Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (12.3%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: YSKartal
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 7.92 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 2
  • Open Issues: 2
  • Releases: 0
Created over 2 years ago · Last pushed 7 months ago
Metadata Files
Readme License Citation

README.md

Scientific Claim Source Retrieval

Description

Given an implicit reference to a scientific paper, i.e., a social media post (tweet) that mentions a research publication without a URL, this method enables to retrieve the mentioned paper from a pool of candidate papers. It was initially developed to leverage CORD19, a corpus of academic papers about COVID-19 and related coronavirus research, however, it can be used with any corpus of publications with enough metadata.

The method takes an input claim or sentence from the user, computes its similarity with the publication titles and abstracts in the corpus, and returns a ranked list of matching publications. The similarity between the input claim and the publications is calculated using BM25.

Use Cases

  1. To find which publication is possible mentioned in a claim/statement.
  2. To find topically similar publications to a claim/statement.

Input Data

The input data consists of social media posts having the following fields:

  • post_id : unique post ID in the collection
  • tweet_text : text of the post (tweet)

Example Input:

  • post_id: 12345678901
  • tweet_text: Published in the journal Antiviral Research, the study from Monash University showed that a single dose of Ivermectin could stop the coronavirus growing in cell culture, effectively eradicating all genetic material of the virus within two days.

Output Data

This output aims to show an example publication matching for the given input.

  • post_id : unique post ID in the collection
  • tweet_text : text of the post (tweet)
  • cord_uid: identifier of the matching publication
  • bm25_topk: top-k matching publications based on BM25 similarity score
  • in_topx: Float value indicating the rank of the matching publication in the top-k list

  • bm25_topk: ['htlvpvz5', 'h7hj64q5', 'rwgqkow3', 'dbgtslc8', 'am11yqbf']

  • in_topx: 1.0 Example Output:

  • post_id: 12345678901

  • tweet_text: Published in the journal Antiviral Research, the study from Monash University showed that a single dose of Ivermectin could stop the coronavirus growing in cell culture, effectively eradicating all genetic material of the virus within two days.

  • cord_uid: htlvpvz5 (Effectiveness of Covid-19 Vaccines against the B.1.617.2 (Delta) Variant)

  • bm25_topk: ['htlvpvz5', 'h7hj64q5', 'rwgqkow3', 'dbgtslc8', 'am11yqbf']

  • in_topx: 1.0

Hardware Requirements

The method runs on a small virtual machine provided by cloud computing company (2 x86 CPU core, 4 GB RAM, 40GB HDD).

Environment Setup

The method is implemented in Python and requires the following libraries which can be installed via pip:

bash pip install -r requirements.txt

How to Use

Please follow the instructions in the notebook.

Technical Details

Published in the journal Antiviral Research, the study from Monash University showed that a single dose of Ivermectin could stop the coronavirus growing in cell culture -- effectively eradicating all genetic material of the virus within two days.

Peer-reviewed in the New England Journal of Medicine regarding Delta (B.1.617.2):
- Pfizer is ~90% effective
- AstraZeneca is ~70% effective.
This falls in line with vaccine efficacy of other variants. Yes, the vaccines ARE indeed effective against Delta.

Contact Details

For questions or feedback, contact Yavuz Selim Kartal via YavuzSelim.Kartal@gesis.org.

Owner

  • Login: YSKartal
  • Kind: user

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - family-names: Kartal
    given-names: Yavuz Selim
title: "Claim Source Retrieval"
version: 1.0
identifiers:
  - type: 
    value: 
date-released: 2025-06-16

GitHub Events

Total
  • Issues event: 2
  • Issue comment event: 4
  • Push event: 16
  • Pull request review event: 1
  • Pull request event: 8
Last Year
  • Issues event: 2
  • Issue comment event: 4
  • Push event: 16
  • Pull request review event: 1
  • Pull request event: 8

Issues and Pull Requests

Last synced: 8 months ago

All Time
  • Total issues: 0
  • Total pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • shyamgupta196 (1)
  • taimoorkhan-nlp (1)
Pull Request Authors
  • taimoorkhan-nlp (2)
  • shyamgupta196 (1)
Top Labels
Issue Labels
Pull Request Labels