Pedro Francis Lopes, Amilton dos Santos Júnior, R. Azevedo, P. Dalgalarrondo, A. Fioravanti
{"title":"学习模型的各个方面来预测巴西大学生的生活质量","authors":"Pedro Francis Lopes, Amilton dos Santos Júnior, R. Azevedo, P. Dalgalarrondo, A. Fioravanti","doi":"10.5753/eniac.2022.227315","DOIUrl":null,"url":null,"abstract":"Quality of life is an essential metric for evaluating the well-being of students. This work investigates the viability of a model to predict a WHOQoL-Bref answer based on other answers and the overall domain and average scores. For that, we use data from an extensive pooling done with undergraduate students in Brazil (UNICAMP), gathered between 2017 and 2018. We also discuss model types and hyperparameter effects on model evaluation metrics. Finally, we conclude that it is possible to create a model to predict the esteem question - which is the most correlated with the average domain score with the data sample available.","PeriodicalId":165095,"journal":{"name":"Anais do XIX Encontro Nacional de Inteligência Artificial e Computacional (ENIAC 2022)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Aspects of a learned model to predict the quality of life of university students in Brazil\",\"authors\":\"Pedro Francis Lopes, Amilton dos Santos Júnior, R. Azevedo, P. Dalgalarrondo, A. Fioravanti\",\"doi\":\"10.5753/eniac.2022.227315\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Quality of life is an essential metric for evaluating the well-being of students. This work investigates the viability of a model to predict a WHOQoL-Bref answer based on other answers and the overall domain and average scores. For that, we use data from an extensive pooling done with undergraduate students in Brazil (UNICAMP), gathered between 2017 and 2018. We also discuss model types and hyperparameter effects on model evaluation metrics. Finally, we conclude that it is possible to create a model to predict the esteem question - which is the most correlated with the average domain score with the data sample available.\",\"PeriodicalId\":165095,\"journal\":{\"name\":\"Anais do XIX Encontro Nacional de Inteligência Artificial e Computacional (ENIAC 2022)\",\"volume\":\"72 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-11-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Anais do XIX Encontro Nacional de Inteligência Artificial e Computacional (ENIAC 2022)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.5753/eniac.2022.227315\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Anais do XIX Encontro Nacional de Inteligência Artificial e Computacional (ENIAC 2022)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5753/eniac.2022.227315","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Aspects of a learned model to predict the quality of life of university students in Brazil
Quality of life is an essential metric for evaluating the well-being of students. This work investigates the viability of a model to predict a WHOQoL-Bref answer based on other answers and the overall domain and average scores. For that, we use data from an extensive pooling done with undergraduate students in Brazil (UNICAMP), gathered between 2017 and 2018. We also discuss model types and hyperparameter effects on model evaluation metrics. Finally, we conclude that it is possible to create a model to predict the esteem question - which is the most correlated with the average domain score with the data sample available.