System and method for determining temporal citation count

1. A system for determining a temporal citation count for a published document associated with an author, wherein the system comprises a database arrangement storing metadata related to the published document, and a server arrangement communicably coupled to the database arrangement, wherein the server arrangement:

receives the metadata associated with the published document;

employs dimensionality reduction techniques on the metadata associated with the published document to obtain a state data;

designates the author of the published document as a source node in an entity network comprising information related to a plurality of authors and citation history between the plurality of authors, wherein the remaining authors in the plurality of authors are designated as destination nodes;

determines an edge weight for edge between any of the source node and the destination nodes based on the state data and any of the source and destination nodes associated therewith; and

aggregates the edge weight for the edge between any of the source node and the destination nodes to obtain the temporal citation count associated with the published document.

2. The system of claim 1 , wherein the server arrangement uses an observed citation data having a temporal value, to update the entity network and distribution of nodes within the entity network.

3. The system of claim 2 , wherein the entity network and distribution of nodes within the entity network is updated using a backpropagation algorithm.

4. The system of claim 1 , wherein the dimensionality reduction techniques are executed via an autoencoder module, wherein the autoencoder module is trained using a variational inference algorithm.

5. The system of claim 1 , wherein the metadata related to the published document includes: title of the published document, abstract of the published document, domain of the published document, keywords associated with the published document, date of publication, authors of the published document.

6. The system of claim 1 , wherein the entity network is a graph neural network.

7. The system of claim 2 , wherein the entity network is optimized using message passing protocol and Adam Optimizer Protocol.

8. The system of claim 1 , wherein the temporal citation count is represented on a citation-time graph.

9. The system of claim 8 , wherein the citation time graph includes a credible interval.

10. A method of determining a temporal citation count for a published document associated with an author, the method comprises:

receiving a metadata associated with the published document, wherein the metadata associated with the published document is stored in a database arrangement;

employing dimensionality reduction techniques on the metadata associated with the published document to obtain a state data;

designating the author of the published document as a source node in an entity network comprising information related to a plurality of authors and citation history between the plurality of authors, wherein the remaining authors in the plurality of authors as destination nodes;

determining an edge weight for edge between any of the source node and the destination nodes based on the state data and any of the source and destination nodes associated therewith; and

aggregating the edge weight for the edge between any of the source node and the destination nodes to obtain the temporal citation count associated with the published document.

11. A method of claim 10 , wherein the method includes using an observed citation data having a temporal value, to update the entity network and distribution of nodes within the entity network.

12. A method of claim 11 , wherein the method includes updating the entity network and distribution of nodes within the entity network using a backpropagation algorithm.

13. A method of claim 10 , wherein the method includes executing the dimensionality reduction techniques via an autoencoder module, wherein the autoencoder module is trained using a variational inference algorithm.

14. A method of claim 10 , wherein the metadata related to the published document includes: title of the published document, abstract of the published document, domain of the published document, keywords associated with the published document, date of publication, authors of the published document.

15. A method of claim 10 , wherein the entity network is a graph neural network.

16. A method of claim 10 , wherein the method includes optimizing the entity network using messaging passing protocol and Adam Optimizer Protocol.

17. A method of claim 10 , wherein the method includes representing the temporal citation count on a citation-time graph.