Eeti Jain

Background

About Eeti Jain

I have submitted my Ph D. thesis in Complex/ Social Networks as wide area and Opinion Dynamics in Temporal Networks as narrow area. Implemented Machine learning techniques in the social graphs. Good hold at Probability and Statistics (Random variables, CDF, PDF, Distributions, Stochastic process, Markov Chain ) Research Area: Machine Learning, Complex Networks (BA Model, ER model)(Degree Distribution, Modularity, Clustering Coefficient), Dynamics on and of the network, Graph Theory. Implemented Models: 1. Classifying nodes as influential in a network: Nodes are classified as influential nodes on the basis of parameters. Further, logistic regression is applied to identify influential nodes. Changing trends on the social networks with the influential people: The effect of influential people in the social networks is spread to change the trend in any real time application such as, marketing, politics, etc. Predicting opinion convergence values: Linear Regression is used to predict the convergence of opinion evolution models based on parameters. Probabilistic Models: Network is updated on the basis of Bayes theorem giving a probabilistic updation. User Profiling: People are recommended the products according to what their acquaintances have ordered in the past representing Knowledge Graphs. Trust and Reputation based recommended opinion evolution model: Opinions are evolved according to the dynamic trust and reputation among the people in the social network. Previously calculated Trust and Reputation values are used to recommend the people from whom to share the opinion values using Markov Chain. Clustering people in temporal networks using Node Embedding: A model is developed to cluster the people according to the same opinion values or the structure of the temporal network. It is analyzed how opinions are getting evolved on the social networks. Analyzing the effect of common neighbours on clustering people: Edges among the people are added by connecting the common neighbours among them in the social network. It is analyzed how the increased common neighbour connections (Triad connections) are affecting the clusters of people.