This paper introduces a Voice-Augmented Virtual Reality (VR) Interface designed to enhance the experience of interacting with 3D models in virtual reality environments, specifically targeting serious games and learning environments. Leveraging natural language as the primary mode of interaction, this paper presents a framework and a study that compares the voice-augmented system with a conventional hand controller version across seven fundamental 3D interaction tasks. The research explores a wide range of object interactions and offers a comprehensive voice-augmented VR interface. The system presents a more accessible and equitable alternative to controller-based interactions. This is demonstrated by a user study that compares the experiences of male and female participants engaging with the system.

This paper presents ContrastWSD, a RoBERTa-based metaphor detection model that integrates the Metaphor Identification Procedure (MIP) and Word Sense Disambiguation (WSD) to extract and contrast the contextual meaning with the basic meaning of a word to determine whether it is used metaphorically in a sentence. By utilizing the word senses derived from a WSD model, our model enhances the metaphor detection process and outperforms other methods that rely solely on contextual embeddings or integrate only the basic definitions and other external knowledge. We evaluate our approach on various benchmark datasets and compare it with strong baselines, indicating the effectiveness in advancing metaphor detection.

Reinforcement learning algorithms have been applied to many research areas in gaming and non-gaming applications. However, in gaming artificial intelligence (AI), existing reinforcement learning tools are aimed at experienced developers and not readily accessible to learners. The unpredictable nature of online learning is also a barrier for casual users. This paper proposes the EasyGameRL framework, a novel approach to the education of reinforcement learning in games using modular visual design patterns. The EasyGameRL framework and its software implementation in Unreal Engine are modular, reusable, and applicable to multiple game scenarios. The pattern-based approach allows users to effectively utilize reinforcement learning in their games and visualize the components of the process. This would be helpful to AI learners, educators, designers and casual users alike.

This paper describes the development of a virtual reality (VR) simulation game for educating engineering students in manufacturing. Undergraduate engineering students work on solving design and manufacturing problems and utilize professional skills to improve their overall performance and outcome. This research utilizes interactive and immersive VR technologies to develop a new integrated approach to understand problem solving in engineering students and determine if engineering students are attending to the correct elements while they are solving design and manufacturing problems. Furthermore, a player modeling technique is proposed to deliver an experience adapted for each student. The approach will be tested, validated and used to bridge the skills gap that exists for many undergraduate engineering students.

Using serious games as a form of training and education has been a growing trend. While there has been research into the adaptation of games for training, assessment of user knowledge as a whole for the purpose of creating tailored training content has not been closely examined. In this paper, we propose a general framework for creating an assessment game and show how Knowledge Assessment can be used to guide the focus of subsequent training modules. Using our framework, we address the frustration and anxiety expressed by medical and nursing professionals about their lack of training regarding indicators of child physical abuse (CPA) in the United States. We develop the Computer Simulated Interactive Child Abuse Screening Tool (CSI-CAST), which contains scenarios in a serious game and uses assistive AI technologies to assess a group of users and discover features that are important in indicating the users' collective knowledge identifying CPA. A user study is conducted to show that CSI-CAST is easy to use and it functions to discover specific training needs.

Gender in video games is a popular topic. However, the focus is usually on how gender is portrayed within games. In this paper, we examine the effects of players' gender on the perception of virtual character behavior and emotion based on the results of two user studies involving story-based games. The first study compared players' perception of virtual character behaviors. We analyzed perceived differences both by gender and by gaming experience. In this study, we found that female gamers were more appreciative of complex behaviors than male gamers. In the second study, we examined the influence of gender on player' ability to identify the emotion being displayed by a virtual character. We found that most emotions were identified comparably, with the exception of anger. Female players were significantly better at identifying angry characters compared to male players. We also investigated any perception differences between emotions expressed by male and female virtual characters, but we did not identify any statistically significant differences. Overall, the studies suggest that there are differences in how male and female players perceive virtual characters, and if game designers want players to perceive these characters in a certain way, they should consider the gender of targeted players.