Assessing order effects in online community-based health forums

Reza Mousavi, T. S. Raghu, Keith Frey

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

Abstract

Measuring the quality of health content in online health forums has been a challenging task. The majority of the existing measures are based on nonprofessional evaluations of forum users and may not be reliable. We employed machine learning techniques, text mining methods, and Big Data platforms to construct four measures of textual quality to automatically determine the similarity of a given answer to professional answers. We then used these measures to assess the quality of 66,888 answers posted on Yahoo! Answers Health section. All four measures of textual quality revealed a higher quality for asker-selected best answers indicating that askers, to some extent, have a proper judgment to select the best answers. We also studied the presence of order effects in online health forums. Our results suggest that the textual quality of the first answer positively influences the mean textual quality of the subsequent answers and negatively influences the quantity of the subsequent answers.

Original languageEnglish (US)
Title of host publication2015 International Conference on Information Systems: Exploring the Information Frontier, ICIS 2015
PublisherAssociation for Information Systems
StatePublished - 2015
Externally publishedYes
Event2015 International Conference on Information Systems: Exploring the Information Frontier, ICIS 2015 - Fort Worth, United States
Duration: Dec 13 2015Dec 16 2015

Other

Other2015 International Conference on Information Systems: Exploring the Information Frontier, ICIS 2015
CountryUnited States
CityFort Worth
Period12/13/1512/16/15

Fingerprint

Online Communities
internet community
Health
health
Learning systems
Order effects
Online communities
Community-based
Text Mining
Machine Learning
evaluation

Keywords

  • Healthcare information systems
  • Information quality
  • Machine learning
  • Online communities
  • Text mining

ASJC Scopus subject areas

  • Computer Science Applications
  • Statistics, Probability and Uncertainty
  • Library and Information Sciences
  • Applied Mathematics

Cite this

Mousavi, R., Raghu, T. S., & Frey, K. (2015). Assessing order effects in online community-based health forums. In 2015 International Conference on Information Systems: Exploring the Information Frontier, ICIS 2015 Association for Information Systems.

Assessing order effects in online community-based health forums. / Mousavi, Reza; Raghu, T. S.; Frey, Keith.

2015 International Conference on Information Systems: Exploring the Information Frontier, ICIS 2015. Association for Information Systems, 2015.

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

Mousavi, R, Raghu, TS & Frey, K 2015, Assessing order effects in online community-based health forums. in 2015 International Conference on Information Systems: Exploring the Information Frontier, ICIS 2015. Association for Information Systems, 2015 International Conference on Information Systems: Exploring the Information Frontier, ICIS 2015, Fort Worth, United States, 12/13/15.
Mousavi R, Raghu TS, Frey K. Assessing order effects in online community-based health forums. In 2015 International Conference on Information Systems: Exploring the Information Frontier, ICIS 2015. Association for Information Systems. 2015
Mousavi, Reza ; Raghu, T. S. ; Frey, Keith. / Assessing order effects in online community-based health forums. 2015 International Conference on Information Systems: Exploring the Information Frontier, ICIS 2015. Association for Information Systems, 2015.
@inproceedings{a47f8314ff9844738e3690c0022e17e8,
title = "Assessing order effects in online community-based health forums",
abstract = "Measuring the quality of health content in online health forums has been a challenging task. The majority of the existing measures are based on nonprofessional evaluations of forum users and may not be reliable. We employed machine learning techniques, text mining methods, and Big Data platforms to construct four measures of textual quality to automatically determine the similarity of a given answer to professional answers. We then used these measures to assess the quality of 66,888 answers posted on Yahoo! Answers Health section. All four measures of textual quality revealed a higher quality for asker-selected best answers indicating that askers, to some extent, have a proper judgment to select the best answers. We also studied the presence of order effects in online health forums. Our results suggest that the textual quality of the first answer positively influences the mean textual quality of the subsequent answers and negatively influences the quantity of the subsequent answers.",
keywords = "Healthcare information systems, Information quality, Machine learning, Online communities, Text mining",
author = "Reza Mousavi and Raghu, {T. S.} and Keith Frey",
year = "2015",
language = "English (US)",
booktitle = "2015 International Conference on Information Systems: Exploring the Information Frontier, ICIS 2015",
publisher = "Association for Information Systems",

}

TY - GEN

T1 - Assessing order effects in online community-based health forums

AU - Mousavi, Reza

AU - Raghu, T. S.

AU - Frey, Keith

PY - 2015

Y1 - 2015

N2 - Measuring the quality of health content in online health forums has been a challenging task. The majority of the existing measures are based on nonprofessional evaluations of forum users and may not be reliable. We employed machine learning techniques, text mining methods, and Big Data platforms to construct four measures of textual quality to automatically determine the similarity of a given answer to professional answers. We then used these measures to assess the quality of 66,888 answers posted on Yahoo! Answers Health section. All four measures of textual quality revealed a higher quality for asker-selected best answers indicating that askers, to some extent, have a proper judgment to select the best answers. We also studied the presence of order effects in online health forums. Our results suggest that the textual quality of the first answer positively influences the mean textual quality of the subsequent answers and negatively influences the quantity of the subsequent answers.

AB - Measuring the quality of health content in online health forums has been a challenging task. The majority of the existing measures are based on nonprofessional evaluations of forum users and may not be reliable. We employed machine learning techniques, text mining methods, and Big Data platforms to construct four measures of textual quality to automatically determine the similarity of a given answer to professional answers. We then used these measures to assess the quality of 66,888 answers posted on Yahoo! Answers Health section. All four measures of textual quality revealed a higher quality for asker-selected best answers indicating that askers, to some extent, have a proper judgment to select the best answers. We also studied the presence of order effects in online health forums. Our results suggest that the textual quality of the first answer positively influences the mean textual quality of the subsequent answers and negatively influences the quantity of the subsequent answers.

KW - Healthcare information systems

KW - Information quality

KW - Machine learning

KW - Online communities

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=84964680497&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964680497&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84964680497

BT - 2015 International Conference on Information Systems: Exploring the Information Frontier, ICIS 2015

PB - Association for Information Systems

ER -