Depression Detection via Harvesting Social Media: A Multimodal Dictionary Learning Solution

Authors: Guangyao Shen, Jia Jia, Liqiang Nie, Fuli Feng, Cunjun Zhang, Tianrui Hu, Tat-Seng Chua, Wenwu Zhu

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental A series of experiments are conducted to validate this model, which outperforms (+3% to +10%) several baselines.
Researcher Affiliation Academia 1Department of Computer Science and Technology, Tsinghua University; TNList 2 Department of Computer Science and Technology, Shandong University 3 School of Computing, National University of Singapore 4School of Information and Communication Engineering, Beijing University of Posts and Telecommunications
Pseudocode No The paper provides mathematical formulations and descriptions of algorithms in text, but no explicit pseudocode blocks or algorithm figures are present.
Open Source Code No The paper states: 'In addition, we release these datasets3 with features to facilitate wellness study for computer science and psychology.' with footnote '3http://depressiondetection.droppages.com/.' While datasets and features are mentioned as released, there is no explicit statement or link confirming the release of the source code for the methodology described in the paper.
Open Datasets Yes We construct benchmark datasets for online depression detection and analysis, including the well-labeled depression and non-depression datasets as well as a large-scale depression-candidate dataset. In addition, we release these datasets3 with features to facilitate wellness study for computer science and psychology. 3http://depressiondetection.droppages.com/.
Dataset Splits Yes We trained and tested these methods under 5-fold cross validation, with over 10 randomized experimental runs.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory, cloud instances) used for running the experiments.
Software Dependencies No The paper mentions several software tools and libraries like Porter Stemmer, word2vec, NLTK toolbox, LIWC, LDA model, and Naive Bayesian (Pedregosa et al., 2011 refers to scikit-learn), but it does not specify version numbers for these software components, which are required for reproducible descriptions.
Experiment Setup Yes There are three key parameters in the MDL: two regularization parameters, λ in Eqn.(3) and p in Eqn.(5), as well as an implicit parameter D. The search range for λ, p, and D are [0.001, 0.04], [10 5, 10 1], and [50, 200], respectively. ... We finally observed that MDL reached the optimal performance when λ = 0.007, p = 10 2.5, and D = 130.