@inproceedings{kao-chen-2010-comment,
title = "Comment Extraction from Blog Posts and Its Applications to Opinion Mining",
author = "Kao, Huan-An and
Chen, Hsin-Hsi",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/17_Paper.pdf",
abstract = "Blog posts containing many personal experiences or perspectives toward specific subjects are useful. Blogs allow readers to interact with bloggers by placing comments on specific blog posts. The comments carry viewpoints of readers toward the targets described in the post, or supportive/non-supportive attitude toward the post. Comment extraction is challenging due to that there does not exist a unique template among all blog service providers. This paper proposes methods to deal with this problem. Firstly, the repetitive patterns and their corresponding blocks are extracted from input posts by pattern identification algorithm. Secondly, three filtering strategies, i.e., tag pattern loop filtering, rule overlap filtering, and longest rule first, are used to remove non-comment blocks. Finally, a comment/non-comment classifier is learned to distinguish comment blocks from non-comment blocks with 14 block-level features and 5 rule-level features. In the experiments, we randomly select 600 blog posts from 12 blog service providers. F-measure, recall, and precision are 0.801, 0.855, and 0.780, respectively, by using all of the three filtering strategies together with some selected features. The application of comment extraction to blog mining is also illustrated. We show how to identify the relevant opinionated objects ― say, opinion holders, opinions, and targets, from posts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kao-chen-2010-comment">
<titleInfo>
<title>Comment Extraction from Blog Posts and Its Applications to Opinion Mining</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huan-An</namePart>
<namePart type="family">Kao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Blog posts containing many personal experiences or perspectives toward specific subjects are useful. Blogs allow readers to interact with bloggers by placing comments on specific blog posts. The comments carry viewpoints of readers toward the targets described in the post, or supportive/non-supportive attitude toward the post. Comment extraction is challenging due to that there does not exist a unique template among all blog service providers. This paper proposes methods to deal with this problem. Firstly, the repetitive patterns and their corresponding blocks are extracted from input posts by pattern identification algorithm. Secondly, three filtering strategies, i.e., tag pattern loop filtering, rule overlap filtering, and longest rule first, are used to remove non-comment blocks. Finally, a comment/non-comment classifier is learned to distinguish comment blocks from non-comment blocks with 14 block-level features and 5 rule-level features. In the experiments, we randomly select 600 blog posts from 12 blog service providers. F-measure, recall, and precision are 0.801, 0.855, and 0.780, respectively, by using all of the three filtering strategies together with some selected features. The application of comment extraction to blog mining is also illustrated. We show how to identify the relevant opinionated objects ― say, opinion holders, opinions, and targets, from posts.</abstract>
<identifier type="citekey">kao-chen-2010-comment</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/17_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comment Extraction from Blog Posts and Its Applications to Opinion Mining
%A Kao, Huan-An
%A Chen, Hsin-Hsi
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F kao-chen-2010-comment
%X Blog posts containing many personal experiences or perspectives toward specific subjects are useful. Blogs allow readers to interact with bloggers by placing comments on specific blog posts. The comments carry viewpoints of readers toward the targets described in the post, or supportive/non-supportive attitude toward the post. Comment extraction is challenging due to that there does not exist a unique template among all blog service providers. This paper proposes methods to deal with this problem. Firstly, the repetitive patterns and their corresponding blocks are extracted from input posts by pattern identification algorithm. Secondly, three filtering strategies, i.e., tag pattern loop filtering, rule overlap filtering, and longest rule first, are used to remove non-comment blocks. Finally, a comment/non-comment classifier is learned to distinguish comment blocks from non-comment blocks with 14 block-level features and 5 rule-level features. In the experiments, we randomly select 600 blog posts from 12 blog service providers. F-measure, recall, and precision are 0.801, 0.855, and 0.780, respectively, by using all of the three filtering strategies together with some selected features. The application of comment extraction to blog mining is also illustrated. We show how to identify the relevant opinionated objects ― say, opinion holders, opinions, and targets, from posts.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/17_Paper.pdf
Markdown (Informal)
[Comment Extraction from Blog Posts and Its Applications to Opinion Mining](http://www.lrec-conf.org/proceedings/lrec2010/pdf/17_Paper.pdf) (Kao & Chen, LREC 2010)
ACL