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

2026-05-13

AI Summary

This study investigates how AI-driven predictions in menstrual cycle tracking applications reshape users’ perceptions of their physical and mental states, revealing a bidirectional co-constitution between humans and technology. Drawing on 14 semi-structured interviews and group autoethnography, and grounded in human-computer interaction (HCI) and science and technology studies (STS) frameworks, the research finds that users often internalize inaccurate AI predictions as authentic bodily experiences. Current interface designs largely lack features that support reflective cognition, thereby exacerbating feelings of isolation among non-normative users. The work offers the first systematic account of the mutual constitution between algorithmic prediction and subjective experience and proposes interaction design strategies to foster critical user engagement with predictive systems.

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.

Problem

• menstrual cycle tracking apps
• AI predictions
• lived experiences
• human-AI entanglement
• user experience

Innovation

• human-AI entanglement
• menstrual cycle tracking apps
• predictive AI
• lived experience
• AI explanations