SMART DOCUMENT URGENCY PROCESSING SYSTEM (SDUPS) FOR SCHOOL GOVERNANCE AND OPERATION DIVISION OF SCHOOLS DIVISION OFFICE OF LAGUNA
Main Article Content
Abstract
This study aimed to evaluate the effectiveness of the SMART Document Urgency Processing System (SDUPS), an AI tool designed to streamline and improve document management processes through automated urgency classification. The system addresses a common challenge in many organizational workflows—inefficient prioritization of documents, which leads to delayed processing and communication gaps. Using the Technology Acceptance Model (TAM), the study assessed the system's perceived usefulness and ease of use. Thirty respondents participated in the TAM survey, with all strongly agreeing on the system’s usefulness and 25 out of 30 strongly agreeing on its ease of use. Zero-Shot Learning (ZSL), supervised machine learning models, and a meta-classifier were evaluated to test their classification accuracy. While the supervised model achieved a perfect recall score for high-urgency documents, it failed to effectively predict low- and medium-urgency categories. The ZSL model showed moderate success, particularly when combined with SpaCy’s natural language processing capabilities for extracting due dates and document types. Integrating SpaCy and ZSL resulted in the highest overall performance, suggesting that hybrid approaches significantly enhance classification accuracy. However, accurately identifying low urgency documents remains a challenge, indicating a need for additional training data or feature engineering. The findings confirm the system’s potential to significantly improve the efficiency and accuracy of urgency classification in document workflows. The study concludes that the SDUPS is practical and user-friendly, promising for adoption in government and organizational contexts. Future enhancements should focus on refining the low-urgency cases and integrating the system with broader document management platforms for streamlined operations.
Keywords: Zero-Shot Learning (ZSL), spaCy NLP, Hybrid approach, Optical Character Recognition (OCR), Urgency classifications.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.