@autoblake is a critical remix of David Erdman’s The Complete Poetry and Prose of William Blake using a Markov-chain algorithm that displays novel lines of Blakean poetry every three hours. The algorithms implemented in Markov-chains use the statistical probability of characters to construct strings of text that are ultimately gibberish, but create potentially meaningful phrases. Zach Whalen explains that these characters “might form a database which could answer a question like, ‘Given an occurrence of Word A, what is the statistical likelihood that it is followed by Word B?”. By searching for characters based upon their statistical likelihood, the algorithm is able to construct a string of text. These strings constructed by the Markov-chain are pseudo-random, rather than truly random, since the algorithm is influenced by specific variables (Markov-order being one, source text being another) that are put to work through the manipulation of numbers. The code was written in Python, a relatively simple scripting language. You can find my code on my Github site (https://github.com/rogerwhitson/Markov-Tweet), where I have included instructions for people to create their own Markov Twitterbot.
“To use a markov chain generator to cut across his life’s oeuvre reveals patterns of style that Blake was probably unaware of. Beyond its utility as form of distant reading, its poetic output is worth reading closely to analyze the textures of Blake’s language beyond semantics. @autoblake gives us access to a surreal Blake, of interest to scholars and enthusiasts alike.” - Leonardo Flores, “I <3 E-Poetry”