Volume 5, Number 2, 2020, 10 – 16

Deep Learning Application – Identifying PII (Personally Identifiable Information) to Protect


Anil K. Makhija, B.E., PGDIM, MBA.
CamEd Business School, Cambodia
Email: [email protected]


Received: August 2020
Revised: October 2020
Accepted: December 2020


This paper presents application of deep learning and machine learning models in detecting personally identifiable information (PII) in unstructured text (emails). The proposed models use support vector machine (trained using sequential minimal optimization) and long short term memory (LSTM) artificial neural network. Synthetic email dataset has been used to train and validate the proposed models and the outcomes are measured by standard measures of accuracy, precision, recall and F1-score of each of the proposed model. The experimental results on the model that uses support vector machine (trained using sequential minimal optimization) showed most promising results on detecting the personally identifiable information in the email dataset. The LSTM model also showed equally promising results.

Keywords: Personally Identifiable Information, Deep Learning in detecting PII, Machine Learning in detecting PII, Artificial Intelligence in protecting privacy, Protecting Personally Identifiable Information.


Read full text

Cite this article in APA 7

Makhija, A., K. (2020). Deep learning application – Identifying PII (personally identifiable information) to protect. JAFESS, 5(2), 10 – 16.

Online citation generator by    Scribbr    QuillBot

Except where otherwise noted, content in JAFESS and CamEd OAR © 2016 by CamEd Business School is licensed under CC BY 4.0