Study on a multimodal psychological state estimation robust to tourist attribute differences and environmental noises

2020 Fiscal Year Final Research Report

• Project/Area Number: 19K24345
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Multi-year Fund
• Review Section: 1001:Information science, computer engineering, and related fields
• Research Institution: Nara Institute of Science and Technology
• Principal Investigator: Matsuda Yuki 奈良先端科学技術大学院大学, 先端科学技術研究科, 助教 (90809708)
• Project Period (FY): 2019-08-30 – 2021-03-31
• Keywords: 心理状態推定 / 感情認識 / 満足度推定 / 観光 / スマートシティ / ウェアラブルコンピューティング / ユビキタスコンピューティング / IoT

Outline of Final Research Achievements

Through a statistical analysis of data obtained from subjects of multiple nationalities, it was clarified that the method of estimating the psychological state of tourists based on their unconscious behavior during sightseeing is affected by their attributes (nationality in this study). Furthermore, through the analysis of the importance of the cues (features), we found that environmental factors (temperature, humidity, and air pressure) contribute to the estimation of the psychological state. Finally, we built a new model for estimating the psychological state of tourists that takes these factors into account. This model was evaluated by collecting data from 24 people of various nationalities, and the results showed that the model could be estimated with the same accuracy as the previous results, i.e., the robustness was improved.

Free Research Field

ユビキタスコンピューティング

Academic Significance and Societal Importance of the Research Achievements

非常に測定が難しい観光中の観光客の心理状態を、IoT（ウェアラブルデバイスやスマートフォン）センサを用いることで推定する手法を構築したことは、今後ますます需要が高まると想定されるスマートツーリズムの実現に向けての重要な社会的意義を持つと考える。さらに本研究では、観光客の属性（特に、国籍）によって観光中の仕草が異なることから推定に影響をおよぼすことを実データによって明らかにするとともに、環境要因という新たな手がかりを推定モデルに加えることによる推定精度向上の可能性を示しており、これは学術的にも意義があると考える。