Urban–Rural Gradients Predict Educational Gaps: Evidence from a Machine Learning Approach Involving Academic Performance and Impervious Surfaces in Ecuador
Academic performance (AP) is explained by a multitude of factors, principally by those related to socioeconomic, cultural, and educational environments. However, AP is less understood from a spatial perspective. The aim of this study was to investigate a methodology using a machine learning approach...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/10/12/830 |
| _version_ | 1797503947486789632 |
|---|---|
| author | Fabián Santos-García Karina Delgado Valdivieso Andreas Rienow Joaquín Gairín |
| author_facet | Fabián Santos-García Karina Delgado Valdivieso Andreas Rienow Joaquín Gairín |
| author_sort | Fabián Santos-García |
| collection | DOAJ |
| description | Academic performance (AP) is explained by a multitude of factors, principally by those related to socioeconomic, cultural, and educational environments. However, AP is less understood from a spatial perspective. The aim of this study was to investigate a methodology using a machine learning approach to determine which answers from a questionnaire-based survey were relevant for explaining the high AP of secondary school students across urban–rural gradients in Ecuador. We used high school locations to construct individual datasets and stratify them according to the AP scores. Using the Boruta algorithm and backward elimination, we identified the best predictors, classified them using random forest, and mapped the AP classification probabilities. We summarized these results as frequent answers observed for each natural region in Ecuador and used their probability outputs to formulate hypotheses with respect to the urban–rural gradient derived from annual maps of impervious surfaces. Our approach resulted in a cartographic analysis of AP probabilities with overall accuracies around 0.83–0.84% and Kappa values of 0.65–0.67%. High AP was primarily related to answers regarding the academic environment and cognitive skills. These identified answers varied depending on the region, which allowed for different interpretations of the driving factors of AP in Ecuador. A rural-to-urban transition ranging 8–17 years was found to be the timespan correlated with achievement of high AP. |
| first_indexed | 2024-03-10T03:57:39Z |
| format | Article |
| id | doaj.art-9507283c1f984f17a251da5cb2e53658 |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-10T03:57:39Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-9507283c1f984f17a251da5cb2e536582023-11-23T08:42:12ZengMDPI AGISPRS International Journal of Geo-Information2220-99642021-12-01101283010.3390/ijgi10120830Urban–Rural Gradients Predict Educational Gaps: Evidence from a Machine Learning Approach Involving Academic Performance and Impervious Surfaces in EcuadorFabián Santos-García0Karina Delgado Valdivieso1Andreas Rienow2Joaquín Gairín3Research Center for the Territory and Sustainable Habitat (CITEHS), Technological University Indoamerica, Machala y Sabanilla, Quito 170301, EcuadorCenter for Research in Human Sciences and Education (CICHE), Technological University Indoamerica, Machala y Sabanilla, Quito 170301, EcuadorInstitute of Geography, Ruhr University Bochum, Universitätsstraße 150, 44780 Bochum, GermanyCenter for Research and Studies for Organizational Development (CRiEDO), Universitat Autònoma de Barcelona, 08193 Bellaterra, SpainAcademic performance (AP) is explained by a multitude of factors, principally by those related to socioeconomic, cultural, and educational environments. However, AP is less understood from a spatial perspective. The aim of this study was to investigate a methodology using a machine learning approach to determine which answers from a questionnaire-based survey were relevant for explaining the high AP of secondary school students across urban–rural gradients in Ecuador. We used high school locations to construct individual datasets and stratify them according to the AP scores. Using the Boruta algorithm and backward elimination, we identified the best predictors, classified them using random forest, and mapped the AP classification probabilities. We summarized these results as frequent answers observed for each natural region in Ecuador and used their probability outputs to formulate hypotheses with respect to the urban–rural gradient derived from annual maps of impervious surfaces. Our approach resulted in a cartographic analysis of AP probabilities with overall accuracies around 0.83–0.84% and Kappa values of 0.65–0.67%. High AP was primarily related to answers regarding the academic environment and cognitive skills. These identified answers varied depending on the region, which allowed for different interpretations of the driving factors of AP in Ecuador. A rural-to-urban transition ranging 8–17 years was found to be the timespan correlated with achievement of high AP.https://www.mdpi.com/2220-9964/10/12/830academic performanceimpervious surfacesurban-ruralEcuador |
| spellingShingle | Fabián Santos-García Karina Delgado Valdivieso Andreas Rienow Joaquín Gairín Urban–Rural Gradients Predict Educational Gaps: Evidence from a Machine Learning Approach Involving Academic Performance and Impervious Surfaces in Ecuador ISPRS International Journal of Geo-Information academic performance impervious surfaces urban-rural Ecuador |
| title | Urban–Rural Gradients Predict Educational Gaps: Evidence from a Machine Learning Approach Involving Academic Performance and Impervious Surfaces in Ecuador |
| title_full | Urban–Rural Gradients Predict Educational Gaps: Evidence from a Machine Learning Approach Involving Academic Performance and Impervious Surfaces in Ecuador |
| title_fullStr | Urban–Rural Gradients Predict Educational Gaps: Evidence from a Machine Learning Approach Involving Academic Performance and Impervious Surfaces in Ecuador |
| title_full_unstemmed | Urban–Rural Gradients Predict Educational Gaps: Evidence from a Machine Learning Approach Involving Academic Performance and Impervious Surfaces in Ecuador |
| title_short | Urban–Rural Gradients Predict Educational Gaps: Evidence from a Machine Learning Approach Involving Academic Performance and Impervious Surfaces in Ecuador |
| title_sort | urban rural gradients predict educational gaps evidence from a machine learning approach involving academic performance and impervious surfaces in ecuador |
| topic | academic performance impervious surfaces urban-rural Ecuador |
| url | https://www.mdpi.com/2220-9964/10/12/830 |
| work_keys_str_mv | AT fabiansantosgarcia urbanruralgradientspredicteducationalgapsevidencefromamachinelearningapproachinvolvingacademicperformanceandimpervioussurfacesinecuador AT karinadelgadovaldivieso urbanruralgradientspredicteducationalgapsevidencefromamachinelearningapproachinvolvingacademicperformanceandimpervioussurfacesinecuador AT andreasrienow urbanruralgradientspredicteducationalgapsevidencefromamachinelearningapproachinvolvingacademicperformanceandimpervioussurfacesinecuador AT joaquingairin urbanruralgradientspredicteducationalgapsevidencefromamachinelearningapproachinvolvingacademicperformanceandimpervioussurfacesinecuador |