A data analytic approach to quantifying scientific impact

Predictive analysis of multiple future scientific impacts by embedding a heterogeneous network

Identifying promising research as early as possible is vital to determine which research deserves investment. Additionally, developing a technology for automatically predicting future research trends is necessary because of increasing digital publications and research fragmentation. In previous studies, many researchers have performed the prediction of scientific indices using specially designed features for each index. However, this does not capture real research trends. It is necessary to develop a more integrated method to capture actual research trends from various directions. Recent deep learning technology integrates different individual models and makes it easier to construct more general-purpose models. The purpose of this paper is to show the possibility of integrating multiple prediction models for scientific indices by network-based representation learning. This paper will conduct predictive analysis of multiple future scientific impacts by embedding a heterogeneous network and showing that a network embedding method is a promising tool for capturing and expressing scientific trends. Experimental results show that the multiple heterogeneous network embedding improved 1.6 points than a single citation network embedding. Experimental results show better results than baseline for the number of indices, including the author h-index, the journal impact factor (JIF), and the Nature Index after three years from publication. These results suggest that distributed representations of a heterogeneous network for scientific papers are the basis for the automatic prediction of scientific trends.

Multimodal ensemble approach to identify and rank top-k influential nodes of scholarly literature using Twitter network

Scholarly literature is an immense network of activities, linked via collaborations or information propagation. Analysing such network can be leveraged by harnessing rich semantic meaning of scholarly graph. Identifying and ranking top- k influential nodes from various domains of scholarly literature using social media data are still infancy. Social networking sites like Twitter provide an opportunity to create inventive graph-based measures to identify and rank influential nodes such as scholars, articles, journal, information spreading media and academic institutions of scholarly literature. Many network-based models such as centrality measures have been proposed to identify influential nodes. The empirical annotation shows that centrality measures for finding influential nodes are high in computational complexity. In addition, notion of these measures have high variance, which signifies an influential node deviation with change in application and nature of information flows in the network. The research aims to propose an ensemble learning approach based on multimodal majority voting influence (MMMVI) to identify and weighted multimodal ensemble average influence (WMMEAI) to rank top- k influential nodes in Twitter network data set of well-known three influential nodes, that is, academic institution, scholar and journal. The empirical analysis has been accomplished to learn practicability and efficiency of the proposed approaches when compared with state-of-the-art approaches. The experimental result shows that the ensemble approach using surface learning models (SLMs) can lead to better identification and ranking of influential nodes with low computational complexity.