@inproceedings{alkhereyf-rambow-2017-work,
title = "Work Hard, Play Hard: Email Classification on the Avocado and {E}nron Corpora",
author = "Alkhereyf, Sakhar and
Rambow, Owen",
editor = "Riedl, Martin and
Somasundaran, Swapna and
Glava{\v{s}}, Goran and
Hovy, Eduard",
booktitle = "Proceedings of {T}ext{G}raphs-11: the Workshop on Graph-based Methods for Natural Language Processing",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-2408",
doi = "10.18653/v1/W17-2408",
pages = "57--65",
abstract = "In this paper, we present an empirical study of email classification into two main categories {``}Business{''} and {``}Personal{''}. We train on the Enron email corpus, and test on the Enron and Avocado email corpora. We show that information from the email exchange networks improves the performance of classification. We represent the email exchange networks as social networks with graph structures. For this classification task, we extract social networks features from the graphs in addition to lexical features from email content and we compare the performance of SVM and Extra-Trees classifiers using these features. Combining graph features with lexical features improves the performance on both classifiers. We also provide manually annotated sets of the Avocado and Enron email corpora as a supplementary contribution.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alkhereyf-rambow-2017-work">
<titleInfo>
<title>Work Hard, Play Hard: Email Classification on the Avocado and Enron Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of TextGraphs-11: the Workshop on Graph-based Methods for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Riedl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swapna</namePart>
<namePart type="family">Somasundaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glavaš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present an empirical study of email classification into two main categories “Business” and “Personal”. We train on the Enron email corpus, and test on the Enron and Avocado email corpora. We show that information from the email exchange networks improves the performance of classification. We represent the email exchange networks as social networks with graph structures. For this classification task, we extract social networks features from the graphs in addition to lexical features from email content and we compare the performance of SVM and Extra-Trees classifiers using these features. Combining graph features with lexical features improves the performance on both classifiers. We also provide manually annotated sets of the Avocado and Enron email corpora as a supplementary contribution.</abstract>
<identifier type="citekey">alkhereyf-rambow-2017-work</identifier>
<identifier type="doi">10.18653/v1/W17-2408</identifier>
<location>
<url>https://aclanthology.org/W17-2408</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>57</start>
<end>65</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Work Hard, Play Hard: Email Classification on the Avocado and Enron Corpora
%A Alkhereyf, Sakhar
%A Rambow, Owen
%Y Riedl, Martin
%Y Somasundaran, Swapna
%Y Glavaš, Goran
%Y Hovy, Eduard
%S Proceedings of TextGraphs-11: the Workshop on Graph-based Methods for Natural Language Processing
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F alkhereyf-rambow-2017-work
%X In this paper, we present an empirical study of email classification into two main categories “Business” and “Personal”. We train on the Enron email corpus, and test on the Enron and Avocado email corpora. We show that information from the email exchange networks improves the performance of classification. We represent the email exchange networks as social networks with graph structures. For this classification task, we extract social networks features from the graphs in addition to lexical features from email content and we compare the performance of SVM and Extra-Trees classifiers using these features. Combining graph features with lexical features improves the performance on both classifiers. We also provide manually annotated sets of the Avocado and Enron email corpora as a supplementary contribution.
%R 10.18653/v1/W17-2408
%U https://aclanthology.org/W17-2408
%U https://doi.org/10.18653/v1/W17-2408
%P 57-65
Markdown (Informal)
[Work Hard, Play Hard: Email Classification on the Avocado and Enron Corpora](https://aclanthology.org/W17-2408) (Alkhereyf & Rambow, TextGraphs 2017)
ACL