Understanding how users adopt new technology is crucial for success in today's fast-paced digital landscape. Traditionally, expensive and time-consuming surveys have been the primary tool for gauging user sentiment. However, a groundbreaking new approach is emerging, leveraging the power of Large Language Models (LLMs) like those behind ChatGPT. Imagine analyzing mountains of user reviews and online comments effortlessly, extracting valuable insights into what makes a product a hit or a miss. This is the promise of LLM annotation systems. These systems can transform unstructured text data, such as online reviews, into structured data based on established technology acceptance models like the Unified Theory of Acceptance and Use of Technology (UTAUT). Our research explored the effectiveness of these LLM systems, and the results are striking. We found that LLMs demonstrated moderate to strong consistency in their analysis, meaning they reliably produce similar interpretations across multiple runs. Even more impressive, the LLMs' agreement with human expert annotations was remarkably high, often exceeding the agreement between human experts themselves! This suggests that AI can not only streamline the analysis process but also offer a level of consistency that surpasses traditional human-centric approaches. This opens exciting new possibilities for researchers and product developers. Imagine being able to rapidly analyze vast amounts of user feedback, gaining real-time insights into user preferences and pain points. This information can then be used to inform product design, improve user experience, and ultimately increase technology adoption. While there are still challenges to overcome, such as refining prompt engineering and addressing ethical considerations, the potential of LLM annotation systems is immense. As these systems mature, we can expect them to become an indispensable tool for understanding user behavior, paving the way for more human-centered technology in the future.