Interest prediction in social networks based on Markov chain modeling on clustered users

Abstract

SUMMARYEffective user interest prediction is significant for service providers in a set of application scenarios such as user behavior analysis and resource recommendation. However, existing approaches are either incomplete or proprietary. In this paper, user interest prediction based on the Markov chain modeling on clustered users is proposed with the following procedure: collect dataset from 4613 users and more than 16 million messages from Sina Weibo; obtain each user's interest eigenvalue sequence and establish single-Markov chain model; and implement user clustering algorithm for the multi-Markov chain construction in order to divide users into a set of predefined interest categories. The proposed solution is capable of predicting both long-term and short-term user interests based on a suitable selection of the initial state distribution, λ. The proposed solution also proves that short-term interests are consistent with long-term interests if the influences of social or user-related events that cause interruptions (e.g., earthquake and birthday) are not considered. Furthermore, experiments show that the proposed solution is feasible and efficient and can achieve a higher accuracy of prediction than that of the other approaches such as Support Vector Machine (SVM) and K-means.

Using improved support vector regression to predict the transmitted energy consumption data by distributed wireless sensor network

“…With respect to the prediction model, machine learning methods were widely used in this field [31][32][33]. It was confirmed that the boosting and ensemble algorithms have superior performance in prediction field [34], but large dataset was required for those model learning, and it was not match to this work due to the collected dataset was insufficient. It is worth noting that the dataset in this work is high dimensional which was composed of electricity consumption and 40 climate factors, and SVR was recommended to perform the small-scale and high dimensional dataset.…”

Research on partitioning algorithm based on RDF graph

“…Initialization phase: Define a three-dimensional array S [C][N] [2] to store the vertices in each segmented subgraph and whether the vertex is accessed. Initially, the vertex's access flag is set to 0, and if it is accessed, it is modified to 1.…”

“…Graph is a ubiquitous data structure that is widely used in various fields. The keyword query based on RDF graph structure is currently a research hotspot; it allows users to obtain efficient query results without any complex structure query language, and using graphs to represent RDF data can not only maintain the correlation information between the data but also cannot lose semantic information 1–4 . Therefore, the query processing of RDF data is usually transformed into a graph matching problem, that is, positioning the Steiner tree containing keywords on the RDF data graph 5 .…”

A Markovian analytical framework for public‐safety video sharing by device‐to‐device communications

“…Due to memoryless properties, Markovian model is a widely used tool for the analysis of large‐scale systems . Markovian model has already been applied to characterize user mobility in simulation of large‐scale scenarios with traditional circle coverage base stations .…”