KT

K. Tsiakas

info

Please Note

6 records found

From Interaction Primitives to a Design Space

Journal article (2024) - Konstantinos Tsiakas, Dave Murray-Rust
This article aims to develop a semi-formal representation for Human-AI (HAI) interactions, by building a set of interaction primitives which can specify the information exchanges between users and AI systems during their interaction. We show how these primitives can be combined into a set of interaction patterns which can capture common interactions between humans and AI/ML models. The motivation behind this is twofold: firstly, to provide a compact generalization of existing practices for the design and implementation of HAI interactions; and secondly, to support the creation of new interactions by extending the design space of HAI interactions. Taking into consideration frameworks, guidelines, and taxonomies related to human-centered design and implementation of AI systems, we define a vocabulary for describing information exchanges based on the model’s characteristics and interactional capabilities. Based on this vocabulary, a message passing model for interactions between humans and models is presented, which we demonstrate can account for existing HAI interaction systems and approaches. Finally, we build this into design patterns which can describe common interactions between users and models, and we discuss how this approach can be used toward a design space for HAI interactions that creates new possibilities for designs as well as keeping track of implementation issues and concerns. ...

How Justifying Chatbot Response Delays Impact User Trust

In human communication, responding to a question very slowly or quickly influences our trust in the answer. As chatbots evolve to increasingly mimic human speech, response speed can be artificially varied to create certain impressions on users. However, studies remain inconclusive, potentially due to the absence of contextual cues that allow for interpretation of the delay. Thus, this study explores textual explanations that justify the instant and dynamic – dependent on answer length – response delays. We derive five design variations based on prior work and evaluate their impact on the chatbot’s perceived social presence and transparency (N = 10). In a between-subject online study (N = 194), we then evaluate the influence of the highest-rated justification on users’ perceptions of chatbot transparency, social presence, and trust for the two delay conditions. Results demonstrate that while such justifications enhance perceived transparency and trust in the immediate response scenario, they show no effect in the dynamic delay context. ...

The Effect of Self-assessment Strategy Through Robots on Children’s Motivation and Performance in Piano Practice

Journal article (2023) - Heqiu Song, Konstantinos Tsiakas, Jaap Ham, Panos Markopoulos, Emilia I. Barakova
This research examines how to design social robots to support self-regulated learning skills for piano practice. More specifically, a social robot is used to provide feedback to children and initiate self-assessment. To assess the impact of this approach on children’s motivation and performance, we conducted an experiment in a music school where 50 children practiced with both a self-assessment and a non-evaluative robot. Results showed that when the children interacted with the self-assessment robot they had higher motivation and better performance than when they interacted with the non-evaluative robot. Furthermore, interaction effects were found between the robot conditions, the children’s learning stages, and their gender regarding their motivation and rhythm performance. Overall, the study demonstrates a positive influence of robot-initiated self-assessment on children’s musical instrument practice and provided insights for personalized child-robot interaction design. ...

Supporting Machine Learning Practitioners Making and Recording Ethical Decisions

Conference paper (2023) - D.S. Murray-Rust, K. Tsiakas
Ethics should be a practice, not a checkbox. Data scientists want to answer questions about individuals and society using the vast torrent of data that flows around us. Machine learning practitioners want to develop and connect complex
models of the world and use them safely in critical situations. Ethical issues can be seen as getting in the way of the core idea and form pain points around managing, using and learning from data, as well as designing human-centric and ethical systems. This is because there is a design gap around ethics in data
science and machine learning: the tools that we use do not support ethical data use, which means that data scientists and machine learning practitioners, already engaged in technically complex, multidisciplinary work, must add another dimension to their thinking. This work proposes and outlines an infrastructure and framework that can support in-the-moment ethical decision
making and recording, as well as post-hoc audits and ethical model deployment. ...
Conference paper (2023) - Xingran Ruan, Charaka Palansuriya, Aurora Constantin, Konstantinos Tsiakas
The present study aims to investigate the relationship between emotions experienced during learning and metacognition in typically developing (TD) children and those with autism spectrum disorder (ASD). This will assist us in using machine learning (ML) to develop a facial emotion recognition (FER) based intelligent tutor system (ITS) to support children’s metacognitive monitoring process in order to enhance their learning outcomes. In this paper, we first report the results of our preliminary research, which utilized an ML-based FER algorithm to detect four spontaneous epistemic emotions (i.e., neutral, confused, frustrated, and boredom) and six spontaneous basic emotions (i.e., anger, disgust, fear, happiness, sadness, and surprise). Subsequently, we adapted an application (‘BrainHood’) to create the ‘Meta-BrainHood’, that embedded our proposed ML-based FER algorithm to examine the relationship between facial emotion expressions and metacognitive monitoring performance in TD children and those with ASD. Finally, we outline the future steps in our research, which adopts the outcomes of the first two steps to construct an ITS to improve children’s metacognitive monitoring performance and learning outcomes. ...
Conference paper (2022) - Konstantinos Tsiakas, Dave Murray-Rust
In this paper, we discuss the trends and challenges of the integration of Artificial Intelligence (AI) methods in the workplace. An important aspect towards creating positive AI futures in the workplace is the design of fair, reliable and trustworthy AI systems which aim to augment human performance and perception, instead of replacing them by acting in an automatic and non-transparent way. Research in Human-AI Interaction has proposed frameworks and guidelines to design transparent and trustworthy human-AI interactions. Considering such frameworks, we discuss the potential benefits of applying human-in-the-loop (HITL) and explainable AI (XAI) methods to define a new design space for the future of work. We illustrate how such methods can create new interactions and dynamics between human users and AI in future work practices. ...