Introduction

This sub-conference is dedicated to exploring the paradigms, principles, design, practice, and application of learning analytics and assessment. Its primary goal is to analyze learning data to uncover patterns of learners' behavior, predict learning performance, advance the design and development of technology-supported learning tools, and gain a deeper understanding of the learning process. The convergence of disciplines including learning technologies, educational research and practice, cognitive and learning sciences, computer science, data science, psychology, linguistics, and other related areas underpins the fields of learning process and learning assessment. Challenges arise from the transdisciplinary nature, multivariate analysis, and methodologies of learning analytics and learning technologies, necessitating cross-disciplinary systematic research and data-driven solutions. The sub-conference provides a platform for scholars to share knowledge, experience, ideas, and strategies to generate new theoretical and practical insights to propel the field forward. While researchers are encouraged to consider the suggested topics for discussion, the scope of research topics extends beyond these suggestions.

Paper Submission Topics (including but not limited to the following)

1. Tools and Methodology for Learning Analytics

This theme covers approaches, tools, and methodologies in learning analytics. We explore various methods and approaches in the study of learning analytics and investigate the tools and techniques employed in learning analytics. The focus is on examining paradigms in learning analytics research, specifically theoretical frameworks and methodologies adopted in educational research. Emphasis is placed on optimizing teaching and learning experiences to provide more effective support for learners. The following are some examples of research areas:

Learning analytics approaches, methods, and tools

Learning analytics research paradigm and curriculum design

Design and application of learning analytics tools

2. Decision-Making and Evaluation in Learning Analytics:

This theme concentrates on utilizing data to diagnose learners and provide timely and effective feedback accurately. We address assessment methods for tracking changes throughout the learning process and evaluating outcomes, enabling educators to comprehensively understand students' learning situations. Additionally, the sub-conference encourages the integration of innovative technologies to enhance the efficiency and accuracy of assessments. The following are examples of research areas:

Data-informed diagnosis, feedback, and decision-making

Measures of learning processes, changes and outcomes

Technological innovations and integration in assessment

Adaptive Learning Technology and Application Research

Learning analytics supported activities, applications, and interventions

3. Learner Characteristics and Learning Analytics:

Learner characteristics and learning analytics focus on individual differences among learners. By analyzing diverse traits such as emotions and behaviors, we propose corresponding assessment methods to better understand students' academic performance and potential. The aim is to delve into learners' personalized needs and behavioral patterns, achieving a more personalized, flexible, and efficient learning experience. The following are examples of research areas:

Theories and Practices of Multimodal Learning Analysis

Learner emotion analysis technology and application

Studies on learners’ knowledge-hiding behavior and evaluation

4. Human-Computer Interaction and Learning Analytics

With the rise of generative AI across industries, this sub-conference seeks to explore learning analytics research in the context of the human-computer interaction process. The theme focuses on understanding how learning analytics technologies can comprehend and enhance interactions between individuals and intelligent partners. Exploring the ethical and moral norms to be followed in learning analytics and AIED and investigating the construction of learning theories and their manifestations in interactions. "By leveraging the understanding of learning analytics technology and adapting to interactions between individuals and intelligent companions, personalized learning support is provided, fostering more effective teaching and learning interactions. The following are examples of research areas:

Understanding human-computer interaction through learning analytics technology.

Constructing theories of learning in human-computer interaction.

Ethics and laws in Learning Analytics and AIED

Paper Submission

Full manuscripts shall be submitted to the conference for review. Abstract submissions will NOT be accepted. This conference uses double-blind review, which means that both the reviewer and author identities are concealed from the reviewers, and vice versa, throughout the review process. Please kindly note that when authors submit papers for review, the authors’ information has to be blinded in the title, the contents, and the reference part. After the paper is being accepted, the author information will be displayed in the final version of the submitted paper.
  1.Authors should only prepare submissions in Chinese (Long paper: 8 pages; Short paper: 4 pages; Poster: 2 pages). Submissions written in Chinese should include the title, abstract and keywords written in both Chinese and English.
  2.Authors should make submissions by uploading papers onto the Submission System of the conference https://easychair.org/conferences/?conf=gccce2025
  3.Authors should submit papers with PDF format. Please make use of the paper template for preparing submissions.
  4. Please pay attention to all English papers, regardless of topic, please submit to English Paper Track。
  5. At least one author is required to register and present for publication once a paper is accepted.

C7 Program Committee

Executive Chair

Co-Chairs

Program Committee Members