2023 Fiscal Year Research-status Report
A study into the use of Extended Concept Maps and Speech Recognition to improve lower-order language skills and higher-order thinking skills for language learners in Japan
| Project/Area Number |
22K00760
|
|---|
| Research Institution | Kanazawa University |
|---|
Principal Investigator |
Gary Ross 金沢大学, 薬学系, 准教授 (10708142)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
ヘネベリー スティーヴン 島根県立大学, 国際関係学部, 教授 (30405477)
ヨーク ジェームズ 明治大学, 政治経済学部, 専任講師 (90774498)
|
|---|
| Project Period (FY) |
2022-04-01 – 2026-03-31
|
| Keywords | speech recognition / Large Language Models / ChatGPT / AI / chatbot |
|---|
| Outline of Annual Research Achievements |
Since the initiation of this project, the rapid advancement of AI technologies has prompted a slight expansion in our goals. Integration of AI Large Language Models with Concept Maps. Specifically, we have explored the application of Concept Maps to model interactions between pharmacy students and various aspects of lifestyle, medicine, and health. Our efforts have yielded successful results in several key areas:
Speech Recognition Integration: We have successfully implemented a speech recognition interface that works in conjunction with AI chatbots. This setup enables a detailed analysis of the complex interactions between patient needs, societal demands, and professional responses.
Enhanced Learning Experiences: By utilizing speech-synthesized AI chatbots, students engaged in simulated interactions that mirror real-world scenarios. This approach has proven effective in providing practical experiences, fostering a deeper understanding of patient-professional dynamics.
These achievements underscore the potential of combining AI with Concept Maps to enhance the learning and analytical capabilities of pharmacy students, paving the way for more innovative educational methodologies. Additionally, this approach can be adapted to address other complex problems beyond the medical field, offering valuable insights and practical applications in areas such as environmental science, engineering, and social sciences.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
Project Overview: This research project has made significant strides in integrating advancements in AI language models with Extended Concept Maps (ECMs). These enhancements have positively impacted our objectives and outcomes across several key areas.
Achievement of Objectives: The integration of AI Large Language Models has been successfully implemented, enabling more sophisticated and nuanced interactions within the ECMs. This has improved the accuracy and responsiveness of speech recognition interfaces and AI-driven chatbots, facilitating better analysis and learning experiences.
Innovative Applications: By extending ECMs to interdisciplinary fields such as medicine, we have broadened the scope and impact of our research.
Collaboration and User Engagement: Development of collaborative platforms has allowed for real-time interaction with ECMs, fostering greater collaboration. User feedback has been integral in continuously improving the functionality and user experience of the ECMs.
Conclusion: The project has successfully integrated cutting-edge AI advancements.
|
| Strategy for Future Research Activity |
Moving forward, the research will focus on:
Interdisciplinary Applications: We will extend Extended Concept Maps (ECMs) to fields like social sciences to analyze complex interactions and broaden our research's scope and impact.
Advanced AI Integration: We will refine the integration of AI Large Language Models with ECMs, improving AI-driven speech recognition interfaces and chatbots to handle sophisticated interactions and provide nuanced insights.
Collaborative Platforms: We aim to develop platforms for real-time interaction with ECMs, fostering greater collaboration among students, educators, and professionals.
Data Analytics and Feedback: We will use advanced data analytics and pilot studies to assess ECM effectiveness and collect user feedback to improve functionality and user experience.
|
| Causes of Carryover |
There was a small amount that was unused
|
