摘要：Domestic dogs are trained using a range of different methods, broadly categorised as reward based (positive reinforcement/negative punishment) and aversive based (positive punishment/negative reinforcement). Previous research has suggested associations between use of positive punishment-based techniques and undesired behaviours, but there is little research investigating the relative welfare consequences of these different approaches. This study used a judgement bias task to compare the underlying mood state of dogs whose owners reported using two or more positive punishment/negative reinforcement based techniques, with those trained using only positive reinforcement/negative punishment in a matched pair study design. Dogs were trained to discriminate between rewarded and unrewarded locations equidistant from a start box, and mean latencies recorded. Their subsequent latency to intermediate ‘ambiguous’ locations was recorded as an indication of whether these were perceived as likely to contain food or not. Dogs trained using aversive methods were slower to all ambiguous locations. This difference was significant for latency to the middle (Wilcoxon Z = − 2.380, P = 0.017), and near positive (Wilcoxon Z = − 2.447, P = 0.014) locations, suggesting that dogs trained using coercive methods may have a more negative mood state, and hence that there are welfare implications of training dogs using such methods.
