Mark LeBlanc and Kate Boylan, "Lexos: an introductory tool for a new "close reading" As the Digital Humanities gains access to a wide array of digitized corpora and matures to a discipline that creatively defines new methods for computationally close and distant readings, a growing gap has emerged between those who apply sophisticated programming and those who are new to the game and need an introduction to the field. Our open-source Lexos tools (lexos.wheatoncollege.edu) narrow the gap by providing an easy to use web-based interface that introduces scholars to a computational lens for close reading digitized texts in any language. Based on NEH-funded work over the last decade, a team of undergraduate programmers and humanities students and scholars have designed an interface that guides users through a workflow that highlights effective practices when conducting computational probes of digitized texts, including the steps of scrubbing (e.g., deciding how to deal with punctuation, special characters, <tags>, lemmatization, and stop words), cutting texts into segments, tokenization (counting word and character n-grams), introductory statistical analyses (e.g., clustering), and visualizations of results (e.g., plotting words or phrases of interest across an entire novel). At CTDH '20 we propose to engage audience members with a set of examples that instill confidence with using the tool as well as generate ideas for a wide variety of potential uses in languages from Old English to Mandarin in order to empower humanities scholars to ask new sets of questions of their digitized texts.
