EUVIMEDEUVIMED entdecken
Crossref

Twitter-based gender recognition using transformers

Zahra Movahedi Nia, Ali Ahmadi, Bruce Mellado, Jianhong Wu, James Orbinski, Ali Asgary, Jude D Kong

Mathematical Biosciences and Engineering · 2023 · 20 (9) · 15962-15981

DOI: 10.3934/mbe.2023711 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematical Biosciences and Engineering, 2023. Verfasst von Zahra Movahedi Nia und 6 weiteren Autor:innen. Beteiligte Einrichtung: Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), York University, Canada. Hauptthemen laut MEDLINE: Social Media. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 60 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Social media contains useful information about people and society that could help advance research in many different areas of health (e.g. by applying opinion mining, emotion/sentiment analysis and statistical analysis) such as mental health, health surveillance, socio-economic inequality and gender vulnerability. User demographics provide rich information that could help study the subject further. However, user demographics such as gender are considered private and are not freely available. In this study, we propose a model based on transformers to predict the user's gender from their images and tweets. The image-based classification model is trained in two different methods: using the profile image of the user and using various image contents posted by the user on Twitter. For the first method a Twitter gender recognition dataset, publicly available on Kaggle and for the second method the PAN-18 dataset is used. Several transformer models, i.e. vision transformers (ViT), LeViT and Swin Transformer are fine-tuned for both of the image datasets and then compared. Next, different transformer models, namely, bidirectional encoders representations from transformers (BERT), RoBERTa and ELECTRA are fine-tuned to recognize the user's gender by their tweets. This is highly beneficial, because not all users provide an image that indicates their gender. The gender of such users could be detected from their tweets. The significance of the image and text classification models were evaluated using the Mann-Whitney U test. Finally, the combination model improved the accuracy of image and text classification models by 11.73 and 5.26% for the Kaggle dataset and by 8.55 and 9.8% for the PAN-18 dataset, respectively. This shows that the image and text classification models are capable of complementing each other by providing additional information to one another. Our overall multimodal method has an accuracy of 88.11% for the Kaggle and 89.24% for the PAN-18 dataset and outperforms state-of-the-art models. Our work benefits research that critically require user demographic information such as gender to further analyze and study social media content for health-related issues.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Social MediaHumansElectric Power SuppliesResearch Design

Stichwörter der Autor:innen

BERTELECTRALeViTRoBERTaSwin transformerViTgender recognitionsocial mediatransformers

Autor:innen und Institutionen

  • Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC), York University, Canada.
  • Laboratory for Industrial and Applied Mathematics, York University, Canada.
  • K.N Toosi University, Faculty of Computer Engineering, Tehran, Iran.
  • Advanced Disaster, Emergency and Rapid-Response Simulation (ADERSIM), York University, Toronto, Ontario, Canada.
  • School of Physics, Institute for Collider Particle Physics, University of Witwatersrand, Johannesburg, South Africa.
  • Dahdaleh Institute for Global Health Research, York University, Canada.

Zitieren

APA

Nia, Z. M., Ahmadi, A., Mellado, B., Wu, J., Orbinski, J., Asgary, A., & Kong, J. D. (2023). Twitter-based gender recognition using transformers. Mathematical Biosciences and Engineering, 20(9), 15962-15981. https://doi.org/10.3934/mbe.2023711

Vancouver

Nia ZM, Ahmadi A, Mellado B, Wu J, Orbinski J, Asgary A, et al. Twitter-based gender recognition using transformers. Mathematical Biosciences and Engineering. 2023;20(9):15962-15981. doi:10.3934/mbe.2023711

BibTeX
@article{Nia2023,
  author = {Nia, Zahra Movahedi and Ahmadi, Ali and Mellado, Bruce and Wu, Jianhong and Orbinski, James and Asgary, Ali and Kong, Jude D},
  title = {Twitter-based gender recognition using transformers},
  journal = {Mathematical Biosciences and Engineering},
  year = {2023},
  volume = {20},
  number = {9},
  pages = {15962--15981},
  doi = {10.3934/mbe.2023711}
}
Kostenlos starten →