Automatic Anonymization of Textual Documents: Detecting Sensitive Information via Word Embeddings.
Fadi HassanDavid SánchezJordi Soria-ComasJosep Domingo-FerrerPublished in: TrustCom/BigDataSE (2019)
Keyphrases
- sensitive information
- textual documents
- privacy preserving
- privacy preservation
- data privacy
- privacy preserving data publishing
- privacy protection
- text mining
- knowledge extraction
- third party
- digital libraries
- sensitive data
- textual data
- data publishing
- free text
- private information
- privacy preserving data mining
- multimedia documents
- original data
- sensitive attributes
- co occurrence
- confidential information
- information retrieval
- protect sensitive
- data sets
- differential privacy
- text classification
- information extraction
- xml documents
- database systems
- machine learning