Online crowds, with their large numbers and diversity, show great potential for creativity. Research has explored different ways of augmenting their creative performance, particularly during large-scale brainstorming sessions. Traditionally, this comes in the form of showing ideators some form of inspiration to get them to explore more categories or generate more and better ideas. The mechanisms used to select which inspirations are shown to ideators thus far have not taken into consideration ideators' individualities, which could hinder the effectiveness of support. In this paper, we introduce and evaluate CrowdMuse, a novel adaptive system for supporting large-scale brainstorming. The system models ideators based on their past ideas and adapts the system views and inspiration mechanism accordingly. We evaluate CrowdMuse over two iterative large online studies and discuss the implication of our findings for designing adaptive creativity support systems.

Research has explored different ways of improving crowd ideation, such as presenting examples or employing facilitators. While such support is usually generated through peripheral tasks delegated to crowd workers who are not part of the ideation, it is possible that the ideators themselves could benefit from the extra thought involved in doing them. Therefore, we iterate over an ideation system in which ideators can perform one of three peripheral tasks (rating originality and usefulness, similarity, or idea combination) on demand. In controlled experiments with workers on Mechanical Turk, we compare the effects of these secondary tasks to simple idea exposure or no support at all, examining usage of the inspirations, fluency, breadth, and depth of ideas generated. We find tasks to be as good or better than exposure, although this depends on the period of ideation and the fluency level. We also discuss implications of inspiration size, homogeneity, and frequency.

As technology is increasingly integrated into the classroom, understanding the facilitators and barriers for deployment becomes an important part of the process. While systems that employ traditional WIMP-based interfaces have a well-established body of work describing their integration into classroom environments, more novel technologies generally lack such a foundation to guide their advancement. In this paper we present Robo-Tangible Activities for Geometry (rTAG), a tangible learning environment that utilizes a teachable agent framing, together with a physical robotic agent. We describe its deployment in a school environment, qualitatively analyzing how teachers chose to orchestrate its use, the value they saw in it, and the barriers they faced while organizing the sessions with their students. Based on this analysis, we extract four recommendations that aid in designing and deploying systems that make use of affordances that are similar to those of the rTAG system.

A teachable agent is a learning companion that students teach about a domain they are trying to master. While most teachable agents have been virtual, there may be advantages to having students teach an agent with a physical form (i.e., a robot). The robot may better engage students in the learning activity, and if students take embodied action in order to instruct the robot, they may develop deeper knowledge. In this paper, we investigate these two hypotheses using the rTAG system, a teachable robot for geometry learning. In a study with 37 4th-6th grade participants, we compare rTAG to two other conditions, one where students use embodied action to teach a virtual agent, and one where students teach a virtual agent on a personal computer. We find that while there are no significant learning differences between conditions, students' perceptions of the agent are influenced by condition and prior knowledge.