Introduction to Microsoft Copilot Usage
Microsoft Copilot, an AI chatbot, has been analyzed based on 37.5 million conversations between January and September. The analysis focuses on how people use Copilot depending on their device and time of day. The researchers used machine-based classifiers to categorize conversations by topic and intent without human review.
Device-Specific Usage Patterns
The study reveals distinct usage patterns on mobile devices versus desktops. On mobile, health and fitness is the most common topic throughout the day. Users seek information and advice on health-related matters consistently across every hour and month. In contrast, desktop usage follows a different rhythm, with technology leading as the top topic overall.
Desktop Usage Patterns
During business hours (8 a.m. to 5 p.m.), work-related conversations rise, and "Work and Career" overtakes "Technology" as the top topic on desktop. Education and science topics also increase during business hours compared to nighttime. Outside business hours, there is a shift toward more personal and reflective topics, such as "Religion and Philosophy," which rises in rank during late-night hours through dawn.
Time-Based Usage Patterns
The study also identifies time-based usage patterns. Programming conversations are more common on weekdays, while gaming rises on weekends. Additionally, there is a spike in relationship conversations on Valentine’s Day. These patterns suggest that the use of AI chatbots varies with context, and device and time of day shape what people ask for and how they ask it.
Methodology and Limitations
The study has some limitations, as it is a preprint and hasn’t been peer-reviewed. It focuses on consumer Copilot usage and excludes enterprise-authenticated traffic, so it doesn’t describe how Copilot is used inside Microsoft 365 at work. The topic and intent labels come from automated classifiers, which means the results reflect how Microsoft’s system groups conversations, not a human-coded review.
Why the Findings Matter
The study suggests that AI chatbot usage is not uniform and depends on the context in which it is used. The researchers connect the mobile health pattern to how people use their phones, writing: "This suggests a device-specific usage pattern where the phone serves as a constant confidant for physical well-being, regardless of the user’s schedule." The findings have implications for understanding how people interact with AI chatbots and how these interactions vary across devices and time.
Looking Ahead
Future research could explore enterprise usage patterns, especially inside Microsoft 365, to clarify how broadly these findings apply. Validating these patterns outside Microsoft’s own tooling and taxonomy would also provide valuable insights. By examining how people use AI chatbots in different contexts, researchers can gain a deeper understanding of the complex interactions between humans and AI systems.
Conclusion
The study of Microsoft Copilot usage patterns reveals that device and time of day significantly influence how people interact with AI chatbots. The findings highlight the importance of considering context in understanding human-AI interactions. As AI chatbots become increasingly integrated into daily life, understanding these usage patterns will be crucial for developing effective and user-friendly AI systems. By recognizing the variations in AI chatbot usage, developers can create more tailored and responsive AI systems that meet the diverse needs of users.