About the Project
Rational and background
I am seeking PhD candidates interested in educational assessment and learning analytics in technology-enhanced learning environments. My research uses rich process data and advanced quantitative and AI-based methods to understand not only whether learners succeed, but how learning, problem solving, self-regulation, and collaboration unfold over time.
Digital learning and assessment environments generate increasingly rich traces of learner activity, including clickstream and log data, response times, dialogue and textual data, interaction sequences, and multimodal classroom records. These data create opportunities to move beyond static outcome scores toward process-based educational assessment: approaches that model learning processes, identify meaningful patterns of interaction and strategy use, and generate interpretable evidence for assessment, feedback, and instructional decision-making.
The PhD candidate will develop an independent project aligned with the broader theme of process-based educational assessment. Possible research directions include:
- Process-based assessment of complex skills such as collaboration, problem solving, planning, and self-regulated learning;
- Learning analytics and educational data mining using log, sequence, temporal, conversational, or multimodal data;
- AI- and large-language-model-supported analysis of educational interactions and human-AI approaches to coding and assessment;
- Computational psychometrics and measurement models for dynamic, sequential, or nested educational data;
- Temporal analysis of classroom learning, group work, feedback, and formative assessment processes;
- Design and validation of indicators that translate complex learning processes into meaningful evidence for learners and educators;
- Methodological studies using psychometrics, machine learning, process mining, sequence analysis, social network analysis, or Bayesian modelling.
Applicants from education, educational psychology, assessment and measurement, learning sciences, data science, statistics, computer science, or related areas are encouraged to apply. Strong candidates will be interested in connecting substantive educational questions with rigorous analytical methods. Prior programming or quantitative experience is valuable, but specific requirements will depend on the proposed project.
Important Note
- The topics listed above are not exhaustive. Prospective PhD candidates are welcome to propose their own research ideas.
- Candidates are strongly encouraged to contact potential supervisors at least 3 months before the application deadline, as the process of identifying a suitable supervisor and preparing a research proposal may require time.
When you email Assistant Professor Surina He, please:
- Introduce yourself and send your curriculum vitae
- Share about your academic background
- Provide information on your research interests and how it is aligned with this project
- And how you hope to achieve your PhD aspirations
Minimum Entry Requirement
- A Bachelor's degree with honours at least at Second Class Upper level, Master's degree in the relevant areas and the ability to pursue research in the candidate's proposed field of advanced study.
- Shortlisted applicants will undergo an interview session as part of the selection process.
- A valid GRE score is required for applicants who are not graduates of the Autonomous Universities in Singapore. See detailed requirements for English language on competency and GRE requirements here.
Funding Notes
Prestigious scholarships offered by the Nanyang Technological University, Singapore (NTU Singapore) allows outstanding PhD students to pursue their research endeavours at a world-class university. At NTU, we recognize academic excellence and research potential that will help you focus on making groundbreaking discoveries in your field.
For Scholarships and Awards: View Website
References
He, S., & Cui, Y. (2025). Systematic review of process data in computer-based assessments. Computers & Education, 228, 105245.
He, S., Epp, C. D., Chen, F., & Cui, Y. (2024). Change in self-regulated learning patterns after formative assessment via process mining. Computers in Human Behavior, 152, 108061.