Mechanisms of attentional cueing during observational learning to facilitate motor skill acquisition

We examined the effectiveness of different cueing conditions during observational learning of a soccer accuracy pass. Sixty participants (30 males, 30 females) were randomly assigned and stratified by sex into one of six groups: discovery learning, verbal instruction, video model with visual cues, video model with verbal cues, video model with visual and verbal cues, and video model only. Each participant completed eight blocks of 10 trials each, with trial blocks 1 and 2 representing the practice phase (no manipulation), trial blocks 3, 4, 5 and 6 the acquisition phase (manipulation administered) and trial blocks 7 and 8 the retention phase (24 h after acquisition, with no manipulation). Absolute error, variable error and kicking form were recorded. The results indicated that those who used video modelling with visual and verbal cues collectively displayed less error and more appropriate form across acquisition and retention trial blocks compared with other groups. Our findings suggest that verbal information in addition to visual cues enhances perceptual representation and retention of modelled activities to improve task reproduction capabilities. Future research directions are proposed with implications for both direct and indirect perception accounts of skill acquisition through observed behaviours.     

Correlation analysis of performance measures for multi-label classification

In many important application domains, such as text categorization, scene classification, biomolecular analysis and medical diagnosis, examples are naturally associated with more than one class label, giving rise to multi-label classification problems. This fact has led, in recent years, to a substantial amount of research in multi-label classification. In order to evaluate and compare multi-label classifiers, researchers have adapted evaluation measures from the single-label paradigm, like Precision and Recall; and also have developed many different measures specifically for the multi-label paradigm, like Hamming Loss and Subset Accuracy. However, these evaluation measures have been used arbitrarily in multi-label classification experiments, without an objective analysis of correlation or bias. This can lead to misleading conclusions, as the experimental results may appear to favor a specific behavior depending on the subset of measures chosen. Also, as different papers in the area currently employ distinct subsets of measures, it is difficult to compare results across papers. In this work, we provide a thorough analysis of multi-label evaluation measures, and we give concrete suggestions for researchers to make an informed decision when choosing evaluation measures for multi-label classification.