In this paper, we propose a new analytical method to grasp the overall structure of the answer items by using the survey results in the field of tourism marketing. In other words, to clarify the behavior of tourists in the Izu Peninsula, we conducted a questionnaire survey to explore the possibility of regional cooperation among local governments, tourism-related industries, and tourists. And extracted statistically significant items by nonparametric tests for this survey. After narrowing down the target, we visualized the evaluation structure of the tourists using the text mining method. As a result, we were able to confirm the effectiveness of the approach method adopted this time and provide useful information to the consideration of the sightseeing measures which should be adopted in the future.
A questionnaire investigation is executed for the aged people who are living at Hachinohe city in Aomori Prefecture during June to September 2016 in order to ascertain the factors which are related with productive activity. In this paper, basic statistical analysis and multiple correspondence analysis are conducted. It was made clear that productive activity increases as the self-efficacy feeling increases. Further study on this should be examined.
Tourists from abroad are increasing rapidly in Japan. Kawazu town in Izu Peninsula is famous for its cherry trees. In the cherry blossom season, many tourists visit this town. The Kawazu Cherry Blossom Festival was carried out in February 2015. Our research investigation was performed during that period. In this paper, a questionnaire investigation is executed in order to clarify tourists’ behavior, and to seek the possibility of developing regional collaboration among local government, tourism related industry and visitors. In this research, we construct the model utilizing Bayesian Network and causal relationship is sequentially chained by the characteristics of travelers, an objective to visit Izu Peninsula in Japan and the main occasion to visit them. Sensitivity Analysis for “Main occasion to visit to Izu Peninsula” was conducted and 17 cases were analyzed. These are utilized for constructing a much more effective and useful tourism service. To confirm the findings by utilizing the new consecutive visiting records would be the future works to be investigated.
Cleft lip and/or palate is a congenital malformation at birth with the incidence of one in about 500 people in Japan. In this study, we have focused on a facial expression training for the patients with cleft lip and/or palate. For the purpose of motivating the patients to introduce a facial expression training, a framework has been proposed and it allows them to set up a facial expression. The patients can select a facial expression by themselves as they want to express using a facial expression synthesizing tool. A preliminary survey was conducted on 17 patients and a hypothesis was formed as a psychological process model for the patients with cleft lip and/or palate. An experiment was conducted on 20 patients to verify the hypothesis (patient psychological process model) and the hypothesis would possibly be appropriate.
This paper describes an interpretation support system for classification patterns based on the contents of learning results in deep learning with texts, and verified its effectiveness. It is well known that classification patterns by deep learning models are often difficult to interpret the reasons derived. The proposed system extracts the contents of learning results in deep learning with texts and provides seeds for interpretations of the patterns learned. Then, the system displays learned network structures so that anyone can easily understand learning results. In verification experiments to confirm the effectiveness of the system, based on the learning result of deep learning classifying sentences, test subjects were instructed to give meanings of classification patterns peculiar to each output. The results show that the test subjects who represent novice data scientists could understand the meanings of the classification patterns of deep learning with texts.