Deep Bag-of-Sub-Emotions for Depression Detection in Social Media

TL;DR

This paper introduces DeepBoSE, a deep learning model that enhances depression detection in social media by integrating emotional features into a differentiable Bag-of-Features framework, improving performance over traditional methods.

Contribution

The paper proposes a novel deep model that combines emotional information with a differentiable Bag-of-Features approach, enabling transfer learning for depression detection.

Findings

DeepBoSE outperforms conventional Bag-of-Features models.

Achieves F1-score over 0.64 on eRisk17 and 0.65 on eRisk18 datasets.

Competitive with state-of-the-art depression detection methods.

Abstract

This paper presents the Deep Bag-of-Sub-Emotions (DeepBoSE), a novel deep learning model for depression detection in social media. The model is formulated such that it internally computes a differentiable Bag-of-Features (BoF) representation that incorporates emotional information. This is achieved by a reinterpretation of classical weighting schemes like term frequency-inverse document frequency into probabilistic deep learning operations. An important advantage of the proposed method is that it can be trained under the transfer learning paradigm, which is useful to enhance conventional BoF models that cannot be directly integrated into deep learning architectures. Experiments were performed in the eRisk17 and eRisk18 datasets for the depression detection task; results show that DeepBoSE outperforms conventional BoF representations and it is competitive with the state of the art, achieving a F1-score over the positive class of 0.64 in eRisk17 and 0.65 in eRisk18.