frequency analysis

By sondre rong davik, 29 August, 2018

How Computers Read Computer Generated Novels

Author
Zach Whalen
Publication Type
Conference paper or presentation
Language
English
Year
Presented at Event
Electronic Literature Organization 2018: Mind the Gap!
URL
How Computers Read Computer Generated Novels
License
CC Attribution
Record Status
Not yet reviewed
Tags
Study of textuality
computer generated text
NaNoGenMo
frequency analysis
Abstract (in English)

In this paper, Whalen proposes a course of study into the textuality of computer-generated novels, specifically the corpus of work generated for NaNoGenMo. Given the scope of this corpus, Whalens' intention is to use text analysis techniques such as topic modeling, frequency analysis, stylometrics, and other varieties of machine reading to explore these questions about the textual characteristics of computer-generated fiction. 

Platform referenced
Twitter

Predictor

Content type
Creative Work
Author
Simon Biggs
Year
URL
Predictor
Language
English
Publication Type
Published on the Web (individual site)
Platform/Software
Shockwave
Record Status
Revisions required
Tags
interpretative text generator
predictive text
frequency analysis
web art
netart
Description (in English)

Predictor is a web browser based online predictive text artwork. The user or inter-actor is able to enter, via the keyboard, text into a browser window. A statistical algorithm then analyses the probability of all the words that might follow the word just typed, based on the frequency of terms in a reference corpus text. This reference text can be arbitrary. In the case of this instance of the work the corpus is Kafka's Great Wall of China.

Technical notes

Requires computer running web browser with Shockwave plugin.

frequency analysis