We are always looking for feedback! Write an email to help us to improve our service.

About Us

Since 13th January 2020, 49228 articles concerning SARS-CoV-2 were published. Many of them are not reviewed in a professional reviewing process at the time of publication. Our objective is to develop an easy to use interface to access, sort and classify the huge amount of articles about the Coronavirus.

Frequently Asked Questions

Features


  • List and access published articles
  • Sort and filter articles by publishing date, authors name, category, journal, location, title and content
  • Get a list of recommended papers related to a specific question
  • Classification of papers into one or more predefined categories
  • List similar papers for a publication
  • Find relations of articles to real-world locations. An overview is accessible as a world map.

Is Collabovid ready-to-use?


This website was created during the COVID-19 Global Hackathon at the end of March 2020. Since then, Collabovid is updated and improved very frequently. Please note that the website is still under development. We are always looking for feedback to improve the site. We kindly ask you to fill out our feedback survey or write an email.

Upcoming Features


  • Allow verified experts to evaluate and review the papers informally to introduce a discussion before the paper is published officially and provide indications for the quality of the articles
  • Integrate new data sources
  • Improve the search engine

Where does the research data come from?


  • The database contains all papers from the medRxiv / bioRxiv COVID-19 SARS-CoV-2 preprints page. Furthermore, we include publications from arXiv, Elsevier and PubMed. All sources are updated several times a day.
  • The category assignment model was trained on the LitCovid dataset.

How does it work?


Semantic Search: Our semantic search should be used to explore a previously unknown research field. It works best when the user provides us with a sentence or question about a COVID-19 related research field, i.e. "How does COVID-19 affect childrens mental health?". The search algorithm is able to analyze and generalize a given query and provide the user with papers that match the query's topic. It is capable of recognizing connections between words, e.g. temperature, weather, humidity. These connections are used to show papers of the overall topics that do not necessarily contain any word that the user provided. We use natural language processing techniques to find correlations between a given query and the content of a paper. For semantic analysis, we trained a BERT model on our dataset that learned to find similarities between papers and a given query.

Keyword Search: The keyword search uses Elasticsearch to find papers with matching keywords in their title, abstract or authors. Despite being very efficient when the user provides a good set of keywords, the search is not able to generalize the search query.

Category Assignment: The category assignment is computed by a machine learning algorithm. The model was trained with an existing dataset from LitCovid. LitCovid is a curated literature hub for tracking scientific information about SARS-CoV-2. Collabovid is an open source project that is licenced under GNU General Public License v3.0. The source code can be found at GitHub.

Hackathons

1st Place
#TechTakesOnCOVID

Join forces with Terminal’s engineering community to develop working solutions to fight COVID-19.

Info page
Highlighted project
#BuildforCOVID19

Collabovid was one of the highlighted projects of the COVID-19 Global Hackathon. The hackathon was an opportunity for developers to build software solutions that drive social impact, with the aim of tackling some of the challenges related to the current coronavirus pandemic.

Highlighted projects
2nd Place
Hack Quarantine

A fully-online, people-focused hackathon bringing people together to use their skills to help combat the issues the world is facing with the COVID-19 pandemic.

Info page

Our Team

Jonas Dippel
Student TU Berlin
Yannic Lieder
Student TU Braunschweig
Eike Niehs
Student TU Braunschweig
Michael Perk
Student TU Braunschweig
Moritz Pfister
Student TU Braunschweig