Collaboration with Cognitive Assistants and AI
Permanent URI for this collection
Browse
Recent Submissions
Item Understanding Human-AI Cooperation Through Game-Theory and Reinforcement Learning Models(2021-01-05) Schelble, Beau; Flathmann, Christopher; Canonico, Lorenzo-Barberis; Mcneese, NathanFor years, researchers have demonstrated the viability and applicability of game theory principles to the field of artificial intelligence. Furthermore, game theory has been shown as a useful tool for researching human-machine interaction, specifically their cooperation, by creating an environment where cooperation can initially form before reaching a continuous and stable presence in a human-machine system. Additionally, recent developments in reinforcement learning artificial intelligence have led to artificial agents cooperating more efficiently with humans, especially in more complex environments. This research conducts an empirical study to understand how different modern reinforcement learning algorithms and game theory scenarios could create different cooperation levels in human-machine teams. Three different reinforcement learning algorithms (Vanilla Policy Gradient, Proximal Policy Optimization, and Deep Q-Network) and two different game theory scenarios (Hawk Dove and Prisoners dilemma) were examined in a large-scale experiment. The results indicated that different reinforcement learning models interact differently with humans with Deep-Q engendering higher cooperation levels. The Hawk Dove game theory scenario elicited significantly higher levels of cooperation in the human-artificial intelligence system. A multiple regression using these two independent variables also found a significant ability to predict cooperation in the human-artificial intelligence systems. The results highlight the importance of social and task framing in human-artificial intelligence systems and noted the importance of choosing reinforcement learning models.Item The Advent of Digital Productivity Assistants: The Case of Microsoft MyAnalytics(2021-01-05) Winikoff , Michael; Cranefield, Jocelyn; Li , Jane; Doyle, Cathal; Richter, AlexanderModern digital work environments allow for great flexibility, but can also contribute to a blurring of work/life boundaries and technostress. An emerging class of intelligent tools, that we term Digital Productivity Assistant (DPA), helps knowledge workers to improve their productivity by creating awareness of their collaboration behaviour and by suggesting improvements. In this revelatory case study, we combine auto-ethnographic insights with interview data from three organisations to explore how one such tool works to influence collaboration and productivity management behaviours, using the lens of persuasive IS design. We also identify barriers to DPAs’ effective use as a partner in personal productivity management.Item Deep learning object detection as an assistance system for complex image labeling tasks(2021-01-05) Leimkühler, Max; Gravemeier, Laura Sophie; Biester, Tim; Thomas, OliverObject detection via deep learning has many promising areas of application. However, robustness and accuracy of fully automated systems are often insufficient for practical use. Integrating results from Artificial Intelligence (AI) and human intelligence in collaborative settings might bridge the gap between efficiency and accuracy. This study proves increased efficiency when supporting human intelligence through AI without negative impact on effectiveness in a fine- grained car scratch image labeling task. Based on the confirmed benefits of AI with human intelligence in the loop approaches, this contribution discusses potential practical application scenarios and envisions the implementation of assistance systems supported by computer vision.Item Introduction to the Minitrack on Collaboration with Cognitive Assistants and AI(2021-01-05) Bittner, Eva; Ebel, Philipp; Oeste-Reiß, Sarah; Söllner, Matthias