Because of the rapid spread of Internet, it has become an important tool for human life. Since the range of information on Internet is wide, the amount of information for searching academic papers becomes very large. To create an information system for quickly searching relative knowledge is essential. Most clustering algorithms used for association rules between words are hierarchical clustering. Therefore, in this thesis, we use a robust possibilistic clustering method for achieving better association rules between words. In this study, there are 60 papers retrieved from a website as samples for experimental comparisons. We find that the inferred association rules using our method are indeed with better results.