Problem
Research questions and friction points this paper is trying to address.
personalized recommendation
digital activity
user education
privacy awareness
AI transparency
A Pedagogically Demonstrative Model Visualizing the Pathway from Online Interactions to Personalized Recommendation
🤖 AI Summary
This study addresses the lack of user awareness regarding how digital footprints are translated into personalized recommendations. To bridge this gap, we propose a novel educational demonstration system that integrates a locally deployed large language model (LLM) with an interactive Sankey diagram. Methodologically, the local LLM generates user profiles, while a three-layer Sankey diagram visualizes the mapping pathways from raw data to recommendations, enabling interactive exploration to intuitively reveal underlying AI recommendation mechanisms. A pilot study demonstrates that the tool effectively helps users comprehend conceptual relationships and enhances their privacy awareness; however, it does not yet significantly alter their anticipated behaviors.
📝 Abstract
Personal digital activity increasingly shapes online experiences, yet few users have been educated regarding the processes transforming raw interactions into personalized suggestions. We developed an education artifact that illustratively simulates how AI leverages users' digital activities to shape online recommendations (e.g., ads). Our artifact processes users' digital activity using a locally-hosted LLM to generate user profiles of their inferred interests and personalized recommendations. A three-layered Sankey diagram maps data sources through inferred interests to personalized recommendations. Interactive filters enable users to explore how different combinations of data sources influence personalized outcomes. This paper describes the artifact and its educational value, and reports findings of a pilot think-aloud study with six young adults. We find that the artifact effectively taught participants the conceptual relationship between digital activities and personalized recommendations. While this did lead participants to develop privacy awareness, they anticipated minimal behavior change due to the perceived unavoidability of platform participation.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Large Language Model
Sankey Diagram
Personalized Recommendation
Interactive Visualization
Digital Activity
🔎 Similar Papers
No similar papers found.
