Our paper on identifying features critical for predicting social support needs in online health communities have been accepted to the Journal of Medical Internet Research.
Min-Je Choi, Sung-Hee Kim, Sukwon Lee, et al. 2017. Toward Predicting Social Support Needs in Online Health Social Networks. Journal of Medical Internet Research (forthcoming). http://doi.org/10.2196/jmir.7660
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 is 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 an online survey with 184 OHSN users. From this survey data, we extracted 34 features based on five categories: (1) demographics, (2) reading behavior, (3) posting behavior, (4) perceived roles in OHSNs, and (5) values sought in OHSNs. Features from the first four 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 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 discovered that users seeking emotional support tend to post more in OHSNs compared to others.
Conclusions: We developed an initial framework for automatically predicting social support needs in OHSNs using survey data. Future work should involve non-survey data to evaluate the feasibility of the framework. Our study contributes to providing personalized social support in OHSNs.