Back to search

North Dakota State University

Signature Extraction from E-Mails

Abstract

dc:description.abstract

Detecting user identity information from the email is one of the predominant exploring topics in data mining. One approach is to extract signature from the body of emails. Those names are usually suitable for representing the sender’s or recipient’s identity. To overcome the limitation, we proposed the novel approach to extract the signature of email sender and recipient from salutation and signature blocks and email bodies. After locating and extracting signature blocks from email bodies, we can identify the names in the salutation and signature lines, which can be directly associated with the corresponding email address in email headers and the body by using named entity recognition (NER) tools. For these tasks Naive Bayes, maximum entropy and Support Vector Machines (SVM) algorithms are preferred in this paper. Results on the data subset of the Enron corpus indicate that the approaches presented in this paper can extract signature from email bodies.

Degree

thesis:*
Grantor dc:publisher
North Dakota State University
Year dc:date.issued
2016

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Muttineni, Divya

Subjects

dc:subject × 4

Rights

dc:rights
Statement dc:rights
  • NDSU Policy 190.6.2

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/10365/25893

Chain of custody

source
Harvested from
North Dakota State University
Base URL
library.ndsu.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Muttineni, Divya. Signature Extraction from E-Mails. North Dakota State University, 2016. https://hdl.handle.net/10365/25893