Profiling low-proficiency science students in the Philippines using machine learning

Abstract

Filipino students’ performance in global assessments of science literacy has always been low, and this was confirmed again in the PISA 2018, where Filipino learners’ average science literacy scores ranked second to last among 78 countries. In this study, machine learning approaches were used to analyze PISA data from the student questionnaire to test models that best identify the poorest-performing Filipino students. The goal was to explore factors that could help identify the students who are vulnerable to very low achievement in science and that could indicate possible targets for reform in science education in the Philippines. The random forest classifier model was found to be the most accurate and more precise, and Shapley Additive Explanations indicated 15 variables that were most important in identifying the low-proficiency science students. The variables related to metacognitive awareness of reading strategies, social experiences in school, aspirations and pride about achievements, and family/home factors, include parents’ characteristics and access to ICT with internet connections. The results of the factors highlight the importance of considering personal and contextual factors beyond the typical instructional and curricular factors that are the foci of science education reform in the Philippines, and some implications for programs and policies for science education reform are suggested.

Project-based learning approach on content mastery and cognitive skills: a pedagogical model for senior high school biology students

“…The poor outcome in the performance level across cognitive skills aligns with the research conducted by Bernardo et al (2023), which found that Filipino students' performance on PISA 2018 is complemented by another international assessment, the Trends in International Mathematics and Science Study (TIMSS). This assessment measures students' ability to apply their knowledge in various content areas in science.…”

“…The results of the study are supported and has similarities with the research study of Bernardo et al (2023) as they unearth the results of PISA 2018 that the performance for Filipino students for global assessments has always been significantly low in performance of science. This means that the average of Filipino learners in scientific literacy ranked second to last among 78 countries.…”

Voyaging Beyond Chalkboards: Unleashing Tomorrow's Minds through AI-Driven Frontiers in Literature and Language Education

“…Through the voices of educators at St. Michael's College, Iligan City, the researcher unravels the intricate process of adapting to AI-infused educational landscapes (Gašević et al, 2023). The stories of educators navigating these uncharted waters provide insights that inform the development of meaningful and impactful training programs, thereby enhancing the potential of AI to catalyze transformative learning experiences (Bernardo et al, 2023).…”

Machine learning predicts upper secondary education dropout as early as the end of primary school

“…Deep learning has played a significant role in advancements in fields such as medical computer vision 15 – 20 and, more recently, in large foundation models 21 – 24 . Although machine learning methods have significantly transformed various disciplines, their application in education remains relatively unexplored 25 , 26 .…”