Publikationen

This article describes our long-term research into automated story generation and our resulting story generation architecture called fAIble that incorporates several innovations. fAIble determines each event that occurs in the tale using a combination of scripted sequences and stochastically chosen events. The probability of an event occurring is based on the skills and personalities of the characters who have agency. Event selection is also influenced by the context of the situation faced by the characters. Each event is associated with a description in grammatically-correct natural language that can be narrated orally via text-to-speech. We describe the evolution of fAIble, its architecture and the results of our independent evaluation of each of the four progressively developed fAIble prototypes (fAIble 0, I, II and III), as tested with human test subjects. On a continuous scale where 0 means unacceptable, 1 means acceptable and 2 means optimal, the composite human test subject rating average from the independent tests of the prototypes was 0.933. The paper also describes a summative assessment where test subjects were asked to review stories from all four prototypes and rank them comparatively. These comparative results indicate an improvement from the original (fAIble 0) to the last one (fAIble III).

In this paper, we propose adding the traditional Japanese nodding behavior to the repertoire of social movements to be used in the context of human-robot interaction. Our approach is motivated by the notion that in many cultures, trust-building can be boosted by small body gestures. We discuss the integration of a robot capable of such movements within CRECA, our context-respectful counseling agent. The frequent nodding called "unazuki" in Japan, often accompanying the "un-un" sound (meaning "I agree") of Japanese onomatopoeia, underlines empathy and embodies unconditioned approval. We argue that unazuki creates more empathy and promotes longer conversation between the robotic counsellor and people. We set up an experiment involving ten subjects to verify these effects. Our quantitative evaluation is based on the classic metrics of utterance, adapted to support the Japanese language. Interactions featuring "unazuki" showed higher value of this metrics. Moreover, subjects assessed the counselling robot's trustworthiness and kindness as "very high" (Likert scale: 5.5 versus 3-4.5) showing the effect of social gestures in promoting empathetic dialogue to general people including the younger generation. Our findings support the importance of social movements when using robotized agents as a therapeutic tool aimed at improving emotional state and social interactions, with unambiguous evidence that embodiment can have a positive impact that warrants further exploration. The 3D printable design of our robot supports creating culture-specific libraries of social movements, adapting the gestural repertoire to different human cultures.

Unusual intense solar flares may cause serious calamities such as those damaging electric/nuclear power plants. It is thereupon highly demanded, but is quite difficult to predict intense solar flares due to the imbalanced character of the available data. To cope with this problem, we have herefore developed and applied a Case Based Genetic Algorithm (CBGALO) that contains a local optimizer, which is a Support Vector Machine (SVM). However, the prediction performance significantly depends on input data for learning. Hereupon, CBGALO is further extended by a Case Based automatically restartable Good combination searching GA for both learning features and input data (CBRsGcmbGA). Even the powerful but computationally expensive Deep Learning cannot automatically (evolutionarily, in our approach) search the learning data. Our approach solved this problem a little better by the case-based approach. However, it became obvious that even this work suffers from the typical GA effect in falling into local optima. To improve the results, we newly developed hence a diversity maintenance approach that inserts good individuals with large Hamming distance into the case base as elite individuals in GAs population. In 2 out of 3 classes of solar flares, the performance of our new approach became as high as the best ones among the conventional world top records. Namely, even in ≥ C class solar flares, our approach applying the Hamming distance to increase diversity had as high a performance 0.662 as compared with the conventional world top record 0.650.

Since marketing research on theme parks such as Tokyo Disney Land is costly, we developed an efficient opinion collection system. However, it is difficult for the interviewer to extract characteristic opinions from several opinions. To cope with this problem, we classify emotions for opinions based on the wheel of Plutchik. We further propose a method of displaying them on a map for visualization. The evaluation result by questionnaires is 4.75 on average out of 5 scales. The result shows that the proposed system can support the action of proposing business ideas.