"It became a self-fulfilling prophecy": How Lived Experiences are Entangled with AI Predictions in Menstrual Cycle Tracking Apps

TL;DR

This study explores how AI predictions in menstrual cycle tracking apps influence users' perceptions of their experiences, revealing issues with understanding, interface support, and feelings of isolation.

Contribution

It provides empirical insights into human-AI entanglement in health apps and offers design implications for improving user engagement and understanding.

Findings

Users interpret their experiences through AI predictions despite inaccuracies.

Current interfaces do not facilitate critical engagement with AI explanations.

Non-normative users feel isolated in their entangled interactions.

Abstract

In menstrual cycle tracking apps (MCTAs), AI-based predictions and insights have become increasingly popular. These features enable users to receive personalized information about their bodies and mental states. However, there is currently little research on how these predictive AI features and explanations affect users' lived experiences. This paper examines human-AI entanglement in MCTAs through 14 semi-structured user interviews and a group autoethnography. These methods uncover the processes leading to this phenomenon. Our results reveal that: (1) users understand their lived experiences in light of AI predictions, although these predictions can be faulty due to imperfect logging practices, (2) the user interface features and AI explanations do not support awareness or critical engagement with this entanglement and meaning-making, and (3) non-normative MCTA users report a sense of isolation in this entangled interaction. Based on our findings, we propose design implications for predictive AI features and explanations.