With　the　development　of　network,　web　forensics　is　becoming　more　and　more　important　due　to　the　rampant　cybercrime.　In　this　paper,　a　forensics　method　of　web　browsing　behavior　based　on　association　rule　mining　is　presented.　The　method　aims　at　providing　the　necessary　data　support　to　build　the　behavior　pattern　library　for　investigation.　The　records　of　the　user＇s　browsing　history　are　collected　to　be　analyzed.　The　obtained　original　data　are　pretreated　to　transactional　data　which　are　suitable　for　association　rule　mining.　Frequent　browsing　time　and　frequent　web　browsing　sequences　are　obtained　from　the　transactional　data　by　Apriori　algorithm.　The　mining　results　are　helpful　for　identification　and　recognition　of　anonymous　or　suspicious　web　browsing　behavior　patterns.　©　2014　IEEE.