Data mining research
Educational data mining researchers (e.g., Baker 2011; Baker and Yacef 2009) view the following as the goals for their research
1.Predicting students’ future learning behavior by creating student models that incorporate such detailed information as students’ knowledge, motivation, metacognition and attitudes;
To accomplish these four goals, educational data mining research uses the five categories of technical methods (Baker 2011) described below.
Technical methods used in learning analytics are varied and draw from those used in educational data mining. Additionally, learning analytics may employ:
In summary, learning analytics systems apply models to answer such questions as:
Visual Data Analytics
Visual interactive principal components analysis (finding the components of a dataset that reduce many variables into few) is a technique once available only to statisticians that is now commonly used to detect trends and data correlations in multidimensional data sets.
Gapminder (http://www.gapminder.org/ ) for example, uses this approach in its analysis of multivariate datasets over time.
Websites, such as Many Eyes (http://edutechwiki.unige.ch/en/IBM_Many_Eyes ), offer tools for any user to create visualizations (map-based, text-based clouds and networks, and charts and graphs) of personal datasets.
Early in its release, the creators of Many Eyes discovered that it was being used for visual analytics, to check for data quality, to characterize social trends, and to reveal personal and collective sentiments or advocate for a position (Viégas et al. 2008). Like Many Eyes, other online services, such as Wordle and FlowingData, accept uploaded data and allow the user to configure the output to varying degrees. To facilitate the development of this field, the National Visualization and Analytics Center was established by the U.S. Department of Homeland Security to provide strategic leadership and coordination for visual analytics technology and tools nationwide, and this has broadened into a visual analytics community (http://vacommunity.org).
An Analysis of Data Activities and Instructional Supports in Middle School Science Textbooks
Operational definitions and results by textbook type
Technology used for gathering and analysing data – Web publishing tools
An ePortfolio is a learner-created collection of digital items, ideas, evidence, reflections, feedback which presents a selected audience with evidence of a person’s learning and/or ability. Portfolios can allow a student to demonstrate development over a period of time. Support real-world tasks. Can be time-consuming to mark. Clear rubrics need to be provided.
Diagrams can be used to capture processes, concepts or creative solutions to problems.
Mindmap: bubbl.us, popplet, mindomo, coggle, mindmiester, mindomo
Flowchart: Lucidchart Infographic: piktochart
General: Google draw
Quizzes and Surveys
Automarking ability lends itself well to large enrolments. The multiple-choice style questions are suited to assessing basic recall/knowledge. Well structured questions take time to write and quizzes take time to set up. Time is saved through automarking. They can be used to give question-specific feedback, but this is time consuming to create. To minimise potential for plagiarism, strategies such as randomisation, complete-in-one-sitting, question banks and multiple test versions can be used. Can be used to collect authentic data for students to analyse, or for students to create their own questions.Can be used to support self-reflection.
Under this topic we reviewed technology used for gathering and analyzing data and analyzing category,definition, concept measurement,coding criteria and other types of analysis of data activities and instructional supports.