Jeroen Linssen

Social Behaviour in Police Interviews: Relating Data to Theories

We analysed a corpus of enacted police interviews to get insight into the social behaviour of interviewees and police officers in this setting. We (exhaustively) collected the terms used to describe the interactions in those interviews. Through factor analysis, we showed that the theories interpersonal stance, face, and rapport and the meta-concepts information and strategy are necessary to include in a model that captures the social interaction in a police interview. Subsequent validation and relational analysis of the concepts from these theories showed which concepts from these theories are related. This work will be used to inform the construction of a virtual agent acting as a suspect in a training game for police officers.

Improving social awareness through thought bubbles and flashbacks of virtual characters

We present two prototypes of a serious game which is a aimed at raising police officers’ awareness of social stance during street interventions by letting them interact with virtual characters. We discuss the design, implementation and evaluation of a method of feedback on the police officers’ game actions. This method uses thought bubbles to show the cognitive state of virtual characters, using a theory of interpersonal stances. We use thought bubbles (1) to provide direct feedback by showing the agent’s current attitude, and (2) to provide delayed feedback at the start of a new scenario by showing a flashback to the previous scenario, expressing the character’s overall attitude towards the player. We conducted two experiments with students from the Dutch Police Academy and found that our implementations of these forms of feedback did not lead to directly measurable learning gains.

You Can Leave Your Head on - Attention Management and Turn-Taking in Multi-party Interaction with a Virtual Human/Robot Duo.

In two small studies, we investigated how a virtual human/ robot duo can complement each other in joint interaction with one or more users. The robot takes care of turn management while the virtual human draws attention to the robot. Our results show that having the virtual human address the robot, highlights the latter’s role in the interaction. Having the robot nonverbally indicate the intended addressee of a question asked by the virtual human proved successful in all cases when the robot was first addressed by the virtual human.

Snoozle -- A Robotic Pillow That Helps You Go to Sleep: HRI 2017 Student Design Competition

Not getting enough sleep is detrimental to our health and productivity, yet we have difficulty to maintain consistent bedtimes. Technological solutions to this problem mostly focus on detecting sleep patterns and providing feedback on them. We felt there was an opportunity for a perspective that concentrates on ones subjective experience. We propose Snoozle, an actuated pillow that supports consistent bedtimes by inviting users to bed, and improves the sleeping experience by enhancing the feeling of co-presence. In this proposal, we present how the concept of Snoozle developed from structured brainstorms, storyboards and sketches. We discuss the actuated pillow behavior and the envisioned interaction, and we detail our next steps.

LOITER-TB: Thought Bubbles that Give Feedback on Virtual Agents’ Experiences

We demonstrate LOITER-TB, a prototype of a serious game meant to improve the social awareness of police students. Central to its design is the provision of feedback through thought bubbles of virtual characters with which players interact. Our initial experiments provide weak support for our hypothesis that this form of feedback leads to gains in police students’ understanding of social interaction.