Transaction Prediction in Blockchain: A Negative Link Prediction Algorithm Based on the Sentiment Analysis and Balance Theory

【Author】 Yuan, Ling; Bin, JiaLi; Wei, YinZhen; Hu, Zhihua; Sun, Ping

【Source】WIRELESS COMMUNICATIONS & MOBILE COMPUTING

【影响因子】2.146

【Abstract】User relationship prediction in the transaction of Blockchain is to predict whether a transaction will occur between two users in the future, which can be abstracted into the link prediction problem. The link prediction can be categorized into the positive one and the negative one. However, the existing negative link prediction algorithms mainly consider the number of negative user interactions and lack the full use of emotion characteristics in user interactions. To solve this problem, this paper proposes a negative link prediction algorithm based on the sentiment analysis and balance theory. Firstly, the user interaction matrix is constructed based on calculating the intensity of emotion polarity for social network texts, and a reliability weight matrix (noted as RW-matrix) is constructed based on the user interaction matrix to measure the reliability of negative links. Secondly, with the RW-matrix, a negative link prediction algorithm is proposed based on the structural balance theory by constructing negative link sample sets and extracting sample features. To evaluate the performance of the negative link prediction algorithm proposed, the variable management method is used to analyze the influence of negative sample control error and other parameters on the accuracy of it. Compared with the existing prediction benchmark algorithms, the experimental results demonstrate that the proposed negative link prediction algorithm can improve the accuracy of prediction significantly and deliver good performances.

【Keywords】

【发表时间】2021 44608

【收录时间】2022-01-02

【文献类型】

【主题类别】

--