Journal of Knowledge & Health1735-577X13220180912Analysis of Drug Addicts Charasteristics Using a Hybrid Learning Approach506110.22100/jkh.v13i2.1942FAHodaORCID: 0000-0003-0080-2743Mashayekhi 1School of Computer Engineering, Shahrood University of Technology, Shahrood, Iran.. hmashayekhi@shahroodut.ac.irMehdiKhaksari 2201805222018071720180623Introduction: Refinement and targeting of addiction prevention and rehabilitation programs, will increase the efficiency of executing such programs. However, the role of learning and data mining methods are rarely studied in this area. The aim of this paper is to assess the performance of data mining methods in analysis, refinement and grouping of the community for targeting the programs.Methods: In this paper, first an analysis framework is introduced. The goal of this framework is indicating the features influencing behavior of the target community, and also deriving different groups from the target community along with specific characteristics of each group. This way, targeted programs can be executed in each group. The information of addicts referring to a number of Methadone maintenance treatment (MMT) centers in Shahrood, Iran are analyzed with a range of data mining techniques as guided by the proposed framework. To indicate the influential features, first the feature selection step (using a hybrid of correlation analysis, association rule mining and decision tree analysis) is performed. Next, the data is clustered considering the selected features. The result of clustering is extraction of different groups from the target community. Finally, a hybrid of association rule mining and decision tree algorithms are used to analyze data in each cluster and determine their characteristics.Results: The results show the effectiveness of the proposed approach in analysing and grouping the community. Specifically, we focus on the reason of referring to a MMT center and indicate influential features in this context. Next, leveraging the extracted features, we derived various groups from the target community and determine their characteristics by deriving rules. The confidence of the extracted rules is at least 84%.Conclusion: The results of this research insist on the significant role of the data mining techniques in improved execution of prevention and rehabilitation programs. Specifically, the relation of the addicts’ family and social conditions with the reason of referring to MMT centers, which are explored in the paper, can be effective in the treatment programs of drug addicts and prevention of similar people becoming a consumer.