Provided is a method and system for detecting a graph-based event in a social network, the method including generating a keyword graph based on social data collected from a social network system; separating the keyword graph into a plurality of candidate graphs through clustering; calculating a user interest for each of the plurality of candidate graphs based on a per-time variation of a social action associated with the social data; and determining k candidate graphs from among the plurality of candidate graphs as an event graph based on the user interest. Here, k denotes a natural number.