EUVIMEDEUVIMED entdecken
Crossref

Rethink data-driven human behavior prediction: A Psychology-powered Explainable Neural Network

Jiyao Wang, Chunxi Huang, Weiyin Xie, Dengbo He, Ran Tu

Computers in Human Behavior · 2024-07 · 156 · 108245

DOI: 10.1016/j.chb.2024.108245 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers in Human Behavior, 2024-07. Verfasst von Jiyao Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: Guangzhou Municipal Science and Technology Bureau.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human behavior prediction is a rapidly evolving field with numerous applications in various domains.Therapiddevelopmentofmachinelearningfacilitatesresearchondata-drivenbehavior prediction.Atthesametime,inhumanfactorsdomains,researchersstillfocusonmodelingpsychologicaldecision-makingprocessesfromthepsychologicalperspectivesofviewbased onsubjectivedata.However,itisdi � cult to obtain one’s psychological states in real-world scenarios, given that the collection of subjective data in real-world settings is di � cult and intrusive. Thus, psychology theories can hardly be applied to behavior prediction directly. To bridge the gap between data-driven behavior prediction and psychological decision-making models, we proposed a novel Psychology-powered Explainable Neural network (PEN). In PEN, for the first time, the psychological factors of individuals (i.e., human-side features such as attitudes to technologies) are modeled and recovered explicitly based on one’s historical behaviorsincertainscenarios.Themulti-taskoptimizationensureseachcomponentinPENtobe optimizedwithpropergradient.Assessmentresultsoverthreeevaluationprotocolsdemonstratethat,basedonthehistoricalbehaviorsofanindividualonly,thePENcanoutperformthebest existingbehaviorpredictionmodelsby1.87%and4.68%ontwodatasetswhena1:9training-testingdatapartitionwasadopted.TheframeworkinPENhasprovidedanewsolutionfor explainablehumanbehaviorpredictionwhenpsychologicalinformationisnotdirectlyavailable.

Förderung

  • Guangzhou Municipal Science and Technology Bureau

Zitieren

APA

Wang, J., Huang, C., Xie, W., He, D., & Tu, R. (2024). Rethink data-driven human behavior prediction: A Psychology-powered Explainable Neural Network. Computers in Human Behavior, 156, 108245. https://doi.org/10.1016/j.chb.2024.108245

Vancouver

Wang J, Huang C, Xie W, He D, Tu R. Rethink data-driven human behavior prediction: A Psychology-powered Explainable Neural Network. Computers in Human Behavior. 2024;156:108245. doi:10.1016/j.chb.2024.108245

BibTeX
@article{Wang2024,
  author = {Wang, Jiyao and Huang, Chunxi and Xie, Weiyin and He, Dengbo and Tu, Ran},
  title = {Rethink data-driven human behavior prediction: A Psychology-powered Explainable Neural Network},
  journal = {Computers in Human Behavior},
  year = {2024},
  volume = {156},
  pages = {108245},
  doi = {10.1016/j.chb.2024.108245}
}
Kostenlos starten →