Identifying commented passages of documents using implicit hyperlinks

Jean Yves Delort

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

Abstract

This paper addresses the issue of automatically selecting passages of blog posts using readers' comments. The problem is difficult because: (i) the textual content of blogs is often noisy, (ii) comments do not always target passages of the posts and, (iii) comments are not equally useful for identifying important passages. We have developed a system for selecting commented passages which takes as input blog posts and their comments and delivers, for each post, the sentences of the post which are the most commented and/or the most discussed. Our approach combines three steps to identify commented passages of a post. The first step is to remove the complexity of processing the contents of posts and comments using heuristics adapted to the language of the blog. The second step is to find useful comments and assigns them a degree of relevance using a model automatically built and validated by an expert. The third step is to identify important passages using relevant comments. We conducted two experiments to evaluate the usefulness and the effectiveness of our approach. The first study show that in only 50% of the posts, the most commented sentence elicited by our approach corresponds to the post extract generated using generic summarization. In the second study, human participants confirmed that, in practice, selected passages are frequently commented passages.

LanguageEnglish
Title of host publicationProceedings of the Seventeenth ACM Conference on Hypertext and Hypermedia, HT'06
Pages89-98
Number of pages10
Volume2006
DOIs
Publication statusPublished - 2006
EventSeventeenth ACM Conference on Hypertext and Hypermedia, HT'06 - Odense, Denmark
Duration: 22 Aug 200625 Aug 2006

Other

OtherSeventeenth ACM Conference on Hypertext and Hypermedia, HT'06
CountryDenmark
CityOdense
Period22/08/0625/08/06

Fingerprint

Blogs
Processing
Experiments

Keywords

  • Implicit links
  • Passage extraction
  • Weblogs

Cite this

Delort, J. Y. (2006). Identifying commented passages of documents using implicit hyperlinks. In Proceedings of the Seventeenth ACM Conference on Hypertext and Hypermedia, HT'06 (Vol. 2006, pp. 89-98) https://doi.org/10.1145/1149941.1149960
Delort, Jean Yves. / Identifying commented passages of documents using implicit hyperlinks. Proceedings of the Seventeenth ACM Conference on Hypertext and Hypermedia, HT'06. Vol. 2006 2006. pp. 89-98
@inproceedings{d637891f419a4e258b32f6128bbcf685,
title = "Identifying commented passages of documents using implicit hyperlinks",
abstract = "This paper addresses the issue of automatically selecting passages of blog posts using readers' comments. The problem is difficult because: (i) the textual content of blogs is often noisy, (ii) comments do not always target passages of the posts and, (iii) comments are not equally useful for identifying important passages. We have developed a system for selecting commented passages which takes as input blog posts and their comments and delivers, for each post, the sentences of the post which are the most commented and/or the most discussed. Our approach combines three steps to identify commented passages of a post. The first step is to remove the complexity of processing the contents of posts and comments using heuristics adapted to the language of the blog. The second step is to find useful comments and assigns them a degree of relevance using a model automatically built and validated by an expert. The third step is to identify important passages using relevant comments. We conducted two experiments to evaluate the usefulness and the effectiveness of our approach. The first study show that in only 50{\%} of the posts, the most commented sentence elicited by our approach corresponds to the post extract generated using generic summarization. In the second study, human participants confirmed that, in practice, selected passages are frequently commented passages.",
keywords = "Implicit links, Passage extraction, Weblogs",
author = "Delort, {Jean Yves}",
year = "2006",
doi = "10.1145/1149941.1149960",
language = "English",
isbn = "1595934170",
volume = "2006",
pages = "89--98",
booktitle = "Proceedings of the Seventeenth ACM Conference on Hypertext and Hypermedia, HT'06",

}

Delort, JY 2006, Identifying commented passages of documents using implicit hyperlinks. in Proceedings of the Seventeenth ACM Conference on Hypertext and Hypermedia, HT'06. vol. 2006, pp. 89-98, Seventeenth ACM Conference on Hypertext and Hypermedia, HT'06, Odense, Denmark, 22/08/06. https://doi.org/10.1145/1149941.1149960

Identifying commented passages of documents using implicit hyperlinks. / Delort, Jean Yves.

Proceedings of the Seventeenth ACM Conference on Hypertext and Hypermedia, HT'06. Vol. 2006 2006. p. 89-98.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

TY - GEN

T1 - Identifying commented passages of documents using implicit hyperlinks

AU - Delort, Jean Yves

PY - 2006

Y1 - 2006

N2 - This paper addresses the issue of automatically selecting passages of blog posts using readers' comments. The problem is difficult because: (i) the textual content of blogs is often noisy, (ii) comments do not always target passages of the posts and, (iii) comments are not equally useful for identifying important passages. We have developed a system for selecting commented passages which takes as input blog posts and their comments and delivers, for each post, the sentences of the post which are the most commented and/or the most discussed. Our approach combines three steps to identify commented passages of a post. The first step is to remove the complexity of processing the contents of posts and comments using heuristics adapted to the language of the blog. The second step is to find useful comments and assigns them a degree of relevance using a model automatically built and validated by an expert. The third step is to identify important passages using relevant comments. We conducted two experiments to evaluate the usefulness and the effectiveness of our approach. The first study show that in only 50% of the posts, the most commented sentence elicited by our approach corresponds to the post extract generated using generic summarization. In the second study, human participants confirmed that, in practice, selected passages are frequently commented passages.

AB - This paper addresses the issue of automatically selecting passages of blog posts using readers' comments. The problem is difficult because: (i) the textual content of blogs is often noisy, (ii) comments do not always target passages of the posts and, (iii) comments are not equally useful for identifying important passages. We have developed a system for selecting commented passages which takes as input blog posts and their comments and delivers, for each post, the sentences of the post which are the most commented and/or the most discussed. Our approach combines three steps to identify commented passages of a post. The first step is to remove the complexity of processing the contents of posts and comments using heuristics adapted to the language of the blog. The second step is to find useful comments and assigns them a degree of relevance using a model automatically built and validated by an expert. The third step is to identify important passages using relevant comments. We conducted two experiments to evaluate the usefulness and the effectiveness of our approach. The first study show that in only 50% of the posts, the most commented sentence elicited by our approach corresponds to the post extract generated using generic summarization. In the second study, human participants confirmed that, in practice, selected passages are frequently commented passages.

KW - Implicit links

KW - Passage extraction

KW - Weblogs

UR - http://www.scopus.com/inward/record.url?scp=34247361251&partnerID=8YFLogxK

U2 - 10.1145/1149941.1149960

DO - 10.1145/1149941.1149960

M3 - Conference proceeding contribution

SN - 1595934170

SN - 9781595934178

VL - 2006

SP - 89

EP - 98

BT - Proceedings of the Seventeenth ACM Conference on Hypertext and Hypermedia, HT'06

ER -

Delort JY. Identifying commented passages of documents using implicit hyperlinks. In Proceedings of the Seventeenth ACM Conference on Hypertext and Hypermedia, HT'06. Vol. 2006. 2006. p. 89-98 https://doi.org/10.1145/1149941.1149960