Anomaly Detection in Text Data Sets Using Character-Level Representation

aut.relation.journalJournal of Physics : Conference Series
dc.contributor.authorMohaghegh, Mahsa
dc.contributor.authorAbdurakhmanov, Amantay
dc.date.accessioned2023-05-15T23:31:49Z
dc.date.available2023-05-15T23:31:49Z
dc.date.issued2021-04-28
dc.description.abstractThis paper proposes a character-level representation of unsupervised text data sets for anomaly detection problems. An empirical examination of the character-level text representation was conducted to demonstrate the ability to separate outlying and normal records using an ensemble of multiple classic numerical anomaly classifiers. Experimental results obtained on two different data sets confirmed the applicability of the developed unsupervised model to detect outlying instances in various real-world scenarios, providing the opportunity to quickly assess a large amount of textual data in terms of information consistency and conformity without knowledge of the data content itself.
dc.identifier.citationJournal of Physics : Conference Series, ISSN: 1742-6588 (Print), Institute of Physics (IoP). doi: 10.1088/1742-6596/1880/1/012028
dc.identifier.doi10.1088/1742-6596/1880/1/012028
dc.identifier.issn1742-6588
dc.identifier.urihttps://hdl.handle.net/10292/16145
dc.publisherInstitute of Physics (IoP)
dc.relation.urihttps://iopscience.iop.org/article/10.1088/1742-6596/1880/1/012028
dc.rights.accessrightsOpenAccess
dc.rights.urihttp://creativecommons.org/licenses/by/3.0
dc.subject0202 Atomic, Molecular, Nuclear, Particle and Plasma Physics
dc.subject0204 Condensed Matter Physics
dc.subject0299 Other Physical Sciences
dc.subject51 Physical sciences
dc.titleAnomaly Detection in Text Data Sets Using Character-Level Representation
dc.typeJournal Article
pubs.elements-id502055
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Mohaghegh_2021_J._Phys.__Conf._Ser._1880_012028.pdf
Size:
610.87 KB
Format:
Adobe Portable Document Format
Description:
Journal article