stylometry   81

« earlier    

How the NSA identified Satoshi Nakamoto – Alexander Muse – Medium
The ‘creator’ of Bitcoin, Satoshi Nakamoto, is the world’s most elusive billionaire. Very few people outside of the Department of Homeland Security know Satoshi’s real name. In fact, DHS will not…
nsa  bitcoin  security  surveillance  privacy  stylometry  writing  text  style  identification  author 
august 2017 by gilberto5757
A force-directed graph that uncannily captures what it feels like to currently be an American
stylometry  from twitter_favs
june 2017 by esrodrigues
Danielle M. Farrar on Twitter: "Who doesn't like a good political metaphor? #stylometry #dhsistylo #DHSI2017"
Who doesn't like a good political metaphor? #stylometry #dhsistylo #DHSI2017

— Danielle M. Farrar (@PalaverousMonks) June 13, 2017

June 13, 2017 at 09:46PM
dh  stylometry  DHSI2017  dhsistylo 
june 2017 by aelang
Introducing the Bibliography on Stylometry – The Dragonfly's Gaze
This post is a brief presentation of the Stylometry Bibliography we recently published on Zotero. The understanding of the term stylometry underlying the conceptual scope of the bibliography is relatively wide and covers any type of quantitative analysis of literary style. via Pocket
bibliography  resources  stylometry 
april 2017 by kintopp
Detecting Hoaxes, Frauds, and Deception in Writing Style Online
stylometry  hoaxes  writing  tools 
september 2015 by lizhenry
stylo R package - computational stylistics
The suite of stylometric tools, so far in the form of separate scripts, has been recently ported to a regular R package. Once installed, it provides a number of functions that can be invoked from inside the R console. 3.4. via Pocket
analysis  statistics  stylometry  tools  texts 
september 2015 by kintopp
Try these exercises and see what they reveal about you.

Perceptual style: You are what you see
Look at an everyday object and write about it for only 5 minutes. See what it reveals about yourself.

A projective test: The TAT
This is a classic test where you will first see a picture or drawing. You will then have 10 minutes to write a story that describes what is happening to the people in the picture. After writing, you will get feedback about your personality.

Time for your I-test
Have you checked your I′s lately? This 2-minute test will reveal how well you understand how I-words are used in everyday language.

The LIFE Survey
What do your daily behaviors reveal about your personality? Check out this questionnaire to find out. The entire questionnaire takes about 8 minutes and provides feedback about your behavioral type.

Language style matching: How in synch are you?
Compare emails, poems, or writing samples that you and someone else have written. Your feedback will tell you how much the two of you match in your language usage.

stylometry  language  style  expression  english 
june 2015 by ivar
On the Feasibility of Internet-Scale Author Identification
Abstract—We study techniques for identifying an anonymous author via linguistic stylometry, i.e., comparing the writing style against a corpus of texts of known authorship. We experimentally demonstrate the effectiveness of our techniques with as many as 100,000 candidate authors. Given the increasing availability of writing samples online, our result has serious implications for anonymity and free speech — an anonymous blogger or whistleblower may be unmasked unless they take steps to obfuscate their writing style.

While there is a huge body of literature on authorship recognition based on writing style, almost none of it has studied corpora of more than a few hundred authors. The problem becomes qualitatively different at a large scale, as we show, and techniques from prior work fail to scale, both in terms of accuracy and performance. We study a variety of classifiers, both “lazy” and “eager,” and show how to handle the huge number of classes. We also develop novel techniques for confi- dence estimation of classifier outputs. Finally, we demonstrate stylometric authorship recognition on texts written in different contexts.

In over 20% of cases, our classifiers can correctly identify an anonymous author given a corpus of texts from 100,000 authors; in about 35% of cases the correct author is one of the top 20 guesses. If we allow the classifier the option of not making a guess, via confidence estimation we are able to increase the precision of the top guess from 20% to over 80% with only a halving of recall.
machinelearning  stylometry  paper  pdf 
june 2015 by jonschoning

« earlier    

related tags

26c3  academic  adversarial_stylometry  against  ai  algorithm  american-literature  analysis  analytics  anonymity  applications  article  author  authors  authorship  bayes  bibliography  billayers  bitcoin  blogging  blogs  book  canada  ccc  classification  code  computational-linguistics  computational-stylistics  corpora  cryptography  datamining  deanonymisation  deanonymization  detection  devere  dh  dhsi2017  dhsistylo  digital-humanities  digitalhumanities  discussion  diss  document  drexel  english  etnul  expression  facialrecognition  filetype:pdf  freeware  getting-lost  gothic  graph  hackernews  hoaxes  howto  identification  information  internet  java  jgaap  jk-rowling  jk_rowling  language  learning  linguistics  literature  machine  machinelearning  mathematics  media:document  mediax  metal  methods  movie  music  natural-language-processing  network  news  nlp  nsa  nytimes  obama  oxford  paper  papers  pdf  penmanship  people  personality-recognition  peter_farey  plagiarism  post  postprivacy  principal_component_analysis  principal_components_analysis  privacy  programming  project  psycholinguistics  python  r  research  researchers  resources  retrieval  review  robert_valenza  satoshi  science  script  security  shakespeare  software  sonnets  sources  speech  statistics  style  surveillance  system  text-analysis  text-analytics  text-proc  text  textmining  texts  tool  tools  trends  uni  university  video  visualisation  w:3  ward_elliott  weimar  wikipedia  windows  writing 

Copy this bookmark: