There has been considerable overlap between the fields of information retrieval
and machine learning. In the 1960s, relevance feedback was introduced as a technique
to improve ranking based on user feedback about the relevance of documents in an initial ranking. This was an example of a simple machine-learning
algorithm that built a classifier to separate relevant from non-relevant documents
based on training data. In the 1980s and 1990s, information retrieval researchers
used machine learning approaches to learn ranking algorithms based on user feedback.