Abstract Online users have generated a large amount of health-related data on medical forums and search engines. However, exploiting these rich data for orienting patient online and assisting medical checkup offline is nontrivial due to the sparseness of existing symptom-disease links, which caused by the natural and chatty expressions of symptoms. In this paper, we propose a novel and general representation learning method C ONTEXT C ARE for human generated health-related data, which learns latent relationship between symptoms and diseases from the symptom-disease diagnosis network for disease prediction, disease category prediction and disease clustering. To alleviate the network sparseness, C ONTEXT C ARE adopts regularizations from rich contextual information networks including a symptom co-occurrence network and a disease evolution network. Extensive experiments on medical forum data demonstrate that C ONTEXT C ARE outperforms the state-of-the-art methods in respects.