Contents
This presentation introduces data-driven approaches for prioritizing improvements to technical documentation. By combining user feedback and web analytics, we’ll explore methods such as correlation analysis, linear regression, and random forest modeling to pinpoint what truly drives the ratings of documentation topics. You'll get a quick overview on what kind of data to aggregate and how to apply data science techniques to identify and predict which topics should be targeted for improvement. Practical examples will showcase how to prioritize topics with poor feedback and high engagement for the best impact on user satisfaction.
Takeaways
Data science techniques like linear regression and random forests empower us to make informed decisions as part of a content transformation stategy.
Prior knowledge
Basic understanding of web analytics (e.g., page views, bounce rates).
Familiarity with the concept of user feedback and how it impacts documentation.
No prior experience with data science techniques like linear regression or random forests is necessary, but a general interest in data-driven approaches will help.