Inference network building and movements prediction based on analysis of induced dependencies

Abstract

State prediction of a node is made through analyses of adjacent nodes to learn about movements and to manage users in inference network. This study first simplifies ego network to reduce the complexity of structural analyses based on three different relationships among users. Second, degrees of mutual influences are computed according to different forms of association. Finally, the action of the centre node is predicted by analysing the changing of the states of adjacent nodes. The experiment proves that accuracy and efficiency of the algorithm proposed performs well not only in the simplification of ego network but also in the prediction of movements.

Overlapping Community Detection Based on Strong Tie Detection and Non-Overlapping Link Clustering

“…(1) INB [11] is a method based on the analysis of induced dependencies to build an inference network. (2) RNM [18] is a local expansion method based on rough neighbourhood.…”

“…Node-based methods [10][11][12] envisage that the strong ties are formed between nodes when there is a high probability of forming triads through diferent types of relationships. Notice that nodes belong to multiple groups, but links are existent for just one dominant reason (e.g., two people linked work together or have common interests), which means that links that occupy unique clusters and nodes naturally account for multiple clusters as a result of their links.…”

Measure User Intimacy by Mining Maximum Information Transmission Paths

“…ere are more than 2 million active users on Facebook every month from all over the world and about 5 billion new tweets on Twitter every day. Social network analysis can be divided into the following aspects [1,2]: (a) studying the network structure and trends [3], (b) online learning of complex networks [4], (c) comparing different models, and (d) predicting node status [1,5]. e focus of social influence study is to investigate neighbors and associations to predict the impact and influence of the occurrence of an action [2,6].…”

“…According to formulas (5) and (6), the degree of intimacy between different users is calculated. e specific algorithm is shown in Algorithm 1.…”

EC‐Structure: Establishing Consumption Structure through Mining E‐Commerce Data to Discover Consumption Upgrade

“…Regarding the characteristics of uses, Curme [5], Chattopadhyay [8], and Guo [9] analyze user behaviors from the perspective of complex systems and extract implicit semantic information from large-scale semistructured data. Glass [10], Singh [11], and Aviano [12] find personal characteristics through the feature extraction of original website data, mine important features of users using to feature selection methods, and finally extract a user profile model.…”