Submissions

Author Guidelines

A. Introduction

1. Background

Format: Must be structured comprehensively, logically, and fluidly using a deductive or "funneling" approach, guiding the reader from macro trends in educational data (e.g., national big data policies) to micro-level learning analytics issues within the classroom/LMS. This section must be written as a cohesive narrative without subheadings.

Proportion: Ideally ranges from 15% to 20% of the total manuscript.

Substantive Issue: Elucidate the fundamental reasons why this learning analytics research or data-driven system evaluation is crucial and urgent. Avoid cliché opening statements. The author must directly address real-world problem contexts, such as failures in early detection of student retention (drop-out prediction), the disconnect between educator dashboard visualizations and on-the-ground pedagogical actions, the lack of algorithmic fairness in predictive models, or data bias in automated assessments.

State of the Art (Literature Mapping): A thematic synthesis is mandatory, establishing a dialogue between at least 5 to 10 primary sources from globally reputable journals (e.g., Journal of Learning Analytics, Computers & Education) published within the last 5 years. The author must act as a "moderator" to categorize previous computational models or pedagogical frameworks, juxtapose their algorithmic efficiencies, and conduct a gap analysis to expose methodological or pedagogical blind spots in prior studies.

Novelty: Explicitly state the scientific value added by the study. It is recommended to use definitive, distinguishing language, such as: "In contrast to previous studies that predominantly focused on [X], this research offers a novel approach in the Learning Analytics landscape by implementing algorithm [Y] to detect students' cognitive load in real-time."

Concluding Paragraph of the Background: Must contain a clear thesis statement asserting the analytical position or computational hypothesis being defended. The author must articulate why the international educational research community should care about this data model. This section concludes with a brief overview of the final findings, model accuracy, or proposed data-driven pedagogical interventions.

2. Problem Statement

Presented in the form of specific research questions or a narrative paragraph focusing on the relationship between digital behavioral patterns (data metrics) and learning outcomes or processes, which will be critically dissected in the discussion section.

3. Research Methodology

Analytically and operationally detail the research design and data pipeline utilized. The author must provide academic justification for why the chosen analytical approach is the most appropriate for answering the research questions. The methodological description must encompass four pillars:

Research Design and Approach: (e.g., Quantitative Educational Research, Educational Data Mining (EDM), Multimodal Learning Analytics (MMLA), Design-Based Research (DBR), or Mixed-Methods Analytics).

Data Sources and Participants: Detail the specifications of the research subjects (students, teachers, or platform users) and the characteristics of the data corpus. This includes primary/secondary data such as LMS clickstream logs, discussion interaction data (Social Network Analysis), eye-tracking, digital assessments, or curriculum documents.

Data Collection and Preprocessing Techniques: Specify the instruments or systems used to capture data (e.g., extraction plugins, LMS APIs, digital questionnaires, or learning outcome tests). The author must also detail the data cleaning processes, the handling of missing values, and data ethics considerations (participant anonymization).

Data Analysis Techniques: Detail the algorithms or statistical methods used to process the data and generate conclusions (such as regression models, Machine Learning classification algorithms, Process Mining, Epistemic Network Analysis (ENA), or thematic analysis for qualitative approaches).

B. Discussion

Analytical Character: It is strictly prohibited for the analysis to be purely descriptive (e.g., merely reporting the percentage of student login activities or displaying raw graphical visualizations from the system without extracting pedagogical meaning). The author is required to present sharp, critical analysis to unravel the root causes of learning dysfunctions (why specific data patterns indicate a decline in student engagement) and intervention mechanisms (how data-driven feedback alters student learning behaviors).

Systematics: The exposition must systematically align with the sequence of the formulated research questions. Learning theories (e.g., Self-Regulated Learning, Cognitive Load Theory) or modern analytical frameworks must be operationally applied as analytical lenses to dissect the empirical data findings.

Academic Dialogue: The author must explicitly situate their empirical data findings in a dialogue with the prior literature outlined in the introduction. Demonstrate whether the accuracy, effectiveness, or pedagogical findings of your model support, complement, or refute the theses of previous Learning Analytics researchers.

Global Context Elevation: Even if the data is sourced from local/national institutions, the author must elevate this context into international discourse (e.g., how this predictive model can be applied to universal LMS standardization or global education systems) to ensure relevance for an international readership.

Supporting Elements: The narrative must be fortified with effective data visualizations, such as scatter plots, network diagrams (SNA), model accuracy curves (ROC/AUC), or statistical metric summary tables to support efficient data presentation.

C. Conclusion

Contains the core answers to the research/learning analytics questions investigated.

Must be written as a single narrative paragraph.

It is strictly prohibited to use numbering or bullet points.

Length Limit: Maximum of 4 sentences.

References

Minimum Quota: Must contain a minimum of 15 primary references (prioritizing reputable journal articles in the fields of educational technology and learning analytics).

Format: Must strictly utilize the Chicago Manual of Style (Full Note) format.

Digital Requirements: Active DOIs are mandatory for all scientific journal articles.

Text Formatting: Use Title Case (Capitalize Each Word) for book titles and journal names.