Data science in education: Big data and learning analytics

Klašnja-Milićević, Aleksandra; Ivanović, Mirjana; Budimac, Zoran

doi:10.1002/cae.21844

Cited by 79 publications

(73 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Literature shows a growing development of frameworks and models (RQ1) with two levels of analysis: the macro level for understanding institutions (school) and groups (class), which use BD strategies, and the micro level (little data) for analysing individuals' profi les and behaviours through LA (Piety et al, 2014). BD and LA are strategies that addresses key challenges such as learners' experience; engaging, effective evidence-based decision making; and strategic adaptation to societal trends (Klašnja-Milićević et al, 2017). Data analysis is intended not only for situational sense-making, but also for systematic instructional personalisation through prediction of learning contexts, discovery of behaviour-learning relationships and production of data-driven knowledge (Klašnja-Milićevi et al, 2017).…”

Section: Resultsmentioning

confidence: 99%

Exploring Data Driven Youth Character Education Frameworks: A Systematic Literature Review on Learning Analytics Models and Participatory Design

Rivera¹

2019

Estudios sobre Educación

View full text Add to dashboard Cite

Character development requires not only high-quality curriculums, but also educators who are able to adapt programs to learners' needs and context and staff development strategies. Big data and learning analytics strategies may improve youth character development especially in developing countries facilitating educators' development and practical wisdom, as well as curriculum implementation's effectiveness in countries with less knowhow in the issue. This study presents a systematic mapping literature review on the models and methods of learning ana-lytics applied in the improvement of youth character education. Based on the literature review results, the research provides insights for future research and implementation of character education programs, and proposes a revised participatory knowledge management data-driven procedure that may facilitate educators to identify and undertake the best character formation actions in specifi c situations.

show abstract

Section: Resultsmentioning

confidence: 99%

Exploring Data Driven Youth Character Education Frameworks: A Systematic Literature Review on Learning Analytics Models and Participatory Design

Rivera¹

2019

Estudios sobre Educación

View full text Add to dashboard Cite

show abstract

“…The supporting unit of instruction could then be given to the struggling learner in an effort to create personalized learning for him/her (Spector, 2013). Klašnja-Milićević, Ivanović, and Budimac (2017) offer that learning analytics can: make predictions about future uses of learning sequences; learn the relationship between course materials and a learner"s academic performance; and, determine significant relationships between learner knowledge level, learner study time, and learner academic achievement. With the growing need to collect and analyze huge sets of data, there are two major issues: 1) the abilities of educators to find and make use of the available data, i.e., findability and usability, and 2) educators do not always have the knowledge and tools necessary to easily access and accomplish successful data analysis, i.e., accessibility and data (learning) analytics skills (Rolleston, Howe & Sprague, 2015).…”

Section: Big Data In Educationmentioning

confidence: 99%

Findability, Accessibility, and Usability of Data Portals in Education

Banker¹

2020

JESP

View full text Add to dashboard Cite

There is a need for stakeholders, at all levels of education, to be able to locate, access, and use the preponderance of data available about schools and students' demographic information and academic performance. The reason for findability, accessibility and usability of the data is for the stakeholders to make data-driven decisions based on trends the data bring to light. However, in many cases, data are located in portals that are cumbersome and difficult to navigate. This article explores the complexity of educational data portals; the wide gap in technology skills of the user of the data; and, interface design challenges.One of the most exciting elements of data analytics in education is the ability it can afford educators to identify and predict trends in many different areas (e.g. academic achievement, student enrollment, student retention, career interests, pedagogical preferences, etc.) for data-driven decisions to improve student learning. The successful use of data analytics starts with educational data mining (EDM). EDM is the process of using computational approaches (statistical algorithms) to analyze different data sets collected by various educational institutions (Romero& Ventura, 2010). In A Roadmap for Educational Technology, 2010, there are seven information technology areas that hold great promise for the future to better help students learn. Those areas are: 1) user modeling; 2) mobile tools; 3) networking tools; 4) serious games; 5) intelligent environments; 6) educational data mining; and, 7) rich interfaces (Computing Community Consortium, 2010, p. 43). As one of the seven information technology areas, EDM is knowledge discovery in databases (Siguenza, Saquicela, Avila-Ordonez, Vandewalle, & Cattrysse, 2015).Knowledge discovery occurs when EDM uses statistical methods that search for new and generalizable relationships rather than testing a hypothesis (Slater, Joksimovic, Kovanovic, Baker & Gasevic, 2017). The new and generalizable relationships can then be used to make decisions that will help learning professionals better design learning for students (Masie, 2013). In other words, the use of EDM can produce knowledge, such as trends and patterns, that was not known before, about the relationship between learning and students from the statistical analysis done on large sets of data. (Siguenza et al., 2015). Due to advances in technology, a large volume, a wide variety, and high speeds of data about students are being generated and collected (Wang, 2017).

show abstract

“…Mining educational textual data is an active research area that employs data mining methods with educational data to understand student learning and performance . Mostow et al present an intelligent tutoring system to browse the interactions between a tutor and students with MySQL databases .…”

Section: Background and Related Workmentioning

confidence: 99%

A semantic network model for measuring engagement and performance in online learning platforms

Lim

Tucker

Jablokow

et al. 2018

Comp Applic In Engineering

View full text Add to dashboard Cite

Due to the increasing global availability of the internet, online learning platforms such as Massive Open Online Courses (MOOCs), have become a new paradigm for distance learning in engineering education. While interactions between instructors and students are readily observable in a physical classroom environment, monitoring student engagement is challenging in MOOCs. Monitoring student engagement and measuring its impact on student performance are important for MOOC instructors, who are focused on improving the quality of their courses. The authors of this work present a semantic network model for measuring the different word associations between instructors and students in order to measure student engagement in MOOCs. Correlation analysis is then performed for identifying how student engagement in MOOCs affect student performance. Real‐world MOOC transcripts and MOOC discussion forum data are used to evaluate the effectiveness of this research.

show abstract

Data science in education: Big data and learning analytics

Cited by 79 publications

References 21 publications

Exploring Data Driven Youth Character Education Frameworks: A Systematic Literature Review on Learning Analytics Models and Participatory Design

Exploring Data Driven Youth Character Education Frameworks: A Systematic Literature Review on Learning Analytics Models and Participatory Design

Findability, Accessibility, and Usability of Data Portals in Education

A semantic network model for measuring engagement and performance in online learning platforms

Contact Info

Product

Resources

About