Gaming the system, a behavior in which learners exploit a system's properties to make progress while avoiding learning, has frequently been shown to be associated with lower learning. However, when we applied a previously validated gaming detector across conditions in experiments with an algebra tutor, the detected gaming was not associated with reduced learning, challenging its validity in our study context. Our exploratory data analysis suggested that varying contextual factors across and within conditions contributed to this lack of association. We present a new approach, latent variable-based gaming detection (LV-GD), that controls for contextual factors and more robustly estimates student-level latent gaming tendencies. In LV-GD, a student is estimated as having a high gaming tendency if the student is detected to game more than the expected level of the population given the context. LV-GD applies a statistical model on top of an existing action-level gaming detector developed based on a typical human labeling process, without additional labeling effort. Across three datasets, we find that LV-GD consistently outperformed the original detector in validity measured by association between gaming and learning as well as reliability. LV-GD also afforded high practical utility: it more accurately revealed intervention effects on gaming, revealed a correlation between gaming and perceived competence in math and helped understand productive detected gaming behaviors. Our approach is not only useful for others wanting a cost-effective way to adapt a gaming detector to their context but is also generally applicable in creating robust behavioral measures.

The current study introduces a model for measuring student diligence using online behaviors during intelligent tutoring system use. This model is validated using a full academic year dataset to test its predictive validity against long-term academic outcomes including end-of-year grades and total work completed by the end of the year. The model is additionally validated for robustness to time-sample length as well as data sampling frequency. While the model is shown to be predictive and robust to time-sample length, the results are inconclusive for robustness in data sampling frequency. Implications for research on interventions, and understanding the influence of self-control, motivation, metacognition, and cognition are discussed.

Large-scale idea generation platforms often expose ideators to previous ideas. However, research suggests people generate better ideas if they see abstracted solution paths (e.g., descriptions of solution approaches generated through human sensemaking) rather than being inundated with all prior ideas. Automated and semi-automated methods can also offer interpretations of earlier ideas. To benefit from sensemaking in practice with limited resources, ideation platform developers need to weigh the cost-quality tradeoffs of different methods for surfacing solution paths. To explore this, we conducted an online study where 245 participants generated ideas for two problems in one of five conditions: 1) no stimuli, 2) exposure to all prior ideas, or solution paths extracted from prior ideas using 3) a fully automated workflow, 4) a hybrid human-machine approach, and 5) a fully manual approach. Contrary to expectations, human-generated paths did not improve ideation (as meas-ured by fluency and breadth of ideation) over simply showing all ideas. Machine-generated paths sometimes significantly improved fluency and breadth of ideation over no ideas (although at some cost to idea quality). These findings suggest that automated sensemaking can improve idea generation, but we need more research to understand the value of human sensemaking for crowd ideation.

Online crowds are a promising source of new innovations. However, crowd innovation quality does not always match its quantity. In this paper, we explore how to improve crowd innovation with real-time expert guidance. One approach would for experts to provide personalized feed-back, but this scales poorly, and may lead to premature convergence during creative work. Drawing on strategies for facilitating face-to-face brainstorms, we introduce a crowd ideation system where experts monitor incoming ideas through a dashboard and offer high-level “inspirations” to guide ideation. A series of controlled experiments show that experienced facilitators increased the quantity and creativity of workers' ideas compared to unfacilitated workers, while Novice facilitators reduced workers' creativity. Analyses of inspiration strategies suggest these opposing results stem from differential use of successful inspiration strategies (e.g., provoking mental simulations). The results show that expert facilitation can significantly improve crowd innovation, but inexperienced facilitators may need scaffolding to be successful.

Soft Pneumatic Actuators (SPAs) have recently become popular for use as fingers in robotic hands because of their inherent compliance, low cost, and ease of construction. We seek to overcome two key limitations which limit SPAs' abilities to grasp and manipulate objects: 1) Current SPAs lack position or force sensor feedback, which prevents controlling them precisely (e.g. to achieve a hand preshape or apply a specified pushing force), and 2) the tip of the SPA is compliant and has high friction against common surfaces, causing the SPA to stick against surfaces when grasping objects from above. To overcome the first limitation we propose methods to integrate soft eGaIn sensors into SPAs and controllers that use these sensors' feedback for position and force control. To overcome the second limitation, we explore embedding rigid fingernails into the tip of the SPA so that the finger does not stick against surfaces and can wedge under objects. Our experiments suggest that we can achieve low steady-state error and overshoot in position and force using feed-forward models that relate pressure, force, and curvature along with a PID controller. We also compare several fingernail designs and show that the best-performing design significantly outperforms having no fingernails when grasping a set of common objects from a table.

Many crowd ideation systems seek to gather scores of ideas from people online. However, this often leads to many bad ideas and duplication. A dedicated facilitator who guides exploration of the solution space is a common and effective strategy for optimizing ideation in face-to-face brainstorming, but has not yet been explored in computer-supported crowd ideation. We introduce IdeaGens, a social ideation system for guided crowd brainstorming. IdeaGens divides the crowd into ideation and synthesis tasks, and enables efficient data-driven facilitation of the crowd’s ideation. This work can inform general strategies for shepherding the crowd to produce better results for complex collaborative tasks.