This study investigates the impact of introducing conversational pauses and self-adaptor gestures in robots to enhance human-likeness during English conversation practice. As globalization increases the demand for English proficiency, there is increasing interest in using conversational robots for language practice. However, conventional robots often lack natural disfluencies, making interactions feel overly artificial, especially for beginners. This study focuses on enhancing the robot's non-verbal behaviors by implementing conversational pauses and self-adaptor gestures such as fidgeting at predetermined intervals during scripted conversational scenarios. The experiment involved 22 men and women in their 20s. An experimental evaluation revealed that approximately 90% of participants perceived an increased sense of human-likeness when the robot exhibited these pausing and hesitation behaviors. These results suggest that strategically incorporating naturalistic disfluencies and human-like self-adaptor gestures into a conversational robot's non- verbal repertoire can significantly increase its perceived anthropomorphism and potentially improve user engagement in language learning contexts.

Fostering creativity in programming tasks is a challenging endeavor, especially when working alone. Traditional programming environments often lack support for stimulating creative thinking and idea generation. This paper presents an interactive augmented reality (AR) system that aims to enhance creativity in Internet of Things (IoT) programming tasks. The proposed system leverages Interactive Evolutionary Computation (IEC) and AR technologies to facilitate the collaborative exploration and evolution of IoT device programs (MESH programs). Users can create, evaluate, and iteratively refine MESH programs through an immersive AR interface, while being inspired by the system's suggestions and other users' creations. The system employs a genetic algorithm to evolve MESH programs based on user evaluations, and utilizes natural language processing to generate program descriptions that can trigger new ideas. A user study (n=16) was conducted to evaluate the system's effectiveness in stimulating creativity and promoting collaboration. Quantitative analysis revealed a significant increase in idea generation over time and a greater impact on inspiration for novice programmers. Qualitative findings highlighted the system's ability to foster a creative and collaborative environment. The insights gained from this study inform the design of future tools and experiences that support creative thinking and collaboration in the IoT domain.

As English becomes increasingly important globally, many agent-based conversation practice environments struggle to maintain learner motivation due to a lack of personalized behavior. This study proposes optimizing a conversational agent's non-verbal cues—such as nodding and voice characteristics—through interactive evolutionary computation to enhance learners' motivation. Participants engaged in role- play scenarios across eight settings, providing feedback after each interaction. The agent's behavior was iteratively optimized, and approximately 90% of participants reported increased willingness to interact, suggesting that personalizing non-verbal behavior can significantly improve motivation in language learners.

Authors sometimes create narratives for the purpose of conveying the message (theme ). In addition, they often start with deciding the emotional genre (emotional impression), such as “sad story.” So far, our research group has defined a narrative discourse structure and has proposed the process for creating it from the theme and emotional impression. The process determines the order of deriving the elements in the discourse structure. However, some authors found difficult to derive them. This paper proposes a system for the step-by-step creation of the discourse structure along with the process by giving supports of deriving the elements.

Writing includes such elements of communication skills as expressing authorial intention in an understandable way that is acceptable to readers. Our research introduces a writing activity that cultivates communication skills by introducing a method for writing novels that are liked by the estimated target readers. An aspect of novels that may reflect individual preferences is the emotional experience produced by them. Therefore, this research proposes a method for creating novels that are liked by target readers from an emotional viewpoint. We first adopt story arcs as a representation of a reader model that expresses the emotional changes that readers are expected to experience from a novel. Second, we define the candidates of emotions for designing scenes from the viewpoint of the emotions of characters. Last, we develop a support system that not only suggests candidates for story arcs and characters’ emotions but also provides feedback when the emotions selected for characters fail to support the selected story arc.

We describe the effectiveness of interactive evolutionary computation (IEC) with tournament-style evaluation to reduce the evaluation load of IEC users. Most previous studies did not clearly demonstrate the effectiveness of the tournament-style evaluation. Therefore, we implemented a tournament-style evaluation for a specific application and inspected the effectiveness of the IEC with tournament-style evaluation using an experiment with real users. We used three evaluation objects: music, animation, and image. We evaluated the performance of the following three methods. The first was a normal IGA (NIGA), which is a conventional 10-stage evaluation. The second was a tournament-style evaluation with two levels (T2), which evaluates only the superiority or inferiority of two candidates at a time. The third was a tournament-style evaluation with four levels (T4), which progressively evaluates the superiority or inferiority of two candidates. We inspected the effectiveness of these methods by simulation using an evaluation agent that imitated human preferences (or Kansei). The simulation results showed that the evolution performances of the NIGA and T2 are higher than those of the T4. Also, we inspected the effectiveness of these methods by an evaluation experiment with 42 subjects in their 20s. The experiment results showed that the satisfaction level for generated candidates were approximately equal among the NIGA, T2, and T4. Moreover, with the T2, it was easiest for test subjects to evaluate solution candidates than with the NIGA in all evaluation objects. And with the T4, it was easier for test subjects to evaluate solution candidates when the evaluation objects were music and image than with the NIGA.

In this study, we improved the coloring support system that was proposed in our previous research. The previous system could advise color combinations for clothing. The user enters some emotional keywords, such as “casual” and “pretty,” which are impressions put forth by colors, and the system retrieves color combinations that seem to suit the keyword from a color database. The proposed system has many fuzzy color emotion models, which are controlled by parameters for defining membership functions or fuzzy rules. These models are evolved using interactive genetic algorithms, to adapt them to the user’s particular emotional responses, because human reactions vary for each individual. This paper proposes a method for the advanced evolution of the fuzzy color emotion model. This method supports co-evaluation of color combinations, which exhibits a better performance in evolving models compared to the previous method.

In this paper, we propose a system named "Virtual Stylist", which aims to help users find out their favorite clothes, which might fit them well. The system is composed of 3 parts as follows, 1) searching clothes in consideration of their color scheme harmonies and image sensations, 2) adopting rules for evaluating color scheme image sensations to a specific user's feeling of color images, 3) virtual fitting system. The system searches through clothes database for some clothes on the basis of the harmony and sensation of colors that are used in them. In the case that a user require a jacket and pants which she might wear with her own shirt, the system search for some jacket and pants whose colors are in harmony with the color of her shirt and with which the color scheme image sensation seems to fit her imagination of dressing. The system possesses some function so that the rules for evaluating color image sensations, which are controlled by some simple parameters are automatically changed and adjusted to the user's emotion. We achieved a way in which the system is real-time adapted to a user's subjectivity with interactive genetic algorithms.

Color design is very important for a product design. In this paper, we propose a system which aims to support such a color design. Proposed system is composed of 5 parts, such as the part which evaluates the harmony of colors, the color combining part, color scheme image judging part, image word output part and lastly image comparison part. First, the system requires the user to input a color and his preferring image of color scheme including his inputting color with image keyword. Next, the system selects colors from the Munsell color database, which are in harmony with the color inputted into the system. Then, the system builds color schemes to combine the color inputted by the user with the colors selected from the database by the system. Finally, images of the color schemes are evaluated and outputted the color combinations whose images accord with the image keyword which the user inputs into the system. Experimental result shows that effective judgments of color harmony and color image are executed and we can get some good color schemes by the system.