Human-AI tools for accounting for differences across contexts

Human-AI tools for accounting for differences across contexts

Our project introduces an innovative AI system designed to adeptly translate different human experiences and cultural contexts into machine-understandable formats, addressing a critical gap in current context-aware computing. The core to this system are differentiated AI models which enable interpretation of various contexts across different geographical and cultural settings. The system will have a user-friendly interface, facilitating easy input and interpretation of data by context-awareness service designers. Its effectiveness is empirically validated through a detailed case study on the concept of 'Where to Sunbathe' in contrasting locales of Florida and Pennsylvania, demonstrating its proficiency in accurately identifying and differentiating contextually relevant categories. This project is proposed to revolutionize context-aware AI tool design, enhancing user experiences and applications across diverse cultural and social backgrounds by bridging the complex area of cultural contexts with the precision of AI analysis.

Human-AI tools for accounting for differences across contexts image 1

Figure 1: Example 1

Human-AI tools for accounting for differences across contexts image 2

Figure 2: Example 2

Human-AI tools for accounting for differences across contexts image 3

Figure 3: Figure 1: Categories in FL related to ’Where to Sunbathe’

Human-AI tools for accounting for differences across contexts image 4

Figure 4: Figure 2: Categories in PA related to ’Where to Sunbathe’

Human-AI tools for accounting for differences across contexts image 5

Figure 5: Figure 3: Comparative Analysis of TF-IDF Scores by Category to ’Where to Sunbathe’ in FL and PA

Team

Faculty

  • None

Ph.D. Students

  • None

Masters and Undergraduate Students

  • Jiayi Zheng
  • Yiran Mo
  • Suhuai Chen