Techniques for analysis of web data


  • Ulrik Franke
  • Fredrik Johansson
  • Magnus Jändel
  • Lisa Kaati
  • Marianela Garcia Lozano

Publish date: 2012-12-10

Report number: FOI-R--3532--SE

Pages: 57

Written in: Swedish


  • web mining
  • web data
  • text analysis
  • social networks
  • integrity
  • preserving analysis
  • alias matching
  • information fusion


This report describes some of the techniques that can be used for analyzing data from the Internet. The report is not an exhaustive description of the subject; it just points to some of the techniques that are available and useful when analyzing data derived from the web. The techniques that are described are different forms of computerized text analysis, social network analysis, techniques for detecting if a user has multiple aliases, how digital traces can be used in the hunt for lone wolf terrorists, integrity preserving data mining and finally how information credibility can be judged.