The Role of Features and Context on Suicide Ideation Detection
Published in Proceedings of the Australasian Language Technology Association Workshop 2016, 2016
There is a growing body of work studying suicide ideation, expressions of intentions to kill oneself, on social media. We explore the problem of detecting such ideation on Twitter, focusing on the impact of a set of features drawn from the literature and on the role of discussion context for this task. Our experiments show a significant improvement upon the previously published results for the O’Dea et al.(2015) dataset on suicide ideation. Interestingly, we found that stylistic features helped while social media metadata features did not. Furthermore, discussion context was useful. To further understand the contributions of these different features and of discussion context, we present a discussion of our experiments in varying the feature representations, and examining their effects on suicide ideation detection on Twitter.