LitOrganizer: Automating the process of data extraction and organization for scientific literature reviews

Şahin A., Kara B. C., DİRSEHAN T.

SoftwareX, vol.30, 2025 (SCI-Expanded, Scopus) identifier

  • Publication Type: Article / Article
  • Volume: 30
  • Publication Date: 2025
  • Doi Number: 10.1016/j.softx.2025.102198
  • Journal Name: SoftwareX
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, Directory of Open Access Journals
  • Keywords: Data extraction, Document organization, Information retrieval, Keyword-based search, Literature review automation, Python-based tool
  • Marmara University Affiliated: Yes

Abstract

Scientific literature reviews have become a time-consuming and complex process due to the increasing volume of data. Manual data extraction and organization significantly hinder the efficiency of this process. LitOrganizer, a Python-based software, assists researchers by scanning PDF files with specified keywords and consolidating the extracted information into a Word document, including the source name and page number where the information appears. Additionally, it identifies the DOI numbers of files, renaming the documents with the correct citation information, and helps organize both the PDF documents and the specific data efficiently.