Statistics-Data mining

Question 1:
What is the difference between supervised and unsupervised learning in data mining.
Question 2:
Given a dataset X consists of over one million entries of research papers published in business journals and
conferences. Among these entries, there are a good number of authors that have coauthor relationships.
a) Propose a method to efficiently mine a set of co-author relationships that are closely related (e.g. often coauthoring papers together.
b) What pattern evaluation measures would you apply to convincingly uncover close collaboration patterns
better than others.