The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Inferring Personality From Social Media User Behaviors Using Dense Net Convolutional Neural Networks
|
|
Author(s): Emilyn J. Jeba (Department of Information Technology, Sona College of Technology, Salem, India), M. Murali (Department of Information Technology, Sona College of Technology, Salem, India)and N. Prabakaran (School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India)
Copyright: 2024
Pages: 12
Source title:
Impact of AI on Advancing Women's Safety
Source Author(s)/Editor(s): Sivaram Ponnusamy (Sandip University, Nashik, India), Vibha Bora (G. H. Raisoni College of Engineering, Nagpur, India), Prema M. Daigavane (G. H. Raisoni College of Engineering, Nagpur, India)and Sampada S. Wazalwar (G. H. Raisoni College of Engineering, Nagpur, India)
DOI: 10.4018/979-8-3693-2679-4.ch011
Purchase
|
Abstract
We live in a world where social media is omnipresent and integrated into our daily lives. People love to express their interests, thoughts, and opinions on these social networking platforms. This information reveals several psychological aspects of their behavior and can be used to predict their personality. To predict this, introduce the method dense net convolutional neural network (DNCNN) is based on predicting the social media users' personality identification. Performed an experimental evaluation on a benchmark dataset for the task of categorizing personality traits into distinct classifications. The review of the dataset yields improved results, showing that the proposed model can really arrange client character attributes when contrasted with cutting-edge models. Posts and status updates can be used to predict the personality of users of social media networks to improve accuracy. These results show that picture features are better predictors of personality than text features, and also found that a profile picture reliably predicts personality with 96% accuracy.
Related Content
|
.
© 2026.
4 pages.
|
|
.
© 2026.
14 pages.
|
|
.
© 2026.
58 pages.
|
|
.
© 2026.
34 pages.
|
|
.
© 2026.
28 pages.
|
|
.
© 2026.
58 pages.
|
|
.
© 2026.
44 pages.
|
|
|