The Role of Polarity and Topic in Private Messages in the Analysis of Academic Trajectories: A Case Study
Resumo
This case study investigates Moodle private messages as a complementary source for monitoring academic trajectories in distance education courses. Messages from students classified as Graduated and Dropout were analyzed using a combination of sentiment analysis and topic modeling. The results indicate low consensus among the analysis methods and weak correlations between average polarity and indicators. Topic modeling showed that the messages primarily address academic and administrative demands, such as grades, deadlines, and technical difficulties. We conclude that average polarity has limited scope, and that using VLE textual records in real contexts depends on the centrality, quality, and completeness of the recorded interactions.
Palavras-chave:
Learning Analytics, Sentiment Analysis, Topic Modeling
Referências
Anwar, A., Rehman, I. U., Nasralla, M. M., Khattak, S. B. A., and Khilji, N. (2023). Emotions matter: A systematic review and meta-analysis of the detection and classification of students' emotions in stem during online learning. Education Sciences, 13(9).
Bobó, M., Campos, F., Ströele, V., David, J. M., and Braga, R. (2019). Identificação do perfil emocional do aluno através de análise de sentimento: Combatendo a evasão escolar. In Anais do XXX Simpósio Brasileiro de Informática na Educação, pages 1431–1440, Porto Alegre, RS, Brasil. SBC.
Carvalho, G., Silva, J. H. N. d. O., Carvalho, Á. M., Barrere, E., et al. (2025). Análise de aprendizagem no moodle: Construção de um painel de dados com indicadores educacionais. In Simpósio Brasileiro de Informática na Educação (SBIE).
Cleveland-Innes, M. and Campbell, P. (2012). Emotional presence, learning, and the online learning environment. The International Review of Research in Open and Distributed Learning, 13:269.
Costas-Jauregui, V., Oyelere, S., Caussin-Torrez, B., Barros-Gavilanes, G., Agbo, F., Toivonen, T., Motz, R., and Tenesaca, J. (2021). Descriptive analytics dashboard for an inclusive learning environment. In IEEE Frontiers in Education Conference (FIE), pages 1–9.
Dake, D. and Bada, G. (2023). Unveiling learner emotions: Sentiment analysis of moodle-based online assessments using machine learning. Journal of Information Technology Education: Innovations in Practice.
Freitas, L. (2013). Comparing portuguese opinion lexicons in feature-based sentiment analysis. International Journal of Computational Linguistics and Applications, 4:147–158.
Id, I., Saputra, H., Syamsudhuha, S., Kurniawan, R., and Andriyani, Y. (2024). Sentiment analysis of student evaluation feedback using transformer-based language models. Indonesian Journal of Electrical Engineering and Computer Science, 36:1127.
Kagklis, V., Karatrantou, A., Tantoula, M., Panagiotakopoulos, C., and Verykios, V. (2015). A learning analytics methodology for detecting sentiment in student fora: A case study in distance education. European Journal of Open, Distance and E-Learning, 18.
Koufakou, A. (2023). Deep learning for opinion mining and topic classification of course reviews. Education and Information Technologies, 29(3):2973–2997.
Lundqvist, K., Liyanagunawardena, T., and Starkey, L. (2020). Evaluation of student feedback within a mooc using sentiment analysis and target groups. The International Review of Research in Open and Distributed Learning, 21.
Martin, F. and Ndoye, A. (2016). Using learning analytics to assess student learning in online courses. Journal of University Teaching and Learning Practice, 13.
Mehall, S. (2020). Purposeful interpersonal interaction: What is it and how is it measured? Online Learning, 24.
Menezes, M. F. d. (2024). Proposta de um dashboard para análise e visualização de dados educacionais de sistemas tutores inteligentes. Universidade Federal do Amazonas.
Mora, H., Ferrández, A., Gil, D., and Peral, J. (2017). A computational method for enabling teaching-learning process in huge online courses and communities. volume 18.
Olivé, D. M., Huynh, D. Q., Reynolds, M., Dougiamas, M., and Wiese, D. (2019). A supervised learning framework: using assessment to identify students at risk of dropping out of a mooc. volume 32, pages 9–26. Springer Science+Business Media, LLC, part of Springer Nature.
