A fuzzy intelligent group recommender method in sparse-data environments based on multi-agent negotiation

Recommender systems have attracted numerous scholars’ attention. Group recommender is a fashionable though challenging topic in the field of recommender systems. Most methods using aggregation technique performs poorly when conflict exists in members’ preferences. The group recommender method based on multi-agent negotiation covers this limitation. However, existing works ignore the imperfect rationality of members during negotiation. To cover up this deficiency, we propose a fuzzy intelligent group recommender method based on multi-agent negotiation. A new concession protocol makes some compensations to the transigent member considering his imperfect rationality. In this work, the dependency structure analysis is introduced to classify opinion terms into aspects, and the fuzzy numbers are introduced to characterize a maze of contradictory opinion terms in textual reviews. Moreover, a new user similarity method is established using normal cloud models. It tackles the problem of sparse data. In addition, a case study on data in is conducted. Its results indicate the good performance of the proposed group recommender method.