TY - GEN
T1 - Predicting Continued Participation in Online Health Forums
AU - Sadeque, Farig
AU - Solorio, Thamar
AU - Pedersen, Ted
AU - Shrestha, Prasha
AU - Bethard, Steven
N1 - Funding Information:
We would like to thank Binod Gyawali who did the initial data gathering and data coding.
Publisher Copyright:
© 2015 Association for Computational Linguistics.
PY - 2015
Y1 - 2015
N2 - Online health forums provide advice and emotional solace to their users from a social network of people who have faced similar conditions. Continued participation of users is thus critical to their success. In this paper, we develop machine learning models for predicting whether or not a user will continue to participate in an online health forum. The prediction models are trained and tested over a large dataset collected from the support group based social networking site dailystrength.org. We find that our models can predict continued participation with over 83% accuracy after as little as 1 month observing the user's activities, and that performance increases rapidly up to 1 year of observation. We also show that features such as the time since a user's last activity are consistently predictive regardless of the length of the observation period, while other features, such as the number of times a user replies to others, decrease in predictiveness as the observation period grows.
AB - Online health forums provide advice and emotional solace to their users from a social network of people who have faced similar conditions. Continued participation of users is thus critical to their success. In this paper, we develop machine learning models for predicting whether or not a user will continue to participate in an online health forum. The prediction models are trained and tested over a large dataset collected from the support group based social networking site dailystrength.org. We find that our models can predict continued participation with over 83% accuracy after as little as 1 month observing the user's activities, and that performance increases rapidly up to 1 year of observation. We also show that features such as the time since a user's last activity are consistently predictive regardless of the length of the observation period, while other features, such as the number of times a user replies to others, decrease in predictiveness as the observation period grows.
UR - http://www.scopus.com/inward/record.url?scp=85011822500&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85011822500&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85011822500
T3 - EMNLP 2015 - 6th International Workshop on Health Text Mining and Information Analysis, LOUHI 2015 - Proceedings of the Workshop
SP - 12
EP - 20
BT - EMNLP 2015 - 6th International Workshop on Health Text Mining and Information Analysis, LOUHI 2015 - Proceedings of the Workshop
PB - Association for Computational Linguistics (ACL)
T2 - 6th International Workshop on Health Text Mining and Information Analysis, LOUHI 2015, co-located with EMNLP 2015
Y2 - 17 September 2015
ER -