{"title":"Fraud-Tolerant Measurement of User Contribution in Online Forum","authors":"Guoying Wang, Jiyu Cheng","doi":"10.1109/WISM.2010.157","DOIUrl":null,"url":null,"abstract":"Because all contents in online forums are provided by users, it’s important to reward the contributive users, and the rewards should be proportional to the contributions. So the determination of user contributions is needed in online forums. On the other hand, some users may do some fake contributions for more reward. In this paper, we analyzed possible frauds in online forum, examined the features of each kind of fraud, and proposed some fraud-tolerant parameters according features of frauds. Based on this, frauds of user contributions can be discriminated, and user contributions can be measured quantitatively and fraud-tolerantly, which provides a basis for forums to reward users in various ways. The result of experiment shows that 81% users in an online forum have fraudulent activities and pure advertising users can be discovered according to the fraud-tolerant parameters we considered.","PeriodicalId":119569,"journal":{"name":"2010 International Conference on Web Information Systems and Mining","volume":"84 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 International Conference on Web Information Systems and Mining","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WISM.2010.157","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
Because all contents in online forums are provided by users, it’s important to reward the contributive users, and the rewards should be proportional to the contributions. So the determination of user contributions is needed in online forums. On the other hand, some users may do some fake contributions for more reward. In this paper, we analyzed possible frauds in online forum, examined the features of each kind of fraud, and proposed some fraud-tolerant parameters according features of frauds. Based on this, frauds of user contributions can be discriminated, and user contributions can be measured quantitatively and fraud-tolerantly, which provides a basis for forums to reward users in various ways. The result of experiment shows that 81% users in an online forum have fraudulent activities and pure advertising users can be discovered according to the fraud-tolerant parameters we considered.