Automatic identification of best answers in online enquiry communities

Grégoire Burel, Yulan He, Harith Alani

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Online communities are prime sources of information. The Web is rich with forums and Question Answering (Q&A) communities where people go to seek answers to all kinds of questions. Most systems employ manual answer-rating procedures to encourage people to provide quality answers and to help users locate the best answers in a given thread. However, in the datasets we collected from three online communities, we found that half their threads lacked best answer markings. This stresses the need for methods to assess the quality of available answers to: 1) provide automated ratings to fill in for, or support, manually assigned ones, and; 2) to assist users when browsing such answers by filtering in potential best answers. In this paper, we collected data from three online communities and converted it to RDF based on the SIOC ontology. We then explored an approach for predicting best answers using a combination of content, user, and thread features. We show how the influence of such features on predicting best answers differs across communities. Further we demonstrate how certain features unique to some of our community systems can boost predictability of best answers.
Original languageEnglish
Title of host publicationThe semantic web : research and applications
Subtitle of host publication9th extended semantic web conference, ESWC 2012, Heraklion, Crete, Greece, May 27-31, 2012. Proceedings
EditorsElena Simperl, Philipp Cimiano, Axel Polleres, Oscar Corcho, Valentina Presutti
Place of PublicationHeidelberg (DE)
PublisherSpringer
Pages514-529
Number of pages16
Volume7295
ISBN (Electronic)978/3/642-30284-8
ISBN (Print)978-3-642-30283-1
DOIs
Publication statusPublished - 2012
Event9th extended semantic web conference, ESWC 2012 - Heraklion, Greece
Duration: 27 May 201231 May 2012

Publication series

NameLecture notes in computer science
PublisherSpringer
Volume7295
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference9th extended semantic web conference, ESWC 2012
CountryGreece
CityHeraklion
Period27/05/1231/05/12

Fingerprint

Ontology

Cite this

Burel, G., He, Y., & Alani, H. (2012). Automatic identification of best answers in online enquiry communities. In E. Simperl, P. Cimiano, A. Polleres, O. Corcho, & V. Presutti (Eds.), The semantic web : research and applications: 9th extended semantic web conference, ESWC 2012, Heraklion, Crete, Greece, May 27-31, 2012. Proceedings (Vol. 7295, pp. 514-529). (Lecture notes in computer science; Vol. 7295). Heidelberg (DE): Springer. https://doi.org/10.1007/978-3-642-30284-8_41
Burel, Grégoire ; He, Yulan ; Alani, Harith. / Automatic identification of best answers in online enquiry communities. The semantic web : research and applications: 9th extended semantic web conference, ESWC 2012, Heraklion, Crete, Greece, May 27-31, 2012. Proceedings. editor / Elena Simperl ; Philipp Cimiano ; Axel Polleres ; Oscar Corcho ; Valentina Presutti. Vol. 7295 Heidelberg (DE) : Springer, 2012. pp. 514-529 (Lecture notes in computer science).
@inproceedings{e9a4c3c0f8a94a23980140fd2b33a5fd,
title = "Automatic identification of best answers in online enquiry communities",
abstract = "Online communities are prime sources of information. The Web is rich with forums and Question Answering (Q&A) communities where people go to seek answers to all kinds of questions. Most systems employ manual answer-rating procedures to encourage people to provide quality answers and to help users locate the best answers in a given thread. However, in the datasets we collected from three online communities, we found that half their threads lacked best answer markings. This stresses the need for methods to assess the quality of available answers to: 1) provide automated ratings to fill in for, or support, manually assigned ones, and; 2) to assist users when browsing such answers by filtering in potential best answers. In this paper, we collected data from three online communities and converted it to RDF based on the SIOC ontology. We then explored an approach for predicting best answers using a combination of content, user, and thread features. We show how the influence of such features on predicting best answers differs across communities. Further we demonstrate how certain features unique to some of our community systems can boost predictability of best answers.",
author = "Gr{\'e}goire Burel and Yulan He and Harith Alani",
year = "2012",
doi = "10.1007/978-3-642-30284-8_41",
language = "English",
isbn = "978-3-642-30283-1",
volume = "7295",
series = "Lecture notes in computer science",
publisher = "Springer",
pages = "514--529",
editor = "Elena Simperl and Philipp Cimiano and Axel Polleres and Oscar Corcho and Valentina Presutti",
booktitle = "The semantic web : research and applications",
address = "Germany",

