Emotion Elicitation in Socially Intelligent Services: the Intelligent Typing Tutor Study Case

The paper discusses the challenges of user emotion elicitation in socially intelligent services, based on the experimental design and results of the intelligent typing tutor. Human-machine communication (HMC) of the typing tutor is supported by the continuous real-time emotion elicitation of user’s expressed emotions and the emotional feedback of the service, through the graphically rendered emoticons. It is argued that emotion elicitation is an important part of successful HMC, as it improves the communication loop and increases user engagement. Experimental results show that user’s valence and arousal are elicited during the typing practice, on average 18% to 25% of the time for valence and 20% to 31% of the time for arousal. However, the efficiency of emotion elicitation varies greatly throughout the use of the service, and also moderately among users. Overall, the results show that emotion elicitation, even via simple graphical emoticons, has significant potential in socially intelligent services.