Caesar AI Atlas

Reporting Bias

Caesar AI Atlas Definition

Reporting bias is the distortion that occurs when the frequency of information in available records does not reflect its real-world frequency. Models trained on reported data may therefore learn what people tend to document or discuss rather than what actually happens.

Other Definitions

Reporting Bias Source

The fact that the frequency with which people write about actions, outcomes, or properties is not a reflection of their real-world frequencies or the degree to which a property is characteristic of a class of individuals. Reporting bias can influence the composition of data that machine learning systems learn from. For example, in books, the word laughed is more prevalent than breathed. A machine learning model that estimates the relative frequency of laughing and breathing from a book corpus would probably determine that laughing is more common than breathing. See Fairness: Types of bias in Machine Learning Crash Course for more information.

Related Terms