Contact Information
707 S. Mathews Ave. | MC-168
Urbana, IL 61801
Research Interests
Computational Linguistics
Language assessment
Second Language Writing
Quantitative research methods
Education
M.A. Linguistics, University of Illinois Urbana-Champaign, United States, 2022
M.A. Foreign Languages and Applied Linguistics, Zhejiang University, China, 2020
B.A., English Language and Literature, Zhejiang University, China, 2017
Grants
TIRF Doctoral Dissertation Grant (October 2025); Project: Exploring a Feature-Based Explainable Automated Essay Scoring System for Local L2 Integrated Argumentative Writing Assessment.
LTTC Joint-Funded Research Grant (August 2024); Project: Development of Feature-Based AI-assisted Scoring System for BESTEP's Integrated Writing Tasks.
LTTC Joint-Funded Research Grant (August 2022); Project: What makes listening comprehension difficult?: A technology-enhanced approach to examining the psychometric quality and construct validity of GEPT listening test.
Awards and Honors
SLCL Dissertation Completion Fellowship, UIUC, Urbana, IL (August 2025)
C.W. Kim Research Award, Department of Linguistics, UIUC, Urbana, IL (May 2024)
Graduate Student Award Nominee, American Association for Applied Linguistics (AAAL) (March 2024)
Conference Travel Award, Department of Linguistics, UIUC, Urbana, IL (November 2023)
Graduate Student Award Nominee, American Association for Applied Linguistics (AAAL), (March 2023)
Conference Travel Award, Department of Linguistics, UIUC, Urbana, IL (February 2023)
Courses Taught
LING 448 Introductory Machine Learning (TA)
LING 413 Corpus Linguistics (TA)
LING 402 Tools & Technology in Speech and Language Processing (TA)
ESL 522 Introduction to Business Writing (Instructor)
Highlighted Publications
Cai, H., Tang, Y., & Yan, X. (2026). A Tutorial on unsupervised Gaussian Mixture Model for performance clustering in second language research. Research Methods in Applied Linguistics, 5(1), 100296.
Cai, H., Yan, X., Chuang, P.L., Pan, Y., & Huo, M. (2025). What makes listening comprehension difficult?: A feature-based machine learning approach to understanding item difficulty. Applied Linguistics, amaf079.
Cai, H. & Yan, X. (2024). Examining the direct and indirect impacts of verbatim source use on linguistic complexity in integrated argumentative writing assessment. Assessing Writing, 61, 100868. [Editor's Choice Pick]
Cai, H. & Yan, X. (2024). Triangulating natural language processing (NLP)-based analysis of rater comments and many-facet Rasch measurement (MFRM): An innovative approach to investigating raters’ application of rating scales in writing assessment. Language Testing, 41(2), 384–411.
Recent Publications
Yan, X., Chuang, P.L., Cai, H., Pan, Y., Staples, S., & Bertho, M.C. (R & R, 2nd round). Disfluency co-occurrence implicates oral language proficiency: Comparing the predictive power of single vs. co-occurrence features. Language Assessment Quarterly.
Yan, X., Chuang, P.L., Pan, Y., Cai, H., Staples, S., & Bertho, M.C. (2025). Disfluency doesn’t happen in isolation: Exploring how individual disfluency features co-occur in L2 speaking performances. Studies in Second Language Acquisition, 47, 560–591.