Text Mining and Twitter Analysis
Title of Thesis
Personality detection using user-generated multilingual content in social networks
Description of Thesis
Social networks have become a storehouse of personal information. Personality prediction is one of the most difficult author profiling tasks in computational stylometry. This is the task of detecting personality traits of authors based on behavioral, temperamental, emotional and mental (footprint). Several personality typologies exist, the Myers-Briggs Type Indicator (MBTI) and BigFive Model are particularly popular in the non-scientific community, and many people use them to analyses their own personality and talk about the results online. The analysis of this data has been used for social computing applications as well as sociological research. One such application is the recommendation systems used in on-line shopping and travelling websites, targeted campaigns, etc.