Toward predicting social support needs in online health social networks

Min Je Choi, Sung Hee Kim, Sukwon Lee, Bum Chul Kwon, Ji Soo Yi, Jaegul Choo, Jina Huh

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Background: While online health social networks (OHSNs) serve as an effective platform for patients to fulfill their various social support needs, predicting the needs of users and providing tailored information remains a challenge. Objective: The objective of this study was to discriminate important features for identifying users' social support needs based on knowledge gathered from survey data. This study also provides guidelines for a technical framework, which can be used to predict users' social support needs based on raw data collected from OHSNs. Methods: We initially conducted a Web-based survey with 184 OHSN users. From this survey data, we extracted 34 features based on 5 categories: (1) demographics, (2) reading behavior, (3) posting behavior, (4) perceived roles in OHSNs, and (5) values sought in OHSNs. Features from the first 4 categories were used as variables for binary classification. For the prediction outcomes, we used features from the last category: the needs for emotional support, experience-based information, unconventional information, and medical facts. We compared 5 binary classifier algorithms: gradient boosting tree, random forest, decision tree, support vector machines, and logistic regression. We then calculated the scores of the area under the receiver operating characteristic (ROC) curve (AUC) to understand the comparative effectiveness of the used features. Results: The best performance was AUC scores of 0.89 for predicting users seeking emotional support, 0.86 for experience-based information, 0.80 for unconventional information, and 0.83 for medical facts. With the gradient boosting tree as our best performing model, we analyzed the strength of individual features in predicting one's social support need. Among other discoveries, we found that users seeking emotional support tend to post more in OHSNs compared with others. Conclusions: We developed an initial framework for automatically predicting social support needs in OHSNs using survey data. Future work should involve nonsurvey data to evaluate the feasibility of the framework. Our study contributes to providing personalized social support in OHSNs.

Original languageEnglish
Article numbere272
JournalJournal of medical Internet research
Volume19
Issue number8
DOIs
Publication statusPublished - 2017 Aug 1

Fingerprint

Social Support
Health
Area Under Curve
Decision Trees
ROC Curve
Reading
Logistic Models
Demography
Guidelines

Keywords

  • Gradient boosting trees
  • Machine learning
  • Online health community
  • Online health social network
  • Prediction models
  • Social media

ASJC Scopus subject areas

  • Health Informatics

Cite this

Toward predicting social support needs in online health social networks. / Choi, Min Je; Kim, Sung Hee; Lee, Sukwon; Kwon, Bum Chul; Yi, Ji Soo; Choo, Jaegul; Huh, Jina.

In: Journal of medical Internet research, Vol. 19, No. 8, e272, 01.08.2017.

Research output: Contribution to journalArticle

Choi, Min Je ; Kim, Sung Hee ; Lee, Sukwon ; Kwon, Bum Chul ; Yi, Ji Soo ; Choo, Jaegul ; Huh, Jina. / Toward predicting social support needs in online health social networks. In: Journal of medical Internet research. 2017 ; Vol. 19, No. 8.
@article{0c027855b1784bfba2b7403166c4147b,
title = "Toward predicting social support needs in online health social networks",
abstract = "Background: While online health social networks (OHSNs) serve as an effective platform for patients to fulfill their various social support needs, predicting the needs of users and providing tailored information remains a challenge. Objective: The objective of this study was to discriminate important features for identifying users' social support needs based on knowledge gathered from survey data. This study also provides guidelines for a technical framework, which can be used to predict users' social support needs based on raw data collected from OHSNs. Methods: We initially conducted a Web-based survey with 184 OHSN users. From this survey data, we extracted 34 features based on 5 categories: (1) demographics, (2) reading behavior, (3) posting behavior, (4) perceived roles in OHSNs, and (5) values sought in OHSNs. Features from the first 4 categories were used as variables for binary classification. For the prediction outcomes, we used features from the last category: the needs for emotional support, experience-based information, unconventional information, and medical facts. We compared 5 binary classifier algorithms: gradient boosting tree, random forest, decision tree, support vector machines, and logistic regression. We then calculated the scores of the area under the receiver operating characteristic (ROC) curve (AUC) to understand the comparative effectiveness of the used features. Results: The best performance was AUC scores of 0.89 for predicting users seeking emotional support, 0.86 for experience-based information, 0.80 for unconventional information, and 0.83 for medical facts. With the gradient boosting tree as our best performing model, we analyzed the strength of individual features in predicting one's social support need. Among other discoveries, we found that users seeking emotional support tend to post more in OHSNs compared with others. Conclusions: We developed an initial framework for automatically predicting social support needs in OHSNs using survey data. Future work should involve nonsurvey data to evaluate the feasibility of the framework. Our study contributes to providing personalized social support in OHSNs.",
keywords = "Gradient boosting trees, Machine learning, Online health community, Online health social network, Prediction models, Social media",
author = "Choi, {Min Je} and Kim, {Sung Hee} and Sukwon Lee and Kwon, {Bum Chul} and Yi, {Ji Soo} and Jaegul Choo and Jina Huh",
year = "2017",
month = "8",
day = "1",
doi = "10.2196/jmir.7660",
language = "English",
volume = "19",
journal = "Journal of Medical Internet Research",
issn = "1439-4456",
publisher = "Journal of medical Internet Research",
number = "8",

}

TY - JOUR

T1 - Toward predicting social support needs in online health social networks

AU - Choi, Min Je

AU - Kim, Sung Hee

AU - Lee, Sukwon

AU - Kwon, Bum Chul

AU - Yi, Ji Soo

AU - Choo, Jaegul

AU - Huh, Jina

PY - 2017/8/1

Y1 - 2017/8/1

N2 - Background: While online health social networks (OHSNs) serve as an effective platform for patients to fulfill their various social support needs, predicting the needs of users and providing tailored information remains a challenge. Objective: The objective of this study was to discriminate important features for identifying users' social support needs based on knowledge gathered from survey data. This study also provides guidelines for a technical framework, which can be used to predict users' social support needs based on raw data collected from OHSNs. Methods: We initially conducted a Web-based survey with 184 OHSN users. From this survey data, we extracted 34 features based on 5 categories: (1) demographics, (2) reading behavior, (3) posting behavior, (4) perceived roles in OHSNs, and (5) values sought in OHSNs. Features from the first 4 categories were used as variables for binary classification. For the prediction outcomes, we used features from the last category: the needs for emotional support, experience-based information, unconventional information, and medical facts. We compared 5 binary classifier algorithms: gradient boosting tree, random forest, decision tree, support vector machines, and logistic regression. We then calculated the scores of the area under the receiver operating characteristic (ROC) curve (AUC) to understand the comparative effectiveness of the used features. Results: The best performance was AUC scores of 0.89 for predicting users seeking emotional support, 0.86 for experience-based information, 0.80 for unconventional information, and 0.83 for medical facts. With the gradient boosting tree as our best performing model, we analyzed the strength of individual features in predicting one's social support need. Among other discoveries, we found that users seeking emotional support tend to post more in OHSNs compared with others. Conclusions: We developed an initial framework for automatically predicting social support needs in OHSNs using survey data. Future work should involve nonsurvey data to evaluate the feasibility of the framework. Our study contributes to providing personalized social support in OHSNs.

AB - Background: While online health social networks (OHSNs) serve as an effective platform for patients to fulfill their various social support needs, predicting the needs of users and providing tailored information remains a challenge. Objective: The objective of this study was to discriminate important features for identifying users' social support needs based on knowledge gathered from survey data. This study also provides guidelines for a technical framework, which can be used to predict users' social support needs based on raw data collected from OHSNs. Methods: We initially conducted a Web-based survey with 184 OHSN users. From this survey data, we extracted 34 features based on 5 categories: (1) demographics, (2) reading behavior, (3) posting behavior, (4) perceived roles in OHSNs, and (5) values sought in OHSNs. Features from the first 4 categories were used as variables for binary classification. For the prediction outcomes, we used features from the last category: the needs for emotional support, experience-based information, unconventional information, and medical facts. We compared 5 binary classifier algorithms: gradient boosting tree, random forest, decision tree, support vector machines, and logistic regression. We then calculated the scores of the area under the receiver operating characteristic (ROC) curve (AUC) to understand the comparative effectiveness of the used features. Results: The best performance was AUC scores of 0.89 for predicting users seeking emotional support, 0.86 for experience-based information, 0.80 for unconventional information, and 0.83 for medical facts. With the gradient boosting tree as our best performing model, we analyzed the strength of individual features in predicting one's social support need. Among other discoveries, we found that users seeking emotional support tend to post more in OHSNs compared with others. Conclusions: We developed an initial framework for automatically predicting social support needs in OHSNs using survey data. Future work should involve nonsurvey data to evaluate the feasibility of the framework. Our study contributes to providing personalized social support in OHSNs.

KW - Gradient boosting trees

KW - Machine learning

KW - Online health community

KW - Online health social network

KW - Prediction models

KW - Social media

UR - http://www.scopus.com/inward/record.url?scp=85029375595&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029375595&partnerID=8YFLogxK

U2 - 10.2196/jmir.7660

DO - 10.2196/jmir.7660

M3 - Article

C2 - 28768609

AN - SCOPUS:85029375595

VL - 19

JO - Journal of Medical Internet Research

JF - Journal of Medical Internet Research

SN - 1439-4456

IS - 8

M1 - e272

ER -