Large scale archives of text content are increasingly becoming available. Exploring their contents which evolve with the
time by leveraging the temporal dimension enables us to realize their full potential. Recently, there has been some work
in this regard, in which a notion of “time-travel keyword queries” is proposed. Time-travel keyword queries are realized
by enhancing the standard keyword query model for text content with a temporal context of interest. Unfortunately, this
approach requires users to specify temporal context for the keywords the user wants to search. If the user does not know
the history of the topic, he will be overwhelmed by the enormity of information which might span over a large time
range. In this work, we assist the user by (1) identifying interesting time-points and (2) ranking them where the
archive contents show significant change.