Reading Between the Lines: Scalable User Feedback via Implicit Sentiment in Developer Prompts
This provides a scalable, practical approach to complement existing feedback channels for understanding developer experience, though it is incremental as it builds on existing sentiment analysis techniques.
The paper tackled the challenge of evaluating developer satisfaction with conversational AI assistants at scale by proposing sentiment analysis of developer prompts as a method to identify implicit signals, showing it detects a signal in ~8% of interactions, which is over 13 times higher than explicit feedback rates.
Evaluating developer satisfaction with conversational AI assistants at scale is critical but challenging. User studies provide rich insights, but are unscalable, while large-scale quantitative signals from logs or in-product ratings are often too shallow or sparse to be reliable. To address this gap, we propose and evaluate a new approach: using sentiment analysis of developer prompts to identify implicit signals of user satisfaction. With an analysis of industrial usage logs of 372 professional developers, we show that this approach can identify a signal in ~8% of all interactions, a rate more than 13 times higher than explicit user feedback, with reasonable accuracy even with an off-the-shelf sentiment analysis approach. This new practical approach to complement existing feedback channels would open up new directions for building a more comprehensive understanding of the developer experience at scale.