Hi there! I am a graduate student researcher at UC Berkeley. I received my PhD degree from Tsinghua University, Management Science and Engineering department in June 2020, and have been committed to designing computational approaches to cross-disciplinary areas, such as education and e-commerce. My research interests include Learning Analytics, Machine Learning, and Recommender Systems etc. Most of my research deal with dynamic user modeling, which ignited my intersts in various NLP related learning methods (such as HMM, RNN, attention-based models such as Transformer) and adapting them to germane recommendation contexts. I am curently committed to promoting equity and fairness in learning analytics research.
I also contributed to academia by professional activities:
Session Chair at the 28th ACM International Conference on Information and Knowledge Management (CIKM 2019), Nov 2019, Beijing, China (Session “Long Paