Classifying suspicious content using frequency analysis

Obika Gellineau, George R. S. Weir

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

67 Downloads (Pure)

Abstract

This paper details an experiment to explore the use of chi by degrees of freedom (CBDF) and Log-Likelihood statistical similarity measures with single word and bigram frequencies as a means of discriminating subject content in order to classify samples of chat texts as dangerous, suspicious or innocent. The control for these comparisons was a set of manually ranked sample texts that were rated, in terms of eleven subject categories (five considered dangerous and six considered harmless). Results from this manual rating of chat text samples were then compared with the ranked lists generated using CBDF and Log-Likelihood measures, for both word and bigram frequency. This was achieved by combining currently available textual analysis tools with a newly implemented software application. Our results show that the CBDF method using word frequencies gave discrimination closest to the human rated samples.
Original languageEnglish
Title of host publicationCorpora and Language Technologies in Teaching, Learning and Research
EditorsGeorge Weir, S. Ishikawa, K. Poonpol
Number of pages8
Publication statusPublished - 2011

    Fingerprint

Keywords

  • CBDF
  • chi by degrees of freedom
  • log-likelihood measures

Cite this

Gellineau, O., & Weir, G. R. S. (2011). Classifying suspicious content using frequency analysis. In G. Weir, S. Ishikawa, & K. Poonpol (Eds.), Corpora and Language Technologies in Teaching, Learning and Research