Pereira, M. R., Alves, L., and Padilha, T. P. (2024). Investigando o uso de análise de sentimentos para identificar comportamentos de bullying em grupo de whatsapp escolar. In Anais do XXXV Simpósio Brasileiro de Informática na Educação, pages 3059–3065, Porto Alegre, RS, Brasil. SBC.
Pfitscher, R., Camargo, L., Moreira, B., Wang, C., Zedral, R., and Garcia, T. (2023). Análise de sentimentos em turmas de programação com vistas ao apoio à permanência estudantil. In Anais do XXXIV Simpósio Brasileiro de Informática na Educação, pages 1329–1340, Porto Alegre, RS, Brasil. SBC.
Queiroga, E. M., Enríquez, C. R., Cechinel, C., Casas, A. P., Paragarino, V. R., Bencke, L. R., and Ramos, V. F. C. (2021). Using virtual learning environment data for the development of institutional educational policies. Applied Sciences, 11(15).
Santos, T. C. B. d. (2024). Lumilab: um dashboard de learning analytics para apoio a gestores e professores de moocs da plataforma lúmina. In Programa de Pós-Graduação em Informática na Educação (UFRGS).
Schwendimann, B. A., Rodríguez-Triana, M. J., Vozniuk, A., Prieto, L. P., Boroujeni, M. S., Holzer, A., Gillet, D., and Dillenbourg, P. (2017). Perceiving learning at a glance: a systematic literature review of learning dashboard research. IEEE Transactions on Learning Technologies, 10(1):30–41.
Siemens, G. (2013). Learning analytics the emergence of a discipline. American Behavioral Scientist, 57:1380–1400.
Souza, M. and Vieira, R. (2012). Sentiment analysis on twitter data for portuguese language. pages 241–247.
van Leeuwen, A. (2023). Teachers' experiences of monitoring their students in online higher education: recommendations for course design and opportunities for learning analytics. Technology, Pedagogy and Education, 32(5):589–604.
Wen, M., Yang, D., and Rosé, C. (2014). Sentiment analysis in mooc discussion forums: What does it tell us?
Yang, D., Wen, M., Howley, I., Kraut, R., and Rose, C. (2015). Exploring the effect of confusion in discussion forums of massive open online courses. pages 121–130.
Zhou, Y., Zhao, J., and Zhang, J. (2023). Prediction of learners' dropout in e-learning based on the unusual behaviors. volume 31, pages 1796–1820. Routledge.
Bobó, M., Campos, F., Ströele, V., David, J. M., and Braga, R. (2019). Identificação do perfil emocional do aluno através de análise de sentimento: Combatendo a evasão escolar. In Anais do XXX Simpósio Brasileiro de Informática na Educação, pages 1431–1440, Porto Alegre, RS, Brasil. SBC.
Carvalho, G., Silva, J. H. N. d. O., Carvalho, Á. M., Barrere, E., et al. (2025). Análise de aprendizagem no moodle: Construção de um painel de dados com indicadores educacionais. In Simpósio Brasileiro de Informática na Educação (SBIE).
Cleveland-Innes, M. and Campbell, P. (2012). Emotional presence, learning, and the online learning environment. The International Review of Research in Open and Distributed Learning, 13:269.
Costas-Jauregui, V., Oyelere, S., Caussin-Torrez, B., Barros-Gavilanes, G., Agbo, F., Toivonen, T., Motz, R., and Tenesaca, J. (2021). Descriptive analytics dashboard for an inclusive learning environment. In IEEE Frontiers in Education Conference (FIE), pages 1–9.
Dake, D. and Bada, G. (2023). Unveiling learner emotions: Sentiment analysis of moodle-based online assessments using machine learning. Journal of Information Technology Education: Innovations in Practice.
Freitas, L. (2013). Comparing portuguese opinion lexicons in feature-based sentiment analysis. International Journal of Computational Linguistics and Applications, 4:147–158.
Id, I., Saputra, H., Syamsudhuha, S., Kurniawan, R., and Andriyani, Y. (2024). Sentiment analysis of student evaluation feedback using transformer-based language models. Indonesian Journal of Electrical Engineering and Computer Science, 36:1127.
Kagklis, V., Karatrantou, A., Tantoula, M., Panagiotakopoulos, C., and Verykios, V. (2015). A learning analytics methodology for detecting sentiment in student fora: A case study in distance education. European Journal of Open, Distance and E-Learning, 18.
