Department of Cybernetics and Artificial Intelligence, Technical University in Košice, Letná 9, 040 01 Košice, Slovakia.
Department of Computer Science, Czech Technical University in Prague, 166 36 Prague, Czech Republic.
Sensors (Basel). 2019 Feb 26;19(5):989. doi: 10.3390/s19050989.
Analyses of user experience in the electronic entertainment industry currently rely on self-reporting methods, such as surveys, ratings, focus group interviews, etc. We argue that self-reporting alone carries inherent problems-mainly the misinterpretation and temporal delay during longer experiments-and therefore, should not be used as a sole metric. To tackle this problem, we propose the possibility of modeling consumer experience using psychophysiological measures and demonstrate how such models can be trained using machine learning methods. We use a machine learning approach to model user experience using real-time data produced by the autonomic nervous system and involuntary psychophysiological responses. Multiple psychophysiological measures, such as heart rate, electrodermal activity, and respiratory activity, have been used in combination with self-reporting to prepare training sets for machine learning algorithms. The training data was collected from 31 participants during hour-long experiment sessions, where they played multiple video-games. Afterwards, we trained and compared the results of four different machine learning models, out of which the best one produced ∼96% accuracy. The results suggest that psychophysiological measures can indeed be used to assess the enjoyment of digital entertainment consumers.
目前，电子娱乐行业的用户体验分析主要依赖于自我报告方法，如调查、评分、焦点小组访谈等。我们认为，仅依靠自我报告存在固有问题，主要是在较长实验期间的误解和时间延迟，因此不应该将其作为唯一的衡量标准。为了解决这个问题，我们提出了使用心理生理测量来模拟消费者体验的可能性，并展示了如何使用机器学习方法来训练这些模型。我们使用机器学习方法来模拟用户体验，使用自主神经系统和无意识心理生理反应产生的实时数据。已经结合自我报告使用了多种心理生理测量方法，例如心率、皮肤电活动和呼吸活动，以准备机器学习算法的训练集。训练数据是从 31 名参与者在长达一小时的实验会话中收集的，他们在其中玩了多个视频游戏。之后，我们对四个不同的机器学习模型的结果进行了训练和比较，其中最好的一个产生了约 96%的准确率。结果表明，心理生理测量确实可以用于评估数字娱乐消费者的享受程度。
