Common goal

In an institution called education, differences are not something that must be marginalized based on the judgment or preferences of the majority, but differences are social dynamics that must be integrated to materialize the core goals of education itself. Inequality in the educational setting remains an important topic of research. Inclusivity is increasingly recognized as a serious, worldwide education concern. The Division for Sustainable Development Goals (DSDG) in the United Nations Department of Economic and Social Affairs (UNDESA) set goals number 4 related to education, namely “Ensure inclusive and equitable quality education and promote lifelong learning opportunities for all.”

Recognize the differences

In the pedagogical system to address the rising issue of diversity among learners, first, the educator has to identify the conditions and attributes attached to the learners. The identification process begins with the sorting process which sometimes problematic. Cope dan Kalantzis (2015) made meta-categories of learner differences as follows:

1. Material conditions (social class, locale, and family);
2. Corporeal attributes (age, race, sex and sexuality, and physical and mental abilities);
3. Symbolic differences (language, ethnos, communities of commitment and gender)

The meta-categories above were created to acknowledge differences among students. Because the refusal of recognizing differences is the birth of inequality.

The aim of this writing

Debate continues about the best strategies to accept and respect differences in the learning context. In this writing, I attempt to propose the initiative namely in the form of an education portal as the source of educational data mining to enable the collection, monitoring, and evaluation of learner material conditions, learner corporeal attributes, learner symbolic differences, learners progress, learners behavior, and academic output.

Why educational data mining

Ensure in the SDG No.4 is defined in Oxford Learner's Dictionaries as to make sure that something happens or is definite (Oxford Learner's Dictionaries and defined in Cambridge Dictionary as to make something certain to happen. This means the stakeholders have to see the evidence informing the state. To see the evidence can be perceived as to directly observe the classroom activity, to see the submitted complaint, to see the academic score, to see the statistic of students enrolled. Since the last of the sentence is “for all” thus the detailed review could spend a vast amount of time due to the dissonance of action among people in the educational context. Educational data mining at a national level is preferable as an option to have a helicopter view of what is going on the ground. Educational data mining is only possible when the data is available. While data availability depends on the policy, learners' and institutions' awareness, and digital infrastructure in terms of learners’ and institutions’ access to technology both for devices and network.

The data pool

To execute educational data mining is very important for the stakeholder- in this case, is the highest authority- the government, to compile data which comply all data quality dimension (completeness, uniqueness, timeliness, validity, accuracy, and consistency). To address this, I presume that the only solution is to have a unified portal and standardized indicators in the form of a web-based education portal. I divide the information collected into two major types:

Evidence-based information:

1. Learners profile (material conditions, corporeal attributes, symbolic differences)
2. Schools profile
3. Syllabi completion checklist both for students and teachers
4. Learners' behavior in collaborative work. To record this, the portal has to have a feature of forum-like to do tasks collaboratively. Learners can upload their assignments and activate the “Need a hand” button to ask for feedback from other learners. This data can record learners’ interest and engagement.
5. Learners' academic score submitted by institution authority.

Perception-based information:

1. Survey on inclusive education practice in school

The surveys used to collect the perception of internal stakeholders contain more practices or statements compared to the evidence-based assessment, as there are many intangible aspects related to the same topic which can be captured through this data collection tool.

Analytic methods

Source: Peña-Ayala (Ed.) (2014), Educational Data Mining Applications and Trends, Studies in Computational Intelligence, Vol. 524

How the findings from the data play a role in pedagogical design and management?

Inclusion is a prodigious task that cannot be materialized through facile policy rhetoric and practices intended to ‘patch up’ the educational system (Weddell 2008). I selected the PDCA cycle as a reliable method to develop appropriate policy in driving a nation to achieve the education goal.

Plan, Do, Check, and Act

As Winn (1989) contends "Recipes only work sometimes, and only in contexts that are remarkably similar to those in which the recipes were developed." Instruction changes that can lead to differentiated instruction must adapt to the changing environment based on data.

Further work

• There must be a well-designed survey question and student profile form to collect the appropriate data.
• There must be a nationally agreed standard of measurement to determine the weight of evidence-based and perception-based in order to evaluate and issue a policy.
• Limitation: Since the system is requiring a high contribution of learners, then the most suitable learners targeted are those who on the Senior High level.

References:

• The Division for Sustainable Development Goals (DSDG) in the United Nations Department of Economic and Social Affairs (UNDESA) (n.d.), Goal 4, available at: https://sdgs.un.org/goals/goal4
• Kalantzis, M., Cope, B. (2016), Learner differences in theory and practice,
• Open Review of Educational Research, 3:1, 85-132, DOI: 10.1080/23265507.2016.1164616, available at: https://www.tandfonline.com/doi/full/10.1080/23265507.2016.1164616
• Liasidou, A. (2015), Inclusive Education and the Issue of Change Theory, Policy and Pedagogy, available at: https://www.palgrave.com/gp/book/9781137333698
• Adelsberger, H. H., Collis, B., Pawlowski, J. M. (Eds.) (2002), Handbook on Information Technologies for Education and Training, International Handbooks on Information Systems, available at: https://www.springer.com/gp/book/9783662076828?utm_campaign=3_pier05_buy_print&utm_content=en_08082017&utm_medium=referral&utm_source=google_books
• Peña-Ayala, A. (2014), Educational Data Mining: Applications and Trends, Studies in Computational Intelligence, Vol. 524, available at: https://www.springer.com/gp/book/9783319027371