Josmario Albuquerque
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Josmario Albuquerque has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Bart Rienties
The Open University
3 shared publications - Jorge Artur Peçanha de Miranda Coelho
Federal University of Alagoas
2 shared publications - Martin Hlosta
Institute for Research in Open-, Distance- and eLearning, Swiss Distance University of Applied Sciences, Brig, Switzerland
2 shared publications - Wayne Holmes
University College London
2 shared publications Alan P. Silva
1 shared publication- Blaženka Divjak
University of Zagreb
1 shared publication
Latest Publications
- Open Access
- 25 February 2026
- Published by Society for Learning Analytics Research in Journal of Learning Analytics
- Vol. 13 (1) , 143-162
Learning Analytics to Uncover Ethnic Bias in Educational Texts
Online learning platforms have expanded access to education but also raise concerns about biased content, particularly in text-based learning materials such as textbooks, lesson plans, and course excerpts. Such biases can perpetuate discrimination, can harm student outcomes, and can often be difficult to detect, as identification typically relies on time-consuming human review. Learning analytics (LA) can enhance this process by supporting human reviewers through automated detection, offering a scalable solution while retaining human judgment for nuanced evaluations. Accordingly, this LA study explores two research questions: RQ1: Which features might support the identification of ethnic bias in text-based online learning materials? and RQ2: Which classification approaches might be suitable for identifying ethnic bias in text-based online learning materials? First, we identified features signalling potential ethnic bias (presence or absence) in textual content using a dataset (N = 345) labelled by 193 students from diverse ethnic backgrounds. Then, we evaluated multiple machine learning (ML) models for their effectiveness in bias classification. The results suggest significant correlations between perceived bias and content from social sciences. Additionally, through bootstrap analysis, support vector machines and random forest classifiers showed consistent performance in bias identification (with F1-scores of 0.71 and 0.70 on the test set, respectively). In contrast, the naive Bayes (NB) model demonstrated the highest precision (0.75 on the test set). We discuss these findings and their implications for LA, emphasizing the importance of quality and inclusive educational tools. As an initial step toward automated bias classification in education, this study provides a foundation for spotting ethnic bias in learning content, supporting fairer technologies for more inclusive learning environments.
- 25 February 2026
- Published by Society for Learning Analytics Research in Journal of Learning Analytics
- Vol. 13 (1) , 143-162
Open AccessLearning Analytics to Uncover Ethnic Bias in Educational Texts
Online learning platforms have expanded access to education but also raise concerns about biased content, particularly in text-based learning materials such as textbooks, lesson plans, and course excerpts. Such biases can perpetuate discrimination, can harm student outcomes, and can often be difficult to detect, as identification typically relies on time-consuming human review. Learning analytics (LA) can enhance this process by supporting human reviewers through automated detection, offering a scalable solution while retaining human judgment for nuanced evaluations. Accordingly, this LA study explores two research questions: RQ1: Which features might support the identification of ethnic bias in text-based online learning materials? and RQ2: Which classification approaches might be suitable for identifying ethnic bias in text-based online learning materials? First, we identified features signalling potential ethnic bias (presence or absence) in textual content using a dataset (N = 345) labelled by 193 students from diverse ethnic backgrounds. Then, we evaluated multiple machine learning (ML) models for their effectiveness in bias classification. The results suggest significant correlations between perceived bias and content from social sciences. Additionally, through bootstrap analysis, support vector machines and random forest classifiers showed consistent performance in bias identification (with F1-scores of 0.71 and 0.70 on the test set, respectively). In contrast, the naive Bayes (NB) model demonstrated the highest precision (0.75 on the test set). We discuss these findings and their implications for LA, emphasizing the importance of quality and inclusive educational tools. As an initial step toward automated bias classification in education, this study provides a foundation for spotting ethnic bias in learning content, supporting fairer technologies for more inclusive learning environments.
