Co-occurrence analysis of scientific documents in citation networks

Suresh Kumar, Ch. Vidyadhari, R. Ganeshan. Infgraph: Influential Researcher and Cited Research Analysis Using Citation Network

The understanding of references in research articles is essential for performing effectual research. This paper devises a hybrid model to find the influential cited paper and influential researchers from Web of Science (WOS) data. For determining the influential researcher, a series of steps is performed. Then the co-citation is performed for providing author-author co-relation that predicts the next co-author. Thereafter, visualization of the network is performed for research communication amongst different authors. Then, the network density is computed. Finally, the cluster coefficient is adapted for finding the influential researcher. Concurrently, for discovering influential cited papers, the pre-processing is performed using the stop word removal and stemming process. Then, the word2vec model is utilized for training the model to forecast the suitable word that comes next. Finally, the modified word mover's distance (MWMD) is utilized for determining the semantic similarity in order to discover influential cited papers.

An approach for bibliographic citation sentiment analysis using deep learning

Sentiment analysis of scientific citations is a novel and remarkable research area. Most of the work on opinion or sentiment analysis has been suggested on social platforms such as Blogs, Twitter, and Facebook. Nevertheless, when it comes to recognizing sentiments from scientific citation papers, investigators used to face difficulties due to the implied and unseen natures of sentiments or opinions. As the citation references are reflected implicitly positive in opinion, famous ranking and indexing prototypes frequently disregard the sentiment existence while citing. Hence, in the proposed framework the paper emphasizes the issue of classifying positive and negative polarity of reference sentiments in scientific research papers. First, the paper scraps the PDF articles from arxiv.org under the computer science group consisting of articles that are comprised of ‘autism’ in their title, then the paper extracted cited references and assigns polarity scores to each cited reference. The paper uses a supervised classifier with a combination of significant feature sets and compared the performance of the models. Experimental results show that a combined CNN-LSTM deep neural network model results in 85% of accuracy while traditional models result in less accuracy.