Natural Language Processing Text Data from Final Contractor/Grantee Reports and Evaluation Reports (2011-2021)

Description

This data asset contains data files of text extracted from pdf reports on the Development Experience Clearinghouse (DEC) for the years 2011 to 2021 (as of July 2021). It includes three specific "Document types" identified by the DEC: Final Contractor/Grantee Report, Final Evaluation Report, and Special Evaluation. Each PDF document labeled as one of these three document types and labeled with a publication year from 2011 to 2021 was downloaded from the DEC in July 2011. The dataset includes text data files from 2,579 Final Contractor/Grantee Reports, 1,299 Final Evaluation reports, and 1,323 Special Evaluation reports. Raw text from each of these PDFs was extracted and saved as individual csv files, the names of which correspond to the Document ID of the PDF document on the DEC. Within each csv file, the raw text is split into paragraphs and corresponding sentences. In addition, to enable Natural Language Processing of the data, the sentences are cleaned by removing unnecessary special characters, punctuation, and numbers, and each word is stemmed to its root to remove inflections (e.g. pluralization and conjugation). This data could be used to analyze trends in USAID's programming approaches and terminology. This data was compiled for USAID/PPL/LER with the Program Cycle Mechanism.

Resources

Name Format Description Link
21 Final Progress Reports prepared by USAID implementing partners at the conclusion of their contract or grant (2011 to July 2021) https://data.usaid.gov/d/ejic-dzga
21 USAID evaluation reports that are summative in nature and completed at or near the end of the USAID project or activity that is being evaluated (2011 to July 2021) https://data.usaid.gov/d/jsuc-wyu4
21 USAID evaluation reports concerning a USAID project or activity that are not included in the data set of Final Evaluation Reports, such as mid-term or formative evaluations (2011 to July 2021) https://data.usaid.gov/d/93rs-uviw
21 USAID evaluation reports concerning a USAID project or activity that are not included in the data set of Final Evaluation Reports, such as mid-term or formative evaluations (2011 to July 2021) https://datahub.usaid.gov/d/93rs-uviw
21 Final Progress Reports prepared by USAID implementing partners at the conclusion of their contract or grant (2011 to July 2021) https://datahub.usaid.gov/d/ejic-dzga
21 USAID evaluation reports that are summative in nature and completed at or near the end of the USAID project or activity that is being evaluated (2011 to July 2021) https://datahub.usaid.gov/d/jsuc-wyu4

Tags

  • ppl
  • final-contractor-grantee-report
  • ethnic-equity
  • nlp
  • special-evaluation-report
  • racial-equity
  • final-evaluation-report

Topics

Categories