Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

In-Situ Mode: Generative AI-Driven Characters Transforming Art Engagement Through Anthropomorphic Narratives

Yongming Li, Hangyue Zhang, Andrea Yaoyun Cui, Zisong Ma, Yunpeng Song, Zhongmin Cai, Yun Huang

TL;DR

EyeSee, a system designed to engage users through anthropomorphic characters acting as a third-person narrator, a first-person creator, and first-person created objects, is presented across two sessions: Narrative and Recommendation.

Abstract

Art appreciation serves as a crucial medium for emotional communication and sociocultural dialogue. In the digital era, fostering deep user engagement on online art appreciation platforms remains a challenge. Leveraging generative AI technologies, we present EyeSee, a system designed to engage users through anthropomorphic characters. We implemented and evaluated three modes (Narrator, Artist, and In-Situ) acting as a third-person narrator, a first-person creator, and first-person created objects, respectively, across two sessions: Narrative and Recommendation. We conducted a within-subject study with 24 participants. In the Narrative session, we found that the In-Situ and Artist modes had higher aesthetic appeal than the Narrator mode, although the Artist mode showed lower perceived usability. Additionally, from the Narrative to Recommendation session, we found that user-perceived relatability and believability within each interaction mode were sustained, but the user-perceived consistency and stereotypicality changed. Our findings suggest novel implications for applying anthropomorphic in-situ narratives to other educational settings.

In-Situ Mode: Generative AI-Driven Characters Transforming Art Engagement Through Anthropomorphic Narratives

TL;DR

EyeSee, a system designed to engage users through anthropomorphic characters acting as a third-person narrator, a first-person creator, and first-person created objects, is presented across two sessions: Narrative and Recommendation.

Abstract

Art appreciation serves as a crucial medium for emotional communication and sociocultural dialogue. In the digital era, fostering deep user engagement on online art appreciation platforms remains a challenge. Leveraging generative AI technologies, we present EyeSee, a system designed to engage users through anthropomorphic characters. We implemented and evaluated three modes (Narrator, Artist, and In-Situ) acting as a third-person narrator, a first-person creator, and first-person created objects, respectively, across two sessions: Narrative and Recommendation. We conducted a within-subject study with 24 participants. In the Narrative session, we found that the In-Situ and Artist modes had higher aesthetic appeal than the Narrator mode, although the Artist mode showed lower perceived usability. Additionally, from the Narrative to Recommendation session, we found that user-perceived relatability and believability within each interaction mode were sustained, but the user-perceived consistency and stereotypicality changed. Our findings suggest novel implications for applying anthropomorphic in-situ narratives to other educational settings.
Paper Structure (33 sections, 10 figures, 4 tables)

This paper contains 33 sections, 10 figures, 4 tables.

Table of Contents

  1. INTRODUCTION
  2. Related Work
  3. Art Appreciation and Interactive Engagement
  4. LLM-enabled Anthropomorphism for Different Role-plays
  5. Multiple Characters' Perspectives in Art Appreciation Context
  6. EyeSee DESIGN AND IMPLEMENTATION
  7. EyeSee Interaction Design
  8. EyeSee Backend and Implementation
  9. Method
  10. Participants
  11. Experiment Materials and Tools
  12. Experiment Procedure
  13. Measures and Data Analysis
  14. Narrative Session
  15. From the Narrative to Recommendation Session
  16. ...and 18 more sections

Figures (10)

  • Figure 1: Narrative Interface Include (A1) AI Agent Character Selection Area, Including Narrator, Artist, and In-Situ Modes; (A2) Task Instruction Panel; (B1) Area of Interest Selection, with Buttons to Add, Remove, or Reset Selection Areas; (B2) Attention Area Display; (C1) Basic Metadata Information: Name, Style, Artist, and Year; (C2) Shortcuts for Art Appreciation Information: Describe, Describe + Analysis, Describe + Analysis + Interpret, and Judge; (C3) Free Question Query; and (D) Artwork Recommendations.
  • Figure 2: Recommendation Interface Include (D1) Recommended Artwork Display; (D2) Rating for Recommended Artworks; (E1) Recommendation Reasons; and (E2) Rating for Recommendation Reasons.
  • Figure 3: EyeSee framework include: (F1) Visual Thinking Strategies Method; (F2) Chain of Thought Method; (G1) Style-based Pipeline; (G2)Object-based Pipeline.
  • Figure 4: Experiment Materials
  • Figure 5: Experiment Procedure Includes Onboarding Session, Narrative Session, and Recommendation Session
  • ...and 5 more figures