Identifying users on social networking using pattern recognition in messages

Online social networks, such as Facebook and Twitter, have become a huge part of many people's lives, often as their main means of communication with other people. Because of frequency of use and the apparent security measures of these sites, users often falsely believe the proffered identity of the person they are talking to. This blind belief sometimes results in security threats due to the passing of private or confidential information to the wrong user. This may lead to malicious readers getting a user's private information and using it illegally. This work proposes a mathematical model for identifying security threats using pattern recognition with the aid of an extension of the Naive Bayes method called the Friendship Naive Bayes. Since specific patterns could be observed by examining the communication history between users, the proposed scheme uses these patterns to authenticate that the new message was written by the same person from the history. The scheme then calculates the probability of identifying the person as either the correct or incorrect user.

Grantor dc:publisher

University of Tennessee at Chattanooga

Author dc:creator

• Joshuva, Justin

Contributors dc:contributor

• Kandah, Farah
• Tanis, Craig; Gunesakara, Sumith
• College of Engineering and Computer Science

• Online social networks -- Security measures
• Computer networks -- Security measures

Licence

• https://rightsstatements.org/page/InC/1.0/?language=en

Language dc:language

English, eng

Repository record dc:identifier

https://scholar.utc.edu/theses/539

OAI identifier oai:identifier

oai:scholar.utc.edu:theses-1692