A two-step approach for the prediction of mood levels based on diary data

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Authors

The analysis of diary data can increase insights into patients suffering from mental disorders and can help to personalize online interventions. We propose a two-step approach for such an analysis. We first categorize free text diary data into activity categories by applying a bag-of-words approach and explore recurrent neuronal networks to support this task. In a second step, we develop partial ordered logit models with varying levels of heterogeneity among clients to predict their mood. We estimate the parameters of these models by employing MCMC techniques and compare the models regarding their predictive performance. This two-step approach leads to an increased interpretability about the relationships between various activity categories and the individual mood level.

OriginalspracheEnglisch
TitelMachine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2018, Proceedings : European Conference, ECML PKDD 2018, Dublin, Ireland
HerausgeberUlf Brefeld, Edward Curry, Elizabeth Daly, Brian MacNamee, Alice Marascu, Fabio Pinelli, Michele Berlingerio, Neil Hurley
Anzahl der Seiten4
ErscheinungsortCham
VerlagSpringer International Publishing
Erscheinungsdatum2019
Seiten626-629
ISBN (Print)978-3-030-10996-7
ISBN (elektronisch)978-3-030-10997-4
DOIs
PublikationsstatusErschienen - 2019
VeranstaltungEuropean Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases - ECML PKDD 2018 - Dublin, Irland
Dauer: 10.09.201814.09.2018
http://www.ecmlpkdd2018.org/

Bibliographische Notiz

weiterer Autor: Tobias Genz, Institut für Wirtschaftsinformatik, Leuphana Universität Lüneburg, Germany

DOI

Zuletzt angesehen

Publikationen

  1. Modeling and Performance Analysis of a Node in Fault Tolerant Wireless Sensor Networks
  2. Evaluating OWL 2 reasoners in the context of checking entity-relationship diagrams during software development
  3. Using trait-based filtering as a predictive framework for conservation
  4. A Multivariate Method for Dynamic System Analysis
  5. Authenticity and authentication in language learning
  6. Supervised clustering of streaming data for email batch detection
  7. Modified dynamic programming approach for offline segmentation of long hydrometeorological time series
  8. A geometric algorithm for the output functional controllability in general manipulation systems and mechanisms
  9. Analysis of Complexity Reduction in Kalman Filters Through Decoupling Control With Chattered Inputs in PMSM
  10. Substructure, subgraph, and walk counts as measures of the complexity of graphs and molecules.
  11. Modeling precipitation kinetics for multi-phase and multi-component systems using particle size distributions via a moving grid technique
  12. Using haar wavelets for fault detection in technical processes
  13. Homogenization modeling of thin-layer-type microstructures
  14. Multi-view learning with dependent views
  15. Machine Learning and Knowledge Discovery in Databases
  16. Model inversion using fuzzy neural network with boosting of the solution
  17. Using Complexity Metrics to Assess Silent Reading Fluency
  18. Comparing the Sensitivity of Social Networks, Web Graphs, and Random Graphs with Respect to Vertex Removal
  19. Computational modeling of material flow networks
  20. A coding scheme to analyse global text processing in computer supported collaborative learning: What eye movements can tell us
  21. Reading and Calculating in Word Problem Solving
  22. XOperator - An extensible semantic agent for instant messaging networks
  23. Microstructural development of as-cast AM50 during Constrained Friction Processing: grain refinement and influence of process parameters
  24. A multi input sliding mode control for Peltier Cells using a cold-hot sliding surface
  25. Classical PI Controllers with Anti-Windup Techniques Applied on Level Systems