Source: wikibot/surprisal-analysis
= Surprisal analysis
{wiki=Surprisal_analysis}
Surprisal analysis is a concept rooted in information theory, primarily developed by Claude Shannon. It measures the amount of information or "surprise" associated with the occurrence of a particular event, which is based on the probability of that event. The basic idea is that events that have low probability are more surprising when they occur than events that are highly probable.