Recognition of Personality Traits using Meta Classifiers

摘要: In this paper, we have tried to understand human personality traits by using meta classifiers. We have used SMO (Sequential Minimal Optimization for Support Vector Machine), RF (Random Forest) and Adaboost as the three main algorithms to design our meta classifiers. As a method of evaluation, we have used weighted and un-weighted average evaluation measure according to the Interspeech 2012 speaker traits challenge guidelines. In the Interspeech 2012 speaker traits challenge, the organizer provided Speaker Personality Corpus (SPC), which we used to design our meta classifiers and measured the accuracy of the system.