Semantic pathways: a novel visualisation of varieties of English

Semantic Pathways is a corpus exploration tool with a unique visual interface in which keyword extraction and keyword-based document clustering have been implemented in order to facilitate insight forming. Semantic Pathways combines corpus comparison techniques from Corpus Linguistics with aestheticallydriven design and interaction, to produce fluidly interactive information exploration. In addition, users can access Semantic Pathways via a command-line interface, where integration with Python and NLTK offers additional benefits. We describe system operation from the user’s perspective, and then use the tool for corpus comparison of different varieties of English with the LOB and Brown corpora as test and reference sets, demonstrating its novelty in gisting an entire document collection and speedy and intuitive exploration of lexical usage across the document set.