A new (semantic) reflexive brain-computer interface: In search for a suitable classifier

► In the context of BCI communication we present healthy users with a new learning paradigm (reflexive semantic classical conditioning). ► Subjects are presented with true and false sentences. ► We use four classification algorithms to separate EEG activity that corresponds to 'yes' and 'no' responses. ► Classifiers perform at chance level when separating 'yes' from 'no' responses. ► Single conditioned responses can be classified with performance up to 68% accuracy.