Abstract: A crisis (e.g. suicide, self-harm, abuse, or eating disorders) is any event that is going (or is expected) to lead to an unstable and dangerous situation affecting an individual, group, community, or whole society. It is very difficult to automatically and accurately detect crisis from social media text due to the commplexity of identifying crisis states. However, detecting a general state of crisis without explaining why has limited applications. An explanation in this context a coherent, concise subset of the text that rationalizes the crisis detection. Explore several methods to detect and explain crisis using a combination of neural and non-neural techniques. Evaluate these techniques on different dataset obtained from different platforms.

Keywords: Natural Language Processing, Support Vector Machine (SVM), Linguistic Inquiry & Word Count (LIWC)