Nineteen subjects high in social anxiety and 20 subjects low in social anxiety were asked to give a 5-min speech in front of three audience members. Audience members were trained to provide indictators of positive evaluation (e.g. smiles) and negative evaluation (e.g. frowns) at irregular intervals during the speech. Subjects were instructed to indicate, by depressing one of two buttons, when they detected either positive or negative behaviours. Results indicated that subjects high in social anxiety were both more accurate at, and had a more liberal criterion for, detecting negative audience behaviours while subjects low in social anxiety were more accurate at detecting positive audience behaviours.