arXiv subjects

Janet Rafner

Publications and source records attributed to Janet Rafner.

10 recordsLinked to original sources

arXiv2025

From Interaction to Collaboration: How Hybrid Intelligence Enhances Chatbot Feedback

Generative AI (GenAI) chatbots are becoming increasingly integrated into virtual assistant technologies, yet their success hinges on the ability to gather meaningful user feedback to improve interaction quality, system outcomes, and overall user acceptance. Successful chatbot interactions can enable organizations to build long-term relationships with their customers and users, supporting customer loyalty and furthering the organization's goals. This study explores the impact of two distinct narratives and feedback collection mechanisms on user engagement and feedback behavior: a standard AI-focused interaction versus a hybrid intelligence (HI) framed interaction. Initial findings indicate that while small-scale survey measures allowed for no significant differences in user willingness to leave feedback, use the system, or trust the system, participants exposed to the HI narrative statistically significantly provided more detailed feedback. These initial findings offer insights into designing effective feedback systems for GenAI virtual assistants, balancing user effort with system improvement potential.

cs.HC↗

arXiv2025

How Do Hackathons Foster Creativity? Towards AI Collaborative Evaluation of Creativity at Scale

Hackathons have become popular collaborative events for accelerating the development of creative ideas and prototypes. There are several case studies showcasing creative outcomes across domains such as industry, education, and research. However, there are no large-scale studies on creativity in hackathons which can advance theory on how hackathon formats lead to creative outcomes. We conducted a computational analysis of 193,353 hackathon projects. By operationalizing creativity through usefulness and novelty, we refined our dataset to 10,363 projects, allowing us to analyze how participant characteristics, collaboration patterns, and hackathon setups influence the development of creative projects. The contribution of our paper is twofold: We identified means for organizers to foster creativity in hackathons. We also explore the use of large language models (LLMs) to augment the evaluation of creative outcomes and discuss challenges and opportunities of doing this, which has implications for creativity research at large.

cs.HC↗

arXiv2025

AI Drawing Partner: Co-Creative Drawing Agent and Research Platform to Model Co-Creation

This paper describes the AI Drawing Partner, which is a co-creative drawing agent that also serves as a research platform to model co-creation. The AI Drawing Partner is an early example of a quantified co-creative AI system that automatically models the co-creation that happens on the system. The method the system uses to capture this data is based on a new cognitive science framework called co-creative sense-making (CCSM). The CCSM is based on the cognitive theory of enaction, which describes how meaning emerges through interaction with the environment and other people in that environment in a process of sense-making. The CCSM quantifies elements of interaction dynamics to identify sense-making patterns and interaction trends. This paper describes a new technique for modeling the interaction and collaboration dynamics of co-creative AI systems with the co-creative sense-making (CCSM) framework. A case study is conducted of ten co-creative drawing sessions between a human user and the co-creative agent. The analysis includes showing the artworks produced, the quantified data from the AI Drawing Partner, the curves describing interaction dynamics, and a visualization of interaction trend sequences. The primary contribution of this paper is presenting the AI Drawing Partner, which is a unique co-creative AI system and research platform that collaborates with the user in addition to quantifying, modeling, and visualizing the co-creative process using the CCSM framework.

cs.HC↗

arXiv2021

Revisiting Citizen Science Through the Lens of Hybrid Intelligence

Artificial Intelligence (AI) can augment and sometimes even replace human cognition. Inspired by efforts to value human agency alongside productivity, we discuss the benefits of solving Citizen Science (CS) tasks with Hybrid Intelligence (HI), a synergetic mixture of human and artificial intelligence. Currently there is no clear framework or methodology on how to create such an effective mixture. Due to the unique participant-centered set of values and the abundance of tasks drawing upon both human common sense and complex 21st century skills, we believe that the field of CS offers an invaluable testbed for the development of HI and human-centered AI of the 21st century, while benefiting CS as well. In order to investigate this potential, we first relate CS to adjacent computational disciplines. Then, we demonstrate that CS projects can be grouped according to their potential for HI-enhancement by examining two key dimensions: the level of digitization and the amount of knowledge or experience required for participation. Finally, we propose a framework for types of human-AI interaction in CS based on established criteria of HI. This "HI lens" provides the CS community with an overview of several ways to utilize the combination of AI and human intelligence in their projects. It also allows the AI community to gain ideas on how developing AI in CS projects can further their own field.

