| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 1.42 MB | Adobe PDF |
Authors
Advisor(s)
Abstract(s)
O abandono escolar Ć© uma constante preocupaĆ§Ć£o das instituiƧƵes de ensino superior, com divergentes e complexos fatores relatados por diversos autores. Conseguimos notar que este problema Ć© bastante abrangente e explorado, jĆ” sendo possĆvel encontrar nas instituiƧƵes setores especializados ou programas de auxĆlio como psicĆ³logos, auxĆlio moradia, programa de monitoria, entre outros, buscando minimizar a quantidade de alunos desistentes. Entretanto estas propostas dependem do prĆ³prio aluno a buscar ajuda necessĆ”ria, abrindo uma lacuna para aqueles que nĆ£o se sentem confortĆ”veis a procurar ou nĆ£o possuem total conhecimento do prĆ³prio caso.
Este trabalho propƵe um modelo para a identificaĆ§Ć£o prĆ©via dos alunos desistentes, com objetivo de tornar as instituiƧƵes de ensino aptas a entender melhor os casos de abandono e se possĆvel encaminhĆ”-los a setores especializados. Para tal, utilizamos o Instituto PolitĆ©cnico de BraganƧa como estudo de caso que nos forneceu mais 200 milhƵes de registros relacionados aos alunos matriculados entre 2008 a 2017.
Analisamos e processamos a Big Data fornecida com a finalidade de moldĆ”-la como parĆ¢metros de entrada de algoritmos de machine learning. Inicialmente testamos trĆŖs algoritmos e descobrimos que o random forest demonstra ser o mais eficiente neste contexto. A partir disso, aproveitamos do volume de dados para identificar qual seria melhor ciclo de treino e obtemos que o perĆodo de 4 anos consegue atingir melhores resultados. No aprimoramento do modelo adicionamos mais 2 atributos buscando realƧar a trajetĆ³ria escolar do aluno.
Para implementaĆ§Ć£o e visualizaĆ§Ć£o do modelo, desenvolvemos uma ferramenta de extraĆ§Ć£o de dados e uma aplicaĆ§Ć£o Web, que atravĆ©s de diferentes nĆveis de acesso, alĆ©m de conseguir identificar os alunos em risco de abandono, tambĆ©m possibilita aos usuĆ”rios efetuar anĆ”lises comparativas entre escolas e cursos por meio de uma pĆ”gina personalizada com estatĆsticas transformadas em grĆ”ficos e tabelas.
O estudo se apresenta como uma boa soluĆ§Ć£o para identificaĆ§Ć£o prĆ©via dos alunos em risco de abandono, possibilitando anĆ”lises e encaminhamentos. O modelo ainda pode ser ampliado a mais parĆ¢metros e tende a obter melhores resultados ao longo dos anos aperfeiƧoando atravĆ©s do reforƧo os atributos criados.
School dropout is a constant concern of higher education institutions, with divergent and complex factors reported by various authors. We can note that this problem is quite broad and exploited, since it is possible to find specialized sectors or assistance programs such as psychologists, housing assistance, monitoring programs, among others, in order to minimize the number of students dropping out. However, these proposals depend on the student himself to seek necessary help, opening a gap for those who do not feel comfortable to seek or do not have full knowledge of the case itself. This work proposes a model for the prior identification of dropouts, with the aim of making higher education institutions able to understand cases of dropout and, if possible, refer them to specialized sectors. For that, we use as a case study the Instituto PolitƩcnico de BraganƧa, which provided 200 million records related to students enrolled between 2008 and 2017. We analyze and process the Big Data provided for molding it as input parameters of machine learning algorithms. We first tested three algorithms and found that random forest proves to be the most efficient in this context. From this, we take advantage of the data volume to identify which would be the best training cycle and obtain that the period of 4 years can achieve better results. In the improvement of the model we added two more attributes to highlight the trajectory of the student. For the implementation and visualization of the model, we developed a data extraction tool and a Web application, which through different levels of access, besides being able to identify students at risk of abandonment, also allows users to make comparative analysis between schools and courses by of a custom page with statistics transformed into graphs and tables. The study presents as a good solution for the prior identification of students at risk of dropout, enabling analysis and referrals. The model can still be extended to more parameters and tends to obtain better results over the years by improving by enhancing the attributes created.
School dropout is a constant concern of higher education institutions, with divergent and complex factors reported by various authors. We can note that this problem is quite broad and exploited, since it is possible to find specialized sectors or assistance programs such as psychologists, housing assistance, monitoring programs, among others, in order to minimize the number of students dropping out. However, these proposals depend on the student himself to seek necessary help, opening a gap for those who do not feel comfortable to seek or do not have full knowledge of the case itself. This work proposes a model for the prior identification of dropouts, with the aim of making higher education institutions able to understand cases of dropout and, if possible, refer them to specialized sectors. For that, we use as a case study the Instituto PolitƩcnico de BraganƧa, which provided 200 million records related to students enrolled between 2008 and 2017. We analyze and process the Big Data provided for molding it as input parameters of machine learning algorithms. We first tested three algorithms and found that random forest proves to be the most efficient in this context. From this, we take advantage of the data volume to identify which would be the best training cycle and obtain that the period of 4 years can achieve better results. In the improvement of the model we added two more attributes to highlight the trajectory of the student. For the implementation and visualization of the model, we developed a data extraction tool and a Web application, which through different levels of access, besides being able to identify students at risk of abandonment, also allows users to make comparative analysis between schools and courses by of a custom page with statistics transformed into graphs and tables. The study presents as a good solution for the prior identification of students at risk of dropout, enabling analysis and referrals. The model can still be extended to more parameters and tends to obtain better results over the years by improving by enhancing the attributes created.
Description
Mestrado de dupla diplomaĆ§Ć£o com a UTFPR - Universidade TecnolĆ³gica Federal do ParanĆ”
Keywords
Big data analytics Abandono escolar Ensino superior