Table 5 Comparison with state-of-the-art
From: Predicting the Big Five personality traits from handwriting
Work/Year | Method | Prediction accuracy |
|---|---|---|
Champa and AnandaKumar [2010] [4] | Set of rule-based classifiers | 68% |
Chen and Lin [2017] [6] | Support Vector Machines, k-nearest neighbors, and AdaBoost classifiers | 72.8% |
Fallah and Khotanlou [2016] [5] | Hidden Markov Models and neural networks | 78.9% |
Current work [2017] | Feed-forward neural networks | 84.4% (intra-subject)/80.5% (inter-subject) |