cs.HC↗

arXiv2021

SciNote: Collaborative Problem Solving and Argumentation Tool

As educators push for students to learn science by doing science, there is a need for computational scaffolding to assist students' evaluation of scientific evidence and argument building. In this paper, we present a pilot study of SciNote, a CSCL tool allowing educators to integrate third-party software into a flexible and collaborative workspace. We explore how SciNote enables teams to build data-driven arguments during inquiry-based learning activities.

cs.CY↗

arXiv2020

The power of pictures: using ML assisted image generation to engage the crowd in complex socioscientific problems

Human-computer image generation using Generative Adversarial Networks (GANs) is becoming a well-established methodology for casual entertainment and open artistic exploration. Here, we take the interaction a step further by weaving in carefully structured design elements to transform the activity of ML-assisted imaged generation into a catalyst for large-scale popular dialogue on complex socioscientific problems such as the United Nations Sustainable Development Goals (SDGs) and as a gateway for public participation in research.

cs.HC↗

arXiv2020

Measuring Cognitive Abilities in the Wild: Validating a Population-Scale Game-Based Cognitive Assessment

Rapid individual cognitive phenotyping holds the potential to revolutionize domains as wide-ranging as personalized learning, employment practices, and precision psychiatry. Going beyond limitations imposed by traditional lab-based experiments, new efforts have been underway towards greater ecological validity and participant diversity to capture the full range of individual differences in cognitive abilities and behaviors across the general population. Building on this, we developed Skill Lab, a novel game-based tool that simultaneously assesses a broad suite of cognitive abilities while providing an engaging narrative. Skill Lab consists of six mini-games as well as 14 established cognitive ability tasks. Using a popular citizen science platform (N = 10725), we conducted a comprehensive validation in the wild of a game-based cognitive assessment suite. Based on the game and validation task data, we constructed reliable models to simultaneously predict eight cognitive abilities based on the users' in-game behavior. Follow-'-up validation tests revealed that the models can discriminate nuances contained within each separate cognitive ability as well as capture a shared main factor of generalized cognitive ability. Our game-based measures are five times faster to complete than the equivalent task-based measures and replicate previous findings on the decline of certain cognitive abilities with age in our large cross-sectional population sample (N = 6369). Taken together, our results demonstrate the feasibility of rapid in-the-wild systematic assessment of cognitive abilities as a promising first step towards population-scale benchmarking and individualized mental health diagnostics.

physics.soc-ph↗

arXiv2020

crea.blender: A Neural Network-Based Image Generation Game to Assess Creativity

We present a pilot study on crea.blender, a novel co-creative game designed for large-scale, systematic assessment of distinct constructs of human creativity. Co-creative systems are systems in which humans and computers (often with Machine Learning) collaborate on a creative task. This human-computer collaboration raises questions about the relevance and level of human creativity and involvement in the process. We expand on, and explore aspects of these questions in this pilot study. We observe participants play through three different play modes in crea.blender, each aligned with established creativity assessment methods. In these modes, players "blend" existing images into new images under varying constraints. Our study indicates that crea.blender provides a playful experience, affords players a sense of control over the interface, and elicits different types of player behavior, supporting further study of the tool for use in a scalable, playful, creativity assessment.

cs.HC↗

arXiv2020

Crowdsourcing human common sense for quantum control

Citizen science methodologies have over the past decade been applied with great success to help solve highly complex numerical challenges. Here, we take early steps in the quantum physics arena by introducing a citizen science game, Quantum Moves 2, and compare the performance of different optimization methods across three different quantum optimal control problems of varying difficulty. Inside the game, players can apply a gradient-based algorithm (running locally on their device) to optimize their solutions and we find that these results perform roughly on par with the best of the tested standard optimization methods performed on a computer cluster. In addition, cluster-optimized player seeds was the only method to exhibit roughly optimal performance across all three challenges. This highlights the potential for crowdsourcing the solution of future quantum research problems.

quant-ph↗

arXiv2019

Geometry of turbulent dissipation and the Navier-Stokes regularity problem

The question of whether a singularity can form in an initially regular flow, described by the 3D incompressible Navier-Stokes (NS) equations, is a fundamental problem in mathematical physics. The NS regularity problem is super-critical, i.e., there is a 'scaling gap' between what can be established by mathematical analysis and what is needed to rule out a singularity. A recently introduced mathematical framework--based on a suitably defined `scale of sparseness' of the regions of intense vorticity--brought the first scaling reduction of the NS super-criticality since the 1960s. Here, we put this framework to the first numerical test using a spatially highly resolved computational simulation performed near a 'burst' of the vorticity magnitude. The results confirm that the scale is well suited to detect the onset of dissipation and provide strong numerical evidence that ongoing mathematical efforts may succeed in closing the scaling gap.

math-ph↗