It is difficult to imagine a society that does not utilize teams. At the same time, teams need to evolve to meet today’s challenges of the ever-increasing proliferation of data and complexity. It may be useful to add artificial intelligent (AI) agents to team up with humans. Then, as AI agents are integrated into the team, the first study asks what roles can AI agents take? The first study investigates this issue by asking whether an AI agent can take the role of a facilitator and in turn, improve planning outcomes by facilitating team processes. Results indicate that the human facilitator was significantly better than the AI facilitator at reducing cognitive biases such as groupthink, anchoring, and information pooling, as well as increasing decision quality and score. Additionally, participants viewed the AI facilitator negatively and ignored its inputs compared to the human facilitator. Yet, participants in the AI Facilitator condition performed significantly better than participants in the No Facilitator condition, illustrating that having an AI facilitator was better than having no facilitator at all. The second study explores whether artificial social intelligence (ASI) agents can take the role of advisors and subsequently improve team processes and mission outcome during a simulated search-and-rescue mission. The results of this study indicate that although ASI advisors can successfully advise teams, they also use a significantly greater number of taskwork interventions than teamwork interventions. Additionally, this study served to identify what the ASI advisors got right compared to the human advisor and vice versa. Implications and future directions are discussed.

The implementation of chatbots in customer service is widely prevalent in today’s world with insufficient research to appropriately refine all of their conversational abilities. Chatbots are favored for their ability to handle simple and typical requests made by users, but chatbots have proven to be prone to conversational breakdowns. The study researched how the use of repair strategies to combat conversational breakdowns in a simple versus complex task setting affected user experience. Thirty participants were collected and organized into six different groups in a two by three between subjects factorial design. Participants were assigned one of two tasks (simple or complex) and one of three repair strategies (repeat, confirmation, or options). A Wizard-of-Oz approach was used to simulate a chatbot that participants interacted with to complete a task in a hypothetical setting. Participants completed the task with this researcher-controlled chatbot as it intentionally failed the conversation multiple times, only to repair it with a repair strategy. Participants recorded their user experience regarding the chatbot afterwards. An Analysis of Covariance statistical test was run with task duration being a covariate variable. Findings indicate that the simple task difficulty was significant in improving the user experience that participants recorded whereas the particular repair strategy had no effect on the user experience. This indicates that simpler tasks lead to improved positive user experience and the more time that is spent on a task, the less positive the user experience. Overall, results associated with the effects of task difficulty and repair strategies on user experience were only partially consistent with previous literature.

Social categories such as race and gender are associated by people with certain characteristics (e.g. males are angry), which unconsciously affects how people evaluate and react to a person of specific social categories. This phenomenon, referred to as implicit bias, has been the interest of many social psychologists. However, the implicit bias research has been focusing on only one social category at a time, despite humans being entities of multiple social categories. The research also neglects the behavioral contexts in which implicit biases are triggered and rely on a broad definition for the locus of the bias regulation mechanism. These limitations raise questions on whether the current bias reduction strategies are effective. The current dissertation sought to address these limitations by introducing an ecologically valid and multidimensional method. In Chapters 1 and 2, the mouse-tracking task was integrated into the implicit association task to examine how implicit biases were moderated in different behavioral contexts. The results demonstrated that the manifestation of implicit biases depended on the behavioral context as well as the distinctive identity created by the combinations of different social categories. Chapter 3 laid groundwork for testing working memory as the processing capacity for the bias regulation mechanism. The result suggested that the hand-motion tracking indices of working memory load could be used to infer the capacity of an individual to suppress the influence of implicit bias. In Chapter 4, the mouse-tracking paradigm was integrated into the Stroop task with implicit associations serving as the Stroop targets. The implicit associations produced various effects including the conflict adaptation effect, like the Stroop targets, which suggested that implicit associations and Stroop stimuli are handled by overlapping cognitive mechanisms. Throughout these efforts, the current dissertation, first, demonstrated that a more ecologically valid and multidimensional approach is required to understand biased behaviors in detail. Furthermore, the current dissertation suggested the cognitive control mechanism as a finer definition for the locus of the bias regulation mechanism, which could be leveraged to offer solutions that are more adaptive and effective in the environment where collaboration and harmony are more important than ever.