Desigualdade educacional e fatores socioeconômicos uma análise com decomposição PARAFAC dos dados do ENEM 2022-2023

Lara Carla Freitas Rodrigues; Luiza Helena Félix de Andrade; Sílvio Roberto Fernandes

doi:10.1590/SciELOPreprints.18791

##article.authors##

Lara Carla Freitas Rodrigues Federal Rural University of Semi-Árido https://orcid.org/0009-0000-6666-7519
- Formal Analysis
- Methodology
- Resources
- Data Curation
Luiza Helena Félix de Andrade Federal Rural University of Semi-Árido https://orcid.org/0000-0002-2255-2194
- Conceptualization
- Funding Acquisition
- Supervision
- Validation
- Writing – Review & Editing
Sílvio Roberto Fernandes Federal Rural University of Semi-Árido https://orcid.org/0000-0001-7300-8423
- Supervision
- Validation
- Writing – Review & Editing

DOI:

https://doi.org/10.1590/SciELOPreprints.18791

Keywords:

academic performance, socioeconomic factors, educational policies

Abstract

This research sought to understand which socioeconomic factors most impacted the performance of Brazilian high school students in 2022 and 2023, using microdata from the National Senior High School Exam (ENEM) provided by the Anísio Teixeira National Institute for Educational Studies and Research (INEP). Only participants who completed all tests and were not "mock candidates" (non-graduating students) were considered. The sample was segmented into two proficiency groups based on the annual average: those equal to or above the average formed the high-performance group, and those below the average, the low-performance group. The data were structured into a third-order tensor (candidates × questions × proficiency) and analyzed through Parallel Factor Analysis (PARAFAC) decomposition, supported by computational tools in Python. The results revealed that factors external to the school environment, especially family income and parental education level, were the most determinant for proficiency, providing evidence for the formulation of public policies that address inequalities and promote greater social equity.

Downloads

Download data is not yet available.

Author Biographies

Lara Carla Freitas Rodrigues, Federal Rural University of Semi-Árido

Graduated with a degree in Building Technology from IFRN in 2022. She holds a bachelor’s degree in Science and Technology from UFERSA and is currently pursuing a bachelor’s degree in Electrical Engineering at UFERSA. She participated in the Sinergy Jr. outreach project between 2023 and 2024 and was a scholarship recipient in the Basic Learning Development (DAB) program at UFERSA in 2023. She was a PIBIC fellow (2023–2024) and a PICI fellow from 2024 to 2025, during which time she conducted research on the application of the PARAFAC dimensionality reduction method to educational data. She continues to pursue her research as a PIBIC fellow, now focusing on the field of antennas, and participates as a volunteer in the Green Hydrogen research group at UFERSA.

Luiza Helena Félix de Andrade, Federal Rural University of Semi-Árido

She holds a bachelor’s degree in Mathematics from the State University of Ceará (2002), a master’s degree in Mathematics from the Federal University of Ceará (2007), and a Ph.D. in Teleinformatics Engineering from the Federal University of Ceará (2018). She served as a postdoctoral researcher at the School of Education at the State University of Campinas (2026), in the area of mathematics teacher education. She is currently an Associate II at the Federal Rural University of the Semi-Arid Region. She has experience in the field of mathematics teacher education, focusing primarily on the following topics: Tasks for Teacher Education, training of mathematics teachers, and Mathematics Teachers’ Specialized Knowledge (MTSK).

Sílvio Roberto Fernandes, Federal Rural University of Semi-Árido

He holds a bachelor’s degree in Computer Science from the Federal University of Rio Grande do Norte (2005), as well as a master’s degree (2008) and a Ph.D. (2012) in Systems and Computing from the Federal University of Rio Grande do Norte. He has experience in the field of Computer Science, with an emphasis on Computer Architecture and Embedded Systems. More recently, he has been conducting research involving conventional machine learning and machine learning for devices with severe computational constraints (TinyML). He has been a professor at the Federal Rural University of the Semi-Arid Region (UFERSA) since 2009, teaching in the undergraduate and graduate programs in Computer Science. He completed a postdoctoral fellowship (2018–2019) at the State University of Campinas (UNICAMP) with a CNPq PDJ grant, conducting research on heterogeneous architectures and high-performance computing. He served as Vice-Rector for Extension and Culture at UFERSA in 2020. He completed postdoctoral research at the Hub for Artificial Intelligence and Cognitive Architectures (HIAAC) at UNICAMP (2025–2026) with a FUNCAMP fellowship, conducting research on signal synthesis for Human Activity Recognition.