}

Burel, G, He, Y & Alani, H 2012, Automatic identification of best answers in online enquiry communities. in E Simperl, P Cimiano, A Polleres, O Corcho & V Presutti (eds), The semantic web : research and applications: 9th extended semantic web conference, ESWC 2012, Heraklion, Crete, Greece, May 27-31, 2012. Proceedings. vol. 7295, Lecture notes in computer science, vol. 7295, Springer, Heidelberg (DE), pp. 514-529, 9th extended semantic web conference, ESWC 2012, Heraklion, Greece, 27/05/12. https://doi.org/10.1007/978-3-642-30284-8_41

Automatic identification of best answers in online enquiry communities. / Burel, Grégoire; He, Yulan; Alani, Harith.

The semantic web : research and applications: 9th extended semantic web conference, ESWC 2012, Heraklion, Crete, Greece, May 27-31, 2012. Proceedings. ed. / Elena Simperl; Philipp Cimiano; Axel Polleres; Oscar Corcho; Valentina Presutti. Vol. 7295 Heidelberg (DE) : Springer, 2012. p. 514-529 (Lecture notes in computer science; Vol. 7295).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Automatic identification of best answers in online enquiry communities

AU - Burel, Grégoire

AU - He, Yulan

AU - Alani, Harith

PY - 2012

Y1 - 2012

N2 - Online communities are prime sources of information. The Web is rich with forums and Question Answering (Q&A) communities where people go to seek answers to all kinds of questions. Most systems employ manual answer-rating procedures to encourage people to provide quality answers and to help users locate the best answers in a given thread. However, in the datasets we collected from three online communities, we found that half their threads lacked best answer markings. This stresses the need for methods to assess the quality of available answers to: 1) provide automated ratings to fill in for, or support, manually assigned ones, and; 2) to assist users when browsing such answers by filtering in potential best answers. In this paper, we collected data from three online communities and converted it to RDF based on the SIOC ontology. We then explored an approach for predicting best answers using a combination of content, user, and thread features. We show how the influence of such features on predicting best answers differs across communities. Further we demonstrate how certain features unique to some of our community systems can boost predictability of best answers.

AB - Online communities are prime sources of information. The Web is rich with forums and Question Answering (Q&A) communities where people go to seek answers to all kinds of questions. Most systems employ manual answer-rating procedures to encourage people to provide quality answers and to help users locate the best answers in a given thread. However, in the datasets we collected from three online communities, we found that half their threads lacked best answer markings. This stresses the need for methods to assess the quality of available answers to: 1) provide automated ratings to fill in for, or support, manually assigned ones, and; 2) to assist users when browsing such answers by filtering in potential best answers. In this paper, we collected data from three online communities and converted it to RDF based on the SIOC ontology. We then explored an approach for predicting best answers using a combination of content, user, and thread features. We show how the influence of such features on predicting best answers differs across communities. Further we demonstrate how certain features unique to some of our community systems can boost predictability of best answers.

UR - http://www.scopus.com/inward/record.url?scp=84861746094&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-30284-8_41

DO - 10.1007/978-3-642-30284-8_41

M3 - Conference contribution

AN - SCOPUS:84861746094

SN - 978-3-642-30283-1

VL - 7295

T3 - Lecture notes in computer science

SP - 514

EP - 529

BT - The semantic web : research and applications

A2 - Simperl, Elena

A2 - Cimiano, Philipp

A2 - Polleres, Axel

A2 - Corcho, Oscar

A2 - Presutti, Valentina

PB - Springer

CY - Heidelberg (DE)

ER -

Burel G, He Y, Alani H. Automatic identification of best answers in online enquiry communities. In Simperl E, Cimiano P, Polleres A, Corcho O, Presutti V, editors, The semantic web : research and applications: 9th extended semantic web conference, ESWC 2012, Heraklion, Crete, Greece, May 27-31, 2012. Proceedings. Vol. 7295. Heidelberg (DE): Springer. 2012. p. 514-529. (Lecture notes in computer science). https://doi.org/10.1007/978-3-642-30284-8_41