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

Juan S. Lara, Mario Ezra Aragón, Fabio A. González, Manuel Montes-y-Gómez

Abstract: This paper presents 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 tf-idf into probabilistic deep learning operations. An 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 on the eRisk17 and eRisk18 datasets for the depression detection task show that DeepBoSE outperforms conventional BoF representations and is competitive with the state of the art methods.