Taking a Steppe Towards Optimizing Note-Taking Software by Creation of a Note Classification Algorithm

  • Daniela Zieba
  • Wren Jenkins
  • Michael Galloway
  • Jean-Luc Houle
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 738)

Abstract

Note-taking software often far surpasses its paper-and-pencil counterpart when measured in metrics such as availability and reliability. However, there is ample opportunity relating to the analysis and organization of notes in structures often called folders, notebooks, or projects within various software. ShovelWare is a project designed for an ongoing field research project analyzing the Bronze and Iron Ages of Mongolia. Accessible through a web interface and cross-platform mobile application, it is a replacement for manual data collection on paper and excessive, error-ridden input into digital spreadsheets. We propose a machine learning algorithm that classifies notes using a variety of metrics, sorting them into graph structures to provide initial insights into the similarity of field notes. As a result, ShovelWare will allow archaeologists to more quickly and cleanly view and share their data. The algorithm, as well as the note-taking structure, are planned with hopes of scalability and applicability into more disciplines.

Keywords

Note-taking software Archaeology-specific software Machine learning-based classification Data management software Digital recording system 

References

  1. 1.
    D. Sosna, L. Brunclkov, D. Henig, Testing iPad in the field: use of a relational database in garbological research. Anthropologie 51, 421–430 (2013)Google Scholar
  2. 2.
    C. Motz, S. Carrier, Paperless Recording at the Sangro Valley Project (Amsterdam University Press, Amsterdam, 2012), pp. 1–2Google Scholar
  3. 3.
    Field acquired management information systems project. FAIMS Project (2017). Online Available: https://www.fedarch.org/
  4. 4.
    D. Michie, D.J. Spiegelhalter, C. Taylor, Machine Learning, Neural and Statistical Classification (Ellis Horwood, Upper Saddle River, 1994)Google Scholar
  5. 5.
    B. Pang, L. Lee, S. Vaithyanathan, Thumbs up?: sentiment classification using machine learning techniques, in Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing - Volume 10, Series EMNLP ’02, Stroudsburg, PA (Association for Computational Linguistics, New York, 2002), pp. 79–86. Online Available: https://doi.org/10.3115/1118693.1118704
  6. 6.
    “NativeScript,” NativeScript (2017). Online Available: https://www.nativescript.org/
  7. 7.
  8. 8.
    AWS Lambda, Amazon Web Services, Inc. (2017) Online Available: https://aws.amazon.com/lambda/
  9. 9.
    Microsoft Azure Functions, Microsoft (2017) Online Available: https://azure.microsoft.com/en-us/services/functions/
  10. 10.
    TensorFlow, Google (2017). Online Available: https://www.tensorflow.org/
  11. 11.
    C. Brooks, C. Goulet, M. Galloway, Toward indoor autonomous flight using a multi-rotor vehicle, in International Conference on Information Technology: New Generations (2016)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Daniela Zieba
    • 1
  • Wren Jenkins
    • 1
  • Michael Galloway
    • 1
  • Jean-Luc Houle
    • 1
  1. 1.Western Kentucky UniversityBowling GreenUSA

Personalised recommendations