1 / 11

Understanding Facebook Account Usage: Identifying True Owners and Privacy Concerns

This research explores user behavior on Facebook, focusing on how to identify the true owner of an account. By analyzing account access patterns and demographics, it highlights privacy issues and account misuse. Utilizing statistical methods and data from Academia Sinica, the study emphasizes the importance of understanding who is using social media accounts. With accuracy rates around 80%, the results show significant insights into online identity and the potential risks of revealing personal information. Awareness and responsible usage are urged for online safety.

cwen
Télécharger la présentation

Understanding Facebook Account Usage: Identifying True Owners and Privacy Concerns

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Research on Facebook [1] Christine Chai, A21

  2. Who is Using YOUR FB Account? • Account name and password match… • True owner? Acquaintance? Stranger? • Facebook server decided to… • Record IP, Operation Systems, web browser • Suspect account misuse identify pictures • Research in Academia Sinica • Statistical method for browsing activities

  3. Statistical Behavior • People generally do… • Account user = self • Click on “like” • Comment on a status • Account user = other • View personal messages • View private clubs

  4. Experiment Design A B C D

  5. Data Analysis • Data clean-up • Feature examples • Act: like, add_comment, follow_link • Expand: page, comments • View: photo, likes, message • Classification Other Self

  6. Experimental Results • Accuracy: around 80% • Error: False positives and false negatives

  7. Difficult Times [2,3]

  8. Current Work [2,4] VPNconnect Download data Add/delete Features

  9. Facebook: What’s in a Name? • Name Gender with > 90% accuracy • Popular name list (Lily Female; John Male) • Facebook profiles with gender specified • Local information: in a relationship / married • Data: Everything can be publicly accessed!

  10. Conclusion • Be aware of what we do online. • Be responsible for what info we reveal.

  11. References • Academia Sinicahttp://blog.libertytimes.com.tw/spieler/2008/07/04/16118 • Academia Sinicahttp://zh.wikipedia.org/wiki/%E4%B8%AD%E5%A4%AE%E7%A0%94%E7%A9%B6%E9%99%A2 • Introduction to Machine Learninghttp://www.cmpe.boun.edu.tr/~ethem/i2ml/ • National Taiwan Universityhttp://blog.chinatimes.com/may.lin/archive/2007/06/19/174928.html

More Related