At the moment, for each subcorpus, Word2Vec models are available for each decade in the period 1830-1889. More models are on the way for the following:</p> <p>- each decade in the periods 1780-1829 and 1890-1920 for both North and South England.</p> <p>- diachronic models for the following regions: Scotland, Wales, and Midlands.</p> <p>The models were trained using the following parameters:</p> <pre><code>sg = True min_count = 1 window = 5 vector_size = 200 epochs = 5</code></pre> <p>Like the embeddings in&nbsp;<a href="https://doi.org/10.5281/zenodo.7181682">this repository</a>, the model for each decade was aligned to the most recent one with Orthogonal Procrustes.</p> <p>See related GitHub repository for the full documentation:&nbsp;<a href="https://github.com/Living-with-machines/DiachronicEmb-BigHistData">https://github.com/Living-with-machines/DiachronicEmb-BigHistData</a>.</p> <p>Project website (Living with Machines):&nbsp;<a href="https://livingwithmachines.ac.uk/">https://livingwithmachines.ac.uk/</a></p> <p>Data related to:&nbsp;Nilo Pedrazzini &amp; Barbara McGillivray,&nbsp;<em>Diachronic and diatopic word embeddings from British historical newspapers</em>, presented at&nbsp;AIUCD (Convegno dell&rsquo;Associazione per l&rsquo;Informatica Umanistica e la Cultura Digitale) in Siena (Italy), June 2023.</p>