T\"ubingen-Oslo system: Linear regression works the best at Predicting Current and Future Psychological Health from Childhood Essays in the CLPsych 2018 Shared Task

TL;DR

This study evaluates various models for predicting psychological health from childhood essays, finding that L2 regularized linear regression outperforms more complex models in accuracy.

Contribution

The paper demonstrates that simple linear regression models can outperform complex neural networks in predicting psychological health from childhood essays.

Findings

L2 regularized linear regression achieved the best results.

Linear regression outperformed recurrent and convolutional neural networks.

The approach was effective for both current and future psychological health prediction.

Abstract

This paper describes our efforts in predicting current and future psychological health from childhood essays within the scope of the CLPsych-2018 Shared Task. We experimented with a number of different models, including recurrent and convolutional networks, Poisson regression, support vector regression, and L1 and L2 regularized linear regression. We obtained the best results on the training/development data with L2 regularized linear regression (ridge regression) which also got the best scores on main metrics in the official testing for task A (predicting psychological health from essays written at the age of 11 years) and task B (predicting later psychological health from essays written at the age of 11).