The traditional methods of profiling

1

• Introduction
• The traditional methods of profiling
• Web 2.0 Self profiling
• Classifying social networking profiles
• Conclusions
• References

2
Demo-graphic data

• Marketing campaigns
• Direct mail
• Telesales scripts
• Email newsletters
• Website banner ads

• Website personalisation (recent)
• Recommendations films, books, music, games
  etc
• Web content news stories, blog posts,
  forums
• Search results

3
(No Transcript)
4
Web 2.0 Unique Profiles
Standardised Profiles
Machine learning
Features
P1, P2, ..., Pn
5

• Not a completely new idea
• consider similar work already done by Google,
  LastFM, Pandora, Digg and others?
• Future trends
• more people using social networking tools,
  accessing information online and shopping online
• people beginning to expect personalisation
• Integration with location based content
• Challenges
• Addressing concerns over privacy
• Choosing suitable profiles
• Applying machine learning techniques
• Applying natural language processing techniques

6

• Raghu, TS, Kannan, PK, Rao, HR Whinston, AB
  2001, Dynamic profiling of consumers for
  customized offerings over the Internet a model
  and analysis. Decision Support Systems, vol. 32,
  no. 2, pp. 117-134.
• Chellappa, RK Sin, RG 2005, Personalization
  versus Privacy An Empirical Examination of the
  Online Consumer's Dilemma. Inf. Technol. and
  Management, vol. 6, no. 2-3, pp. 181-202.
• Tan, P, Steinbach, M, Kumar, V 2006 Introduction
  to Data Mining, Pearson Education. ISBN-13
  978-0321420527
• Jurafsky, D. Martin, J.H. 2009 Speech and
  Language Processing (2nd edition), Pearson
  International Edition.
• For further information please contact
• Jake Daniel Collins
• jc317_at_sussex.ac.uk
• http//techabstractions.wordpress.com