Nader Hanna

Evaluating the Impact of the Human-Agent Teamwork Communication Model (HAT-CoM) on the Development of a Shared Mental Model

It is well known that the development of a Shared Mental Model (SMM) leads to better teamwork performance. Communication of shared knowledge is considered a crucial factor in successful teamwork. In this paper, we evaluate the impact of applying a proposed Human-Agent Teamwork Communication Model, namely HAT-CoM, on the development of SMM between human and agent teammates. Another aim of the paper is to investigate the impact of an implausible or unreasonable request on the SMM. The results show that HAT-CoM is effective in assisting the human and agent teammates to develop SMM. In addition, the results show that an implausible request breaks the developed SMM.

Automatic acquisition of user models of interaction to evaluate the usability of virtual environments

Evaluation is an essential step in the research and development of software, particularly for new technologies such as Virtual Environments. One of the challenges to such evaluation is to collect data needed for analyzing the behavior of the users of the virtual environment. Conventional acquisition of evaluation data is time-consuming and prone to bias. In this paper, we present a taxonomy to assist identification and collection of appropriate variables for automatic data collection. We further show how these variables, such as navigation paths and characters met, can be used to capture the behavioral interaction of learners in a virtual ecosystem and to produce a user-model to evaluate the usability of the world under development.

A framework for a multi-agent collaborative virtual learning environment (MACVILLE) based on activity theory

Virtual Learning Environments are increasingly used in education to encourage collaborative learning and engagement with the learning material. However, collaborative activity is often minimal and superficial. We propose a multi-agent collaborative virtual learning environment in which the agents support communication skills and collaboration among and with learners. Our framework is underpinned by Activity theory which is a theoretical model of human activity that reflects its collaborative nature.

Academic Performance in a 3D Virtual Learning Environment: Different Learning Types vs. Different Class Types

The last decade has seen an increasing interest in the use of 3D virtual environments for educational applications. However, very few studies investigated the influence of the learning context, such as class type and learning type, on learners’ academic performance. This paper studied the impact of class type (i.e. comprehensive or selective) classes, as well as learning type (i.e. guided or challenge and guided), on students’ level of usage of a Virtual Learning Environment (VLE) as well as on their academic performance. The results showed that, unlike class type, there is a significant difference between learners’ in their usage of the VLE. Moreover, the results showed that the levels of using a VLE significantly correlated with learners’ academic performance.

Exploring the influence of a human-like dancing virtual character on the evocation of human emotion

ABSTRACT Dance has universally been used as a form of human expression for thousands of years. This common human behaviour and communication method has not been explored much in the context of computer-based technology, even within the field of virtual human research. This paper presents an experimental study investigating the impact of watching dancing virtual characters on human emotions. The study analysed the responses of 55 participants, composed of a mix of dancers and non-dancers, who watched a dancing virtual character perform 3 different dances that represented anger, sadness and happiness in different display orders. The participants’ reported changes in their emotions and their feelings of anger, sadness and happiness were significantly dependent on which dancing character’s emotion they watched and the emotional change did not rely on correct recognition of the depicted emotion. For experimental control, our characters were faceless and danced without music. Our results suggest that just by watching a dancing virtual character some of the benefits associated with dancing could be accessed in circumstances where it is not desirable or feasible to dance, justifying further research to develop a personalised character with a face and music that adapts according to the humans’ emotions and preferences.

Do birds of a feather work better together? The impact of a match in personality between humans and virtual agents on a shared mental model during collaboration

A shared mental model SMM between human team members has been found to improve teamwork performance. In the literature, multimodal communication of shared knowledge has been reported to influence the development of a SMM. In virtual worlds, within a team comprised of a human and an intelligent virtual agent IVA, the influence of IVA personality on collaboration and development of a SMM has not been previously studied. In this study, we explore the impact of an IVAs personality traits on the development of taskwork and teamwork SMMs with human teammates. Moreover, this study investigated the influence of a match in personality traits between IVAs and humans on the development of a SMM. In this study, five versions of an IVA performing the same scenario were developed. Besides a neutral personality, four combinations of two personality traits, i.e., extraversion and agreeableness were created. Participants were divided into five groups each assigned one version of the IVA. The results showed that agreeable IVAs positively impacted on the development of taskwork and teamwork SMMs; whereas extraversion did not influence development of the SMM. Moreover, when the human and IVA had matching agreeableness personality traits, SMM development and performance improved.

A collaborative agent architecture with human-agent communication model

Designing a virtual agent architecture that comprises collaboration between the agents and human users remains a challenging issue due to differences in beliefs, ways of reasoning and the abilities used to achieve the common goal. Allowing the agent and human to communicate verbally and non-verbally while achieving the collaborative task, further increases the difficulty of the challenge. In this paper, we present an overview of existing research involving collaborative agents in virtual environments and extend our Multi-Agent Collaborative VIrtuaL Learning Environment (MACVILLE) agent architecture to handle two-way human-agent collaboration. A scenario is provided.