Tweets to Traits: An Ensemble Approach

View at publisher Summarise with VIRAT
Authors: Gayatri Gamini, Achyuth Kasyap P, Janviba Dharmendrasinh Gohil, Utkarsh Mishra, Avinash Chandra Pandey
Cited by: 0
References: 12

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Artificial intelligence has transformed social media sites like Twitter, making them useful tools for smart personality prediction. While transformer models like BERT and RoBERTa provide solid results, they tend to be computationally expensive, slower to train and suffer from imbalanced data. To mitigate these limitations, this paper proposes a hybrid ensemble strategy that leverages powerful contextual representations from transformers alongside the efficiency and speed of machine learning methods. Not only does this approach reduce computation time and memory complexity, but it also enhances robustness and scalability. Experimental results on Twitter data prove that the suggested model performs better than previous methods, with 90% accuracy and 91% precision, illustrating its efficiency in predicting personality characteristics based on social media content.

Fields of Study & Subjects

Mental Health via Writing Authorship Attribution and Profiling Sentiment Analysis and Opinion Mining

Publication details

Journal / source
International Conference on Computing, Communication, Control and Cyber-Physical Systems (I5CPS)
Pages
1–8
Publication date
26 February 2026
Language
EN