Koufakou, A. (2023). Deep learning for opinion mining and topic classification of course reviews. Education and Information Technologies, 29(3):2973–2997.
Lundqvist, K., Liyanagunawardena, T., and Starkey, L. (2020). Evaluation of student feedback within a mooc using sentiment analysis and target groups. The International Review of Research in Open and Distributed Learning, 21.
Martin, F. and Ndoye, A. (2016). Using learning analytics to assess student learning in online courses. Journal of University Teaching and Learning Practice, 13.
Mehall, S. (2020). Purposeful interpersonal interaction: What is it and how is it measured? Online Learning, 24.
Menezes, M. F. d. (2024). Proposta de um dashboard para análise e visualização de dados educacionais de sistemas tutores inteligentes. Universidade Federal do Amazonas.
Mora, H., Ferrández, A., Gil, D., and Peral, J. (2017). A computational method for enabling teaching-learning process in huge online courses and communities. volume 18.
Olivé, D. M., Huynh, D. Q., Reynolds, M., Dougiamas, M., and Wiese, D. (2019). A supervised learning framework: using assessment to identify students at risk of dropping out of a mooc. volume 32, pages 9–26. Springer Science+Business Media, LLC, part of Springer Nature.
Pereira, M. R., Alves, L., and Padilha, T. P. (2024). Investigando o uso de análise de sentimentos para identificar comportamentos de bullying em grupo de whatsapp escolar. In Anais do XXXV Simpósio Brasileiro de Informática na Educação, pages 3059–3065, Porto Alegre, RS, Brasil. SBC.
Pfitscher, R., Camargo, L., Moreira, B., Wang, C., Zedral, R., and Garcia, T. (2023). Análise de sentimentos em turmas de programação com vistas ao apoio à permanência estudantil. In Anais do XXXIV Simpósio Brasileiro de Informática na Educação, pages 1329–1340, Porto Alegre, RS, Brasil. SBC.
Queiroga, E. M., Enríquez, C. R., Cechinel, C., Casas, A. P., Paragarino, V. R., Bencke, L. R., and Ramos, V. F. C. (2021). Using virtual learning environment data for the development of institutional educational policies. Applied Sciences, 11(15).
Santos, T. C. B. d. (2024). Lumilab: um dashboard de learning analytics para apoio a gestores e professores de moocs da plataforma lúmina. In Programa de Pós-Graduação em Informática na Educação (UFRGS).
Schwendimann, B. A., Rodríguez-Triana, M. J., Vozniuk, A., Prieto, L. P., Boroujeni, M. S., Holzer, A., Gillet, D., and Dillenbourg, P. (2017). Perceiving learning at a glance: a systematic literature review of learning dashboard research. IEEE Transactions on Learning Technologies, 10(1):30–41.
Siemens, G. (2013). Learning analytics the emergence of a discipline. American Behavioral Scientist, 57:1380–1400.
Souza, M. and Vieira, R. (2012). Sentiment analysis on twitter data for portuguese language. pages 241–247.
van Leeuwen, A. (2023). Teachers' experiences of monitoring their students in online higher education: recommendations for course design and opportunities for learning analytics. Technology, Pedagogy and Education, 32(5):589–604.
Wen, M., Yang, D., and Rosé, C. (2014). Sentiment analysis in mooc discussion forums: What does it tell us?
Yang, D., Wen, M., Howley, I., Kraut, R., and Rose, C. (2015). Exploring the effect of confusion in discussion forums of massive open online courses. pages 121–130.
Zhou, Y., Zhao, J., and Zhang, J. (2023). Prediction of learners' dropout in e-learning based on the unusual behaviors. volume 31, pages 1796–1820. Routledge.
Publicado
05/10/2026
Como Citar
CARVALHO, Gabriella; DE SOUZA, Jairo F.; VELOSO, Renê R..
The Role of Polarity and Topic in Private Messages in the Analysis of Academic Trajectories: A Case Study. In: SIMPÓSIO BRASILEIRO DE INFORMÁTICA NA EDUCAÇÃO (SBIE), 37. , 2026, Goiânia/GO.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 318-331.
DOI: https://doi.org/10.5753/sbie.2026.27094.
