https://github.com/ashenoy95/writeprints-static

Writeprints-Static Feature Set exctraction for Adversarial Stylometry
https://github.com/ashenoy95/writeprints-static

feature-extraction nlp python python-3 python3 stylometry

Last synced: about 2 months ago
JSON representation

Writeprints-Static Feature Set exctraction for Adversarial Stylometry

• Host: GitHub
• URL: https://github.com/ashenoy95/writeprints-static
• Owner: ashenoy95
• Created: 2017-05-13T19:28:04.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2018-03-12T21:55:22.000Z (almost 7 years ago)
• Last Synced: 2023-07-26T08:48:27.759Z (over 1 year ago)
• Topics: feature-extraction, nlp, python, python-3, python3, stylometry
• Language: Python
• Homepage:
• Size: 8.79 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Writeprints-Static Feature Set

Code to extract important features from the Writeprint-Static Feature Set for (Adverserial) __Stylometry__

[[Brennan, Afroz, and Greenstadt (2012)]](https://www.cs.drexel.edu/~sa499/papers/adversarial_stylometry.pdf).

(Adapted from the Whiteprints approach [[Abbasi and Chen, 2008]](https://www.scss.tcd.ie/Khurshid.Ahmad/Research/Sentiments/K_Teams_Buchraest/a7-abbasi.pdf))

| Group     | Category            | No. of Features | Description                                                       |

| :-------: |:-------------------:| :--------------:| :---------------------------------------------------------------- |

| Lexical   | Word level          | 3               | Total words, average word length, number of short words           |

|           | Character level     | 3               | Total char, percentage of digits, percentage of uppercase letters |

|           | Special characters  | 22              | Frequency of each of 22 special characters                        |                      

|           | Letters             | 26              | Letter frequency                                                  |

|           | Digits              | 10              | Digit frequency                                                   |

|           | Vocabulary richness | 1               | Ratio of hapax and dis legomena                                   |

| Syntactic | Function Words      | 153             | Frequency of function words                                       |

|           | POS tags            | 12              | Frequency of parts of speech tags (universal)                     |

|           | Punctuation         | 9               | Frequency and percentage of colon, semicolon, qmark, period, exclamation, comma, single inverted comma, double inverted comma |