An Analysis of Structural Properties in Social Network Links in Educational Data Mining

Social Network Link Analysis is the interaction between the vertices or nodes in the network. These interactions are could be career guidance, common interest, career opportunities; the spark of exchange of interaction becomes belief and knowledge. The interaction becomes complex in the process of time series. To analyze the social network that resulted from these interactions is modeled as a graph structure; it consists of nodes and edges. Various data mining techniques to extract useful information from vast data and support to decide various aspects. It is a dire need of a machine-learning algorithm to assist the knowledge of data mining; we proposed career guidance link analysis in the online social network. In this How students to select the institutions based on the location for their carrier. The proposed study is to evaluate and analyze location-based parameters such as distance, centrality values between the nodes, and residual factors of the parameters. In this paper, we collect the student's data and apply K-Means algorithms using R programming for predicting the ties between the nodes and similarity between the users to make the strong cohesion group. The collected data is categorized using Naïve Bayes classification, and the categorized values are validated 26.4% of students had been accepted the career guidance level, behavioral traits, and organizational traits yielded 38.78 %. Career guidance ties are diffused to 26.3% of Higher education students to choose the choice of institutions. The experimental study of the higher education data results yielded 96.78% accuracy establish to propagate the influence of links to students for the career guidance path.