Abstract With the rise of social media such as Twitter, people are more willing to convey their stressful life events via these platforms. In a sense, it is feasible to detect stress from social media data for proactive health care. In psychology, stress is composed of stressor and stress level, where stressor further comprises of stressor event and subject. By far, little attention has been paid to estimate exact stressor and stress level from social media data, due to the following challenges: 1) stressor subject identification, 2) stressor event detection, and 3) data collection and representation. To address these problems, we devise a comprehensive scheme to measure a user’s stress level from his/her social media data. In particular, we first build a benchmark dataset and extract a rich set of stress-oriented features. We then propose a novel hybrid multi-task model to detect the stressor event and subject, which is capable of modeling the relatedness among stressor events as well as stressor subjects. At last, we lookup an expert-defined stress table with the detected subject and event to estimate the stressor and stress level. Extensive experiments on real-world datasets well verify the effectiveness of our scheme.