Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A multi-task learning-based fully connected neural network for personalized news recommendation.

ZhuoMin Ren1, Hong Xie2

  • 1Shaanxi Fashion Engineering University, Xian City, 710000, China. 1029012593@qq.com.

Scientific Reports
|June 17, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Honokiol ameliorates angiotensin II-induced cardiac hypertrophy by promoting dissociation of the Nur77-LKB1 complex and activating the AMPK pathway.

Journal of cellular and molecular medicine·2023
Same author

miR-HCC2 suppresses hepatitis B virus replication by inhibiting the activity of the enhancer I/X promoter.

Archives of virology·2023
Same author

Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium.

NeuroImage·2023
Same author

Genomic Epidemiology of Treponema pallidum and Circulation of Strains With Diminished tprK Antigen Variation Capability in Seattle, 2021-2022.

The Journal of infectious diseases·2023
Same author

SALL1 promotes proliferation and metastasis and activates phosphorylation of p65 and JUN in colorectal cancer cells.

Pathology, research and practice·2023
Same author

Mycotoxin Determination in Peaches and Peach Products with a Modified QuEChERS Extraction Procedure Coupled with UPLC-MS/MS Analysis.

Foods (Basel, Switzerland)·2023
Same journal

Correction: A method for supervoxel-wise association studies of age and other non-imaging variables from coronary computed tomography angiograms.

Scientific reports·2026
Same journal

Poly(bromophenol blue)/CoSn(OH)<sub>6</sub> cubic particles modified pencil graphite electrode for electrochemical determination of diphenhydramine.

Scientific reports·2026
Same journal

Dietary Chlorella, Spirulina, and acidifier modulate jejunal cytokine-related gene expression in broiler chickens.

Scientific reports·2026
Same journal

Perceived physical activity barriers in university students: associations with fatigue and eating behaviours.

Scientific reports·2026
Same journal

Refuge limitation structures habitat use in agricultural landscapes: evidence from Sunda pangolins.

Scientific reports·2026
Same journal

Lightweight stateless transaction verification with outsourced witness updates for UTXO blockchains.

Scientific reports·2026
See all related articles

This study introduces a novel Fully Connected Neural Network (MT-FCNN) model to enhance personalized news recommendations by better capturing dynamic user interests and improving accuracy, especially for new users. The new model significantly outperforms existing methods in key performance metrics.

Area of Science:

  • Artificial Intelligence
  • Computer Science
  • Information Retrieval

Background:

  • Traditional personalized news recommendation systems struggle with dynamic user interests, accuracy-diversity balance, and cold-start performance.
  • Existing methods often fail to effectively model the evolving nature of user preferences and encounter significant performance drops in new user scenarios.

Purpose of the Study:

  • To propose a novel Personalized News Recommendation Model via a Fully Connected Neural Network (MT-FCNN) to overcome the limitations of traditional methods.
  • To enhance the modeling of dynamic user interests and improve recommendation accuracy and diversity, particularly in cold-start situations.

Main Methods:

  • Developed a Fully Connected Neural Network (MT-FCNN) model incorporating user behavior sequence embeddings.
Keywords:
Fully Connected Neural NetworkMulti-Task Learningpersonalized news recommendationrecommendation system optimizationuser behavior modeling

Related Experiment Videos

  • Implemented a multi-task learning framework to jointly optimize click intention prediction and interest distribution learning within a unified representation space.

    • Main Results:

    • MT-FCNN demonstrated significant improvements: AUC increased by 12.4%, NDCG@5 by 10.7%, and CTR by 8.9% compared to established approaches.
    • Recommendation accuracy for cold-start users (Precision@5) improved by 11.2%.
    • Experimental results on the Microsoft News Dataset confirmed the model's stability and superior performance through repeated experiments and statistical tests.

    Conclusions:

    • The proposed MT-FCNN model offers a new methodological perspective for recommendation systems by effectively modeling dynamic user behavior.
    • This approach provides a more efficient technological solution for personalized news recommendation, addressing key challenges in the field.