EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Enhanced MIBKA-CNN-BiLSTM Model for Fake Information Detection

Sining Zhu, Guangyu Mu iD, Jie Ma, Xiurong Li iD

Biomimetics · 23.08.2025 · 10 (9) · 562

DOI: 10.3390/biomimetics10090562 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomimetics, online erschienen am 23.08.2025. Verfasst von Sining Zhu und 3 weiteren Autor:innen. Beteiligte Einrichtung: International Business School, Jilin International Studies University, Changchun 130117, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Social Science Fund of China, the Natural Science Fund Project of the Science and Technology Department of Jilin Province, the Pioneering Project of Jilin University of Finance and Economics.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The complexity of fake information and the inefficiency of parameter optimization in detection models present dual challenges for current detection technologies. Therefore, this paper proposes a hybrid detection model named MIBKA-CNN-BiLSTM, which significantly improves detection accuracy and efficiency through a triple-strategy enhancement of the Black Kite Optimization Algorithm (MIBKA) and an optimized dual-channel deep learning architecture. First, three improvements are introduced in the MIBKA. The population initialization process is restructured using circle chaotic mapping to enhance parameter space coverage. The conventional random perturbation is replaced by a random-to-elite differential mutation strategy (DE/rand-to-best/1) to balance global exploration and local exploitation. Moreover, a logarithmic spiral opposition-based learning (LSOBL) mechanism is integrated to dynamically explore the opposition solution space. Second, a CNN-BiLSTM dual-channel feature extraction network is constructed, with hyperparameters such as the number of convolutional kernels and LSTM units optimized by MIBKA to enable adaptive model structure alignment with task requirements. Finally, a high-quality fake information dataset is created based on social media platforms, including CCTV. The experimental results show that our model achieves the highest accuracy on the self-built dataset, which is 3.11% higher than the optimal hybrid model. Additionally, on the Weibo21 dataset, our model’s accuracy and F1-score increased by 1.52% and 1.71%, respectively, compared to the average values of all baseline models. These findings offer a practical and effective approach for detecting lightweight and robust false information.

Schlagwörter

Stichwörter der Autor:innen

black kite optimization algorithmdual-channelfake information detectionhybrid modelsocial media platforms

Autor:innen und Institutionen

  • International Business School, Jilin International Studies University, Changchun 130117, China.
  • School of Management Science and Information Engineering, Jilin University of Finance and Economics, Changchun 130117, China.
  • Office of Scientific Research, Jilin University of Finance and Economics, Changchun 130117, China.
  • Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.

ORCID-Profile: Guangyu Mu, Xiurong Li

Förderung

  • the National Social Science Fund of China
  • the Natural Science Fund Project of the Science and Technology Department of Jilin Province
  • the Pioneering Project of Jilin University of Finance and Economics
  • National Social Science Fund of China
  • Natural Science Fund Project of the Science and Technology Department of Jilin Province
  • Pioneering Project of Jilin University of Finance and Economics

Zitieren

APA

Zhu, S., Mu, G., Ma, J., & Li, X. (2025). An Enhanced MIBKA-CNN-BiLSTM Model for Fake Information Detection. Biomimetics, 10(9), 562. https://doi.org/10.3390/biomimetics10090562

Vancouver

Zhu S, Mu G, Ma J, Li X. An Enhanced MIBKA-CNN-BiLSTM Model for Fake Information Detection. Biomimetics. 2025;10(9):562. doi:10.3390/biomimetics10090562

BibTeX
@article{Zhu2025,
  author = {Zhu, Sining and Mu, Guangyu and Ma, Jie and Li, Xiurong},
  title = {An Enhanced MIBKA-CNN-BiLSTM Model for Fake Information Detection},
  journal = {Biomimetics},
  year = {2025},
  volume = {10},
  number = {9},
  pages = {562},
  doi = {10.3390/biomimetics10090562}
}
Kostenlos starten →