This project will develop and train an AI agent in identifying relevant patterns of conflict and affectivity during team interaction, both in text and video, and conveying appropriate real-time feedback. A set of three studies will test the role of the agent-led feedback on team dynamics and outcomes, such as performance, interpersonal affect regulation, engagement, as well as the role of the agent's features in its acceptance by the team.

Little is known about which team roles autonomous technology can adopt (e.g., monitor-evaluator, resource investigator, team worker, Fisher et al., 2001) or which sets of task types (e.g., problem solving, advising, managing others, Wildman et al., 2012) it can tackle successfully when working interdependently with humans towards a common goal. More specifically, in what interpersonal team processes (Marks et al., 2001) are concerned, we don´t know if or how these autonomous agents can contribute to regulating the affect in the team or to manage interpersonal conflict.

First, we will develop and train an AI agent for the detection of interaction affective and conflict patterns from multiple-source information types (i.e., verbal language, gestures, tone of voice, etc) in work teams. Second, and narrowing down the focus of the project to the organizational behavior field, we will explore the developmental role of the agent, by defining feedback messages tailored to the interpersonal needs of the team identified previously, and explore their impact of that feedback on the teams’ performance, viability, and interpersonal processes over time. Third, we will analyze the impact of different types of agent-led feedback, in terms of content and form, to the perception of Yoda as a team member by the remaining members of the team, and its relationship to team effectiveness.

At the scientific level, we expect to contribute to open the dialogue between human resources and organizational behavior scholars and artificial intelligence scholars. More specifically, we will propose a Special Issue on Computers in Human Behavior, with a Guest Editorial Board consisting of experts from both areas (the project’s team), to where some of the results of the project will be submitted. We expect to have two scientific publications on top-tier journals, and to disseminate the results of the project, in its different phases, in international conferences, namely EAWOP and INGroup.

            Still at a scientific level, we will broader our knowledge on the pressing and timely issue of Human-AI Teamwork, leading the research on agent-led feedback on interpersonal interaction. This project will help unveil the potential of agents in taking on the role of managing relationships, as well as of the psychological and collective reaction to it. Hence, future work on the development of HATs can benefit from the insights of the project, and future work on the development of sentiment analysis’ processes too.

From a practical point of view, we will develop a new tool that can be used by teams in different companies in the management of their interpersonal processes. This will be an useful tool for team members and team leaders who interact mostly in virtual environments. Beyond informing the team in real time about their affective state to allow for emotional regulation, Yoda can also give relevant information to team leaders and human resources professionals that can inform future team composition, soft skills assessment and training, and a longitudinal tracking of general emotional state of teams and their members. This will allow practitioners to use AI systems not only for optimizing work processes and extend human capabilities, but to influence interpersonal dynamics in a positive way.

No records found.

No records found.

No records found.

No records found.

No records found.

With the objective to increase the research activity directed towards the achievement of the United Nations 2030 Sustainable Development Goals, the possibility of associating scientific projects with the Sustainable Development Goals is now available in Ciência_Iscte. These are the Sustainable Development Goals identified for this project. For more detailed information on the Sustainable Development Goals, click here.