Research On Spam Filter Based On Social Computing

With Internet growing rapidly,E-mail has become one of the most convenient communication methods.However,at the same time,more and more spam taking up huge transmission,storage and computation resources impacts the network seriously.Since most of the traditional spam filtering approaches only takes single user termination into consideration,it leads to the waste of spam information.Besides,the deployed spam filtering system also doesn't care the user's individual interest,which results in the lack of personalization.In this paper,we firstly concludes the conception of spam,traditional spam filtering approaches,social computing,social network,collective intelligence and the application of social computing and collective intelligence.Besides,we introduce and analyze the related researches and finger out their disadvantages.Secondly,we propose a spam filtering approach in which a collaborative and personalized spam filter based on social network is developed.The key idea is to enable users to push spam reports to their social network friends with similar interest,which reflects collaboration and personalization.Our proposal takes advantage of push technology to share user's individual spam knowledge with others via social network,which utilizes wisdom of crowds to resist spam.Different users may have different views on judging spam which makes it difficult to filter spam from normal emails for email server.We found users with similar interest may have similar opinions.According to interest similarity among users,a user can determine whether to push spam reports to his friends with the purpose of taking user's individual interest into consideration.We use interest similarity to measure the similarity level between users and give an introduction of computing interest similarity.Due to decentralization,we need to store some information in local user host so that we introduce the structure of local information table.We integrate an interest-based spam filter with a basic Bayesian filter to discriminate spam from legitimate emails.Finally,we establish the social network according to the real social network data online,and deploy our system on it to conduct the evaluation.The result shows it significantly improves the performance compared with Bayesian filter according to the accuracy rate.Besides,we evaluate our system under different social networks,interest similarity thresholds,average number of social network friends,receiving ratio of spam reports and push mechanism to find the appropriate parameters to make our system perform better.