Table of Contents
Peer Reviewers App is a web application that uses AI knowledge extraction to perform document similarity to help recommend peer reviewers for academic and scholarly journals and articles. A possible peer reviewer for a submitted scholarly article or paper is a researcher or academic with experience in the research area of the submitted research paper. Using knowledge extraction and document similarity we can compare research papers of academics to determine possible reviewers.
The inspiration for this project is based on a university project I worked on where I used the Bag of Words approach to search indexed documents in a search store. In this application we take advantage of Expert AI Keyphrase API to extract key phrases from submitted research papers, the topics and main sentences are used to build an intelligent query to retrieve the best matching document from a document store built using Azure Cognitive Services.
You can view the demo here
You can try the live application here Live site using these research papers from the demo Test Papers
To run the application locally, please follow the steps below.
- Clone the repo
- Create a developer account at Expert AI
- Create a free Azure Account at Azure or use an existing one.
- Create a free Azure Cognitive Search (Free Tier) resource and index these research papers. You can do that by following the tutorial here. For this project we used 15 unique research papers in various fields in computer science. The details of the research papers are managed in memory. The details can be moved to a database or any persistent storage if prefered.
- Update
appsettings.json
{
"Logging": {
"LogLevel": {
"Default": "Information",
"Microsoft": "Warning",
"Microsoft.Hosting.Lifetime": "Information"
}
},
"AllowedHosts": "*",
"AzureCognitive": {
"Endpoint": "<your azure search endpoint>",
"ApiKey": "<your azure search api key>",
"ApiVersion": "<your azure search api version>",
"Index": "<your azure search index>",
"Docblob": "<the url to the public blob from your tutorial in pt.4>"
},
"ExpertAi": {
"Username": "<developer account username>",
"Password": "<developer account password>",
"Endpoint": "<expert ai nlp base url>",
"AuthUrl": "<expert ai authentical base url>"
}
}
- Install front end dependencies
npm install
- From Visual Studio, press
F5
Please refer to the demo
Distributed under the MIT License. See LICENSE
for more information.