Toward Predicting Social Support Needs in Online Health Social Networks.

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

doi:10.2196/jmir.7660

Abstract

BackgroundWhile 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.ObjectiveThe 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.MethodsWe 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.ResultsThe 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.ConclusionsWe 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.

Highlights

The social support model [1,2] received substantial interest in the field of medical informatics
gradient boosting tree (GBT) consistently produced superior Area under receiver operating characteristic (ROC) curve (AUC) scores compared with others, except for predicting emotional support where it ranked second to support vector machines (SVM)
To provide a better understanding on which features are of actual importance, we devoted the rest of this section to interpreting the results of these AUC scores

Summary

Introduction

The social support model [1,2] received substantial interest in the field of medical informatics. Medical facts refer to traditional medical information, such as experiments and other statistical data as well as published writings on illnesses and treatments, such as a doctor’s online blog Patients have their own social support needs, and correctly understanding social support needs and providing adequate measures has positive effects on patients of both mental and physical conditions [10,11,12]. We used features from the last category: the needs for emotional support, experience-based information, unconventional information, and medical facts. 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. Our study contributes to providing personalized social support in OHSNs

Objectives

Methods

Results

Discussion

Conclusion