What Really Matters? A Study into People's Instinctive Evaluation Metrics for Continuous Emotion Prediction in Music
2013 Humaine Association Conference on Affective Computing and Intelligent Interaction (2013)
Sept. 2, 2013 to Sept. 5, 2013
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ACII.2013.106
Continuous emotion prediction in the arousal-valence space is now being used in various modalities: music, facial expressions, gestures, text, etc. In order to be able to compare the work of different research groups effectively, we believe it is necessary to set certain guidelines for how to conduct research-the choice of evaluation metrics of emotion recognition algorithms in particular. In this paper we focus on the field of musical emotion recognition and describe a study designed to discover people's instinctive preference among the most commonly used evaluation techniques. We gather strong evidence that root mean squared error or Kullback-Leibler divergence should be used for regression based approaches. The raw study data we collected is made publicly available.
Correlation, Emotion recognition, Gaussian distribution, Noise measurement, Visualization, Euclidean distance
V. Imbrasaite, T. Baltruaitis and P. Robinson, "What Really Matters? A Study into People's Instinctive Evaluation Metrics for Continuous Emotion Prediction in Music," 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction(ACII), Geneva Switzerland, 2014, pp. 606-611.