Stress is a mental state involving emotional strain and tension resulting from adverse or demanding circumstances. Individuals in academic campuses, particularly students often go through periods of stress throughout the academic calendar. Additionally, extreme events involving violence, such as shooting, mass stabbing, or terrorist attack in college campuses, induces fear, resulting in increased stress among the campus population, which gets reflected on their social media activities. In this study, we propose to analyze how different campus population collectively react to such adverse events, using a causal inference based technique. We choose 8 violent incidents that occurred in US college campuses in the last four years, including the 2015 Chapel Hill Shooting, 2016 UCLA Shooting, and 2016 OSU Attack. Building a machine learning classifier of stress, which uses language models and expert validation, we also aim to identify the language cues for the expression of stress on social media.
The SocWeB Lab's mission is to develop novel computational techniques, and technologies powered by these techniques, to responsibly and ethically employ social media in quantifying, understanding, and improving our mental health and well-being.