Association rule mining with fuzzy linguistic information based on attribute partial ordered structure

In many application domains, there is an urgent need for data owners to mine attribute associations hidden in linguistic conceptual knowledge. Numerous linguistically valued facts from the actual world have been modeled using the fuzzy linguistic approach. To solve the problem of association rule mining with fuzzy linguistic information, this paper proposes an association rule mining approach based on fuzzy linguistic attribute partial ordered structure diagram (FL-APOSD). First, complex relationships between linguistic values in association rule mining are represented by fuzzy linguistic association nodes and association paths via FL-APOSD. On this basis, the maximum frequent attribute set is mined from the FL-APOSD, and then the non-redundancy association rules are extracted. Second, to show the information hidden in the rules and help users to deeply understand the mining results, a fuzzy linguistic association rule visualization approach is proposed to convert the association rules into the FL-APOSD-based knowledge representation. Finally, experimental results on real-world datasets show the proposed approach's high efficiency, outperforming two relevant state-of-the-art approaches.