- Open Access
- 3 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 407-417
Decoding Learning Design Decisions: A Cluster Analysis of 12,749 Teaching and Learning Activities
- 3 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 407-417
Open AccessDecoding Learning Design Decisions: A Cluster Analysis of 12,749 Teaching and Learning Activities
- Open Access
- 25 October 2024
- Published by Taylor & Francis in Interactive Learning Environments
- Vol. 33 (3) , 2332-2354
From hype to evidence: exploring large language models for inter-group bias classification in higher education
- 25 October 2024
- Published by Taylor & Francis in Interactive Learning Environments
- Vol. 33 (3) , 2332-2354
Open AccessFrom hype to evidence: exploring large language models for inter-group bias classification in higher education
- Open Access
- 9 September 2022
- Published by STAR Scholars Network in Journal of International Students
- Vol. 12 (S3) , 57-76
Marginalization and Underrepresentation in Virtual Exchange: Reasons and Remedies
The recent expansion of virtual exchange (VE) in lieu of the Covid-19 pandemic and the ongoing advance of technology has resulted in considerably larger numbers of VE participants for those in certain areas and contexts, yet not all would-be participants have been so fortunate. In some regions and in various contexts, challenges in VE implementation have resulted in disadvantaged populations in terms of underrepresentation and marginalization in global VE networks. To illuminate such challenges, a mixed-method approach was utilized in the current study, beginning with a global survey to elucidate reasons for underrepresentation in terms of political, governmental, institutional, administrative, technological, pedagogical, cultural and personal challenges. Thereafter, semi-structured interviews with instructors, administrators, and educational decision makers were conducted to gain further insights. Although VE is now well established as an impactful mode of studying abroad, various region-specific challenges remain. We conclude with recommendations for underrepresented regions and populations.
- 9 September 2022
- Published by STAR Scholars Network in Journal of International Students
- Vol. 12 (S3) , 57-76
Open AccessMarginalization and Underrepresentation in Virtual Exchange: Reasons and Remedies
The recent expansion of virtual exchange (VE) in lieu of the Covid-19 pandemic and the ongoing advance of technology has resulted in considerably larger numbers of VE participants for those in certain areas and contexts, yet not all would-be participants have been so fortunate. In some regions and in various contexts, challenges in VE implementation have resulted in disadvantaged populations in terms of underrepresentation and marginalization in global VE networks. To illuminate such challenges, a mixed-method approach was utilized in the current study, beginning with a global survey to elucidate reasons for underrepresentation in terms of political, governmental, institutional, administrative, technological, pedagogical, cultural and personal challenges. Thereafter, semi-structured interviews with instructors, administrators, and educational decision makers were conducted to gain further insights. Although VE is now well established as an impactful mode of studying abroad, various region-specific challenges remain. We conclude with recommendations for underrepresented regions and populations.
- Open Access
- 10 May 2021
- Published by ANGRAD in Administração: Ensino e Pesquisa
- Vol. 22 (1) , 1-30
Planejamento de Questionários: Unificando conhecimentos em Pesquisa de Mercado e Psicometria
Neste estudo, são apresentadas especificidades práticas para a construção de questionários para fins técnicos e/ou acadêmicos, considerando a funcionalidade e a contextualização com a pesquisa em administração. A partir disso, propôs-se aprofundar teoricamente a operacionalização de questionários como instrumentos de pesquisa. Com base em um estudo bibliográfico, discutem-se o planejamento adequado de instrumentos para a triagem, a construção, a aplicação (levantamento) e as possibilidades analíticas, considerando os conceitos de fidedignidade, validade e precisão. Foram utilizados exemplos da literatura para demonstrar a aplicação profícua de questionários em contexto gerenciais. Como contribuição, este estudo avança na compilação de conhecimentos em psicometria e pesquisa de mercado, que possibilitam um espectro mais amplo para a usabilidade de instrumentos para a tomada de decisão com maior robustez metodológica.
- 10 May 2021
- Published by ANGRAD in Administração: Ensino e Pesquisa
- Vol. 22 (1) , 1-30
Open AccessPlanejamento de Questionários: Unificando conhecimentos em Pesquisa de Mercado e Psicometria
Neste estudo, são apresentadas especificidades práticas para a construção de questionários para fins técnicos e/ou acadêmicos, considerando a funcionalidade e a contextualização com a pesquisa em administração. A partir disso, propôs-se aprofundar teoricamente a operacionalização de questionários como instrumentos de pesquisa. Com base em um estudo bibliográfico, discutem-se o planejamento adequado de instrumentos para a triagem, a construção, a aplicação (levantamento) e as possibilidades analíticas, considerando os conceitos de fidedignidade, validade e precisão. Foram utilizados exemplos da literatura para demonstrar a aplicação profícua de questionários em contexto gerenciais. Como contribuição, este estudo avança na compilação de conhecimentos em psicometria e pesquisa de mercado, que possibilitam um espectro mais amplo para a usabilidade de instrumentos para a tomada de decisão com maior robustez metodológica.
- 1 December 2017
- Published by Elsevier in Computers & Education
- Vol. 115, 161-170
Does gender stereotype threat in gamified educational environments cause anxiety? An experimental study
- 1 December 2017
- Published by Elsevier in Computers & Education
- Vol. 115, 161-170
Does gender stereotype threat in gamified educational environments cause anxiety? An experimental study