%0 Generic %1 washington2020training %A Washington, Peter %A Kalantarian, Haik %A Kent, Jack %A Husic, Arman %A Kline, Aaron %A Leblanc, Emilie %A Hou, Cathy %A Mutlu, Cezmi %A Dunlap, Kaitlyn %A Penev, Yordan %A Varma, Maya %A Stockham, Nate %A Chrisman, Brianna %A Paskov, Kelley %A Sun, Min Woo %A Jung, Jae-Yoon %A Voss, Catalin %A Haber, Nick %A Wall, Dennis P. %D 2020 %K %T Training an Emotion Detection Classifier using Frames from a Mobile Therapeutic Game for Children with Developmental Disorders %U http://arxiv.org/abs/2012.08678 %X Automated emotion classification could aid those who struggle to recognize emotion, including children with developmental behavioral conditions such as autism. However, most computer vision emotion models are trained on adult affect and therefore underperform on child faces. In this study, we designed a strategy to gamify the collection and the labeling of child affect data in an effort to boost the performance of automatic child emotion detection to a level closer to what will be needed for translational digital healthcare. We leveraged our therapeutic smartphone game, GuessWhat, which was designed in large part for children with developmental and behavioral conditions, to gamify the secure collection of video data of children expressing a variety of emotions prompted by the game. Through a secure web interface gamifying the human labeling effort, we gathered and labeled 2,155 videos, 39,968 emotion frames, and 106,001 labels on all images. With this drastically expanded pediatric emotion centric database (>30x larger than existing public pediatric affect datasets), we trained a pediatric emotion classification convolutional neural network (CNN) classifier of happy, sad, surprised, fearful, angry, disgust, and neutral expressions in children. The classifier achieved 66.9% balanced accuracy and 67.4% F1-score on the entirety of CAFE as well as 79.1% balanced accuracy and 78.0% F1-score on CAFE Subset A, a subset containing at least 60% human agreement on emotions labels. This performance is at least 10% higher than all previously published classifiers, the best of which reached 56.% balanced accuracy even when combining änger" and "disgust" into a single class. This work validates that mobile games designed for pediatric therapies can generate high volumes of domain-relevant datasets to train state of the art classifiers to perform tasks highly relevant to precision health efforts.

@misc{washington2020training, abstract = {Automated emotion classification could aid those who struggle to recognize emotion, including children with developmental behavioral conditions such as autism. However, most computer vision emotion models are trained on adult affect and therefore underperform on child faces. In this study, we designed a strategy to gamify the collection and the labeling of child affect data in an effort to boost the performance of automatic child emotion detection to a level closer to what will be needed for translational digital healthcare. We leveraged our therapeutic smartphone game, GuessWhat, which was designed in large part for children with developmental and behavioral conditions, to gamify the secure collection of video data of children expressing a variety of emotions prompted by the game. Through a secure web interface gamifying the human labeling effort, we gathered and labeled 2,155 videos, 39,968 emotion frames, and 106,001 labels on all images. With this drastically expanded pediatric emotion centric database (>30x larger than existing public pediatric affect datasets), we trained a pediatric emotion classification convolutional neural network (CNN) classifier of happy, sad, surprised, fearful, angry, disgust, and neutral expressions in children. The classifier achieved 66.9% balanced accuracy and 67.4% F1-score on the entirety of CAFE as well as 79.1% balanced accuracy and 78.0% F1-score on CAFE Subset A, a subset containing at least 60% human agreement on emotions labels. This performance is at least 10% higher than all previously published classifiers, the best of which reached 56.% balanced accuracy even when combining "anger" and "disgust" into a single class. This work validates that mobile games designed for pediatric therapies can generate high volumes of domain-relevant datasets to train state of the art classifiers to perform tasks highly relevant to precision health efforts.}, added-at = {2020-12-17T03:24:23.000+0100}, author = {Washington, Peter and Kalantarian, Haik and Kent, Jack and Husic, Arman and Kline, Aaron and Leblanc, Emilie and Hou, Cathy and Mutlu, Cezmi and Dunlap, Kaitlyn and Penev, Yordan and Varma, Maya and Stockham, Nate and Chrisman, Brianna and Paskov, Kelley and Sun, Min Woo and Jung, Jae-Yoon and Voss, Catalin and Haber, Nick and Wall, Dennis P.}, biburl = {https://www.bibsonomy.org/bibtex/206393d4dda8c8305ee72765bdce668e8/peterwashington}, interhash = {15d247f79bc25d5c5aadfc7a6b3b5fa8}, intrahash = {06393d4dda8c8305ee72765bdce668e8}, keywords = {}, note = {cite arxiv:2012.08678}, timestamp = {2020-12-17T03:24:23.000+0100}, title = {Training an Emotion Detection Classifier using Frames from a Mobile Therapeutic Game for Children with Developmental Disorders}, url = {http://arxiv.org/abs/2012.08678}, year = 2020 }