This paper describes our approach to the CLPsych 2018 Shared Task, in which we attempted to predict cross-sectional psychological health at age 11 and future psychological distress based on childhood essays. We attempted several modeling approaches and observed best cross-validated prediction accuracy with relatively simple models based on psychological theory. The models provided reasonable predictions in most outcomes. Notably, our model was especially successful in predicting out-of-sample psychological distress (across people and across time) at age 50.
|Title of host publication||Proceedings of the Fifth Workshop on Computational Linguistics and Clinical Psychology: From Keyboard to Clinic|
|Place of Publication||New Orleans, LA|
|Publisher||Association for Computational Linguistics|
|Number of pages||6|
|State||Published - 1 Jun 2018|