Big Data Technologies and Applications. 8th International Conference, BDTA 2017, Gwangju, South Korea, November 23–24, 2017, Proceedings

Research Article

Keyboard and Mouse: Tools in Identifying Emotions During Computer Activities

Download
343 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-98752-1_13,
        author={Jheanel Estrada and Jomar Buhia and Albert Guevarra and Marvin Forcado},
        title={Keyboard and Mouse: Tools in Identifying Emotions During Computer Activities},
        proceedings={Big Data Technologies and Applications. 8th International Conference, BDTA 2017, Gwangju, South Korea, November 23--24, 2017, Proceedings},
        proceedings_a={BDTA},
        year={2018},
        month={11},
        keywords={Affective computing Self- assessment Manikin Gradient-Boosted Trees},
        doi={10.1007/978-3-319-98752-1_13}
    }
    
  • Jheanel Estrada
    Jomar Buhia
    Albert Guevarra
    Marvin Forcado
    Year: 2018
    Keyboard and Mouse: Tools in Identifying Emotions During Computer Activities
    BDTA
    Springer
    DOI: 10.1007/978-3-319-98752-1_13
Jheanel Estrada1,*, Jomar Buhia1,*, Albert Guevarra1,*, Marvin Forcado1,*
  • 1: Technological Institute of the Philippines
*Contact email: jheanelestrada29@gmail.com, buhiajomar@gmail.com, abetguevarra@gmail.com, coolviper01@gmail.com

Abstract

Emotion recognition is a field of study that is much investigated by researchers because it is an important piece in the development of intelligent system. Researchers used different techniques to capture the emotional response of the people based on the situation and design patterns to see its effects and relevance. In this paper, the researchers investigated the emotional patterns of the students towards programming using input devices such as keyboard and mouse. The use of keyboard and mouse provided an affordable and non-intrusive method of collecting data. The keyboard and mouse data collected were mapped by an expert on facial expressions to emotions captured on video at the same the students were answering the programming problem. From these annotations, the classes of emotions were derived. Rapid miner was then used to identify the pattern of keyboard and mouse strokes that corresponds to different emotions. The accuracy of the results were 70.25% and with a Kappa of 0.612%.