Experimenting Learning Analytics and Educational Data Mining in different educational contexts and levels

被引：3

作者：

Queiroga, Emanuel M. ^{[1
]}

Rodes Paragarino, Virginia ^{[2
]}

Perez Casas, Alen ^{[3
]}

Primo, Tiago Thompsen ^{[4
]}

Munoz, Roberto ^{[5
]}

Ramos, Vinicius Culmant ^{[6
]}

Cechinel, Cristian ^{[7
]}

机构：

[1] Inst Fed Sul Rio Grandense, Dept Tec Informacao, Pelotas, RS, Brazil

[2] Univ Republica, Com Sec Ensenanza, Montevideo, Uruguay

[3] Univ Republica, Fac Inf & Comunicac, Montevideo, Uruguay

[4] Univ Fed Pelotas, CDTec, Pelotas, RS, Brazil

[5] Univ Valparaiso, Escuela Ingn Informat, Valparaiso, Chile

[6] Univ Fed Santa Catarina, Dept Engn Conhecimento, Florianopolis, SC, Brazil

[7] Univ Fed Santa Catarina, Campus Ararangua, Ararangua, SC, Brazil

来源：

2022 XVII LATIN AMERICAN CONFERENCE ON LEARNING TECHNOLOGIES (LACLO 2022) | 2022年

关键词：

learning analytics; educational data mining; dropout prediction; STUDENTS;

D O I：

10.1109/LACLO56648.2022.10013478

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

This paper seeks to present the similarities and differences of the practical application of Learning Analitycs and Educational Data Mining in different educational contexts and levels. To accomplish such objective this paper explains the theories involved, as well as the methodologies, processes, methods and the context of the applications. Therefore, three distinct use cases and practical applications developed are presented for the following scenarios: face-to-face secondary education, university education and technical secondary distance education. In this context, we seek to generate practical methodologies for exploring data from different educational databases and contexts, focusing on generating early warning models for school dropout. Thus, this paper presents the results obtained in these applications, the similarities and differences among them according 19 technical aspects (existence of temporality in the data, size of the databases, existence of multiple data sources, techniques used, among others). Lastly, the thesis establishes the scientific contribution and future work related to the topic.

引用

页码：106 / 114

页数：9

共 24 条

[11] Learning analytics in Latin America present an opportunity not to be missed [J].

Ochoa, Xavier .

NATURE HUMAN BEHAVIOUR, 2019, 3 (01) :6-7

[12]

Queiroga E., 2019, S BRASILEIRO INFORMA, V8, P119

[13]

Queiroga E., 2017, AN 28 S BRAS INF ED, P1547, DOI DOI 10.5753/CBIE.SBIE.2017.1547

[14]

Queiroga E., 2015, ANAIS WORKSHOPS CONG, V4, P1074

[15]

Queiroga E. M., 2017, THESIS U FEDERAL PEL

[16] Early Prediction of At-Risk Students in Secondary Education: A Countrywide K-12 Learning Analytics Initiative in Uruguay [J].

Queiroga, Emanuel Marques ;

Batista Machado, Matheus Francisco ;

Paragarino, Virginia Rodes ;

Primo, Tiago Thompsen ;

Cechinel, Cristian .

INFORMATION, 2022, 13 (09)

[17] Using Virtual Learning Environment Data for the Development of Institutional Educational Policies [J].

Queiroga, Emanuel Marques ;

Enriquez, Carolina Rodriguez ;

Cechinel, Cristian ;

Casas, Alen Perez ;

Paragarino, Virginia Rodes ;

Bencke, Luciana Regina ;

Culmant Ramos, Vinicius Faria .

APPLIED SCIENCES-BASEL, 2021, 11 (15)

[18] A Learning Analytics Approach to Identify Students at Risk of Dropout: A Case Study with a Technical Distance Education Course [J].

Queiroga, Emanuel Marques ;

Lopes, Joao Ladislau ;

Kappel, Kristofer ;

Aguiar, Marilton ;

Araujo, Ricardo Matsumura ;

Munoz, Roberto ;

Villarroel, Rodolfo ;

Cechinel, Cristian .

APPLIED SCIENCES-BASEL, 2020, 10 (11)

[19]

Queiroga EM, 2016, 2016 XI LATIN AMERICAN CONFERENCE ON LEARNING OBJECTS AND TECHNOLOGY (LACLO), P196

[20] Analysis of Dimensionality Reduction Techniques on Big Data [J].

Reddy, G. Thippa ;

Reddy, M. Praveen Kumar ;

Lakshmanna, Kuruva ;

Kaluri, Rajesh ;

Rajput, Dharmendra Singh ;

Srivastava, Gautam ;

Baker, Thar .

IEEE ACCESS, 2020, 8 :54776-54788

← 1 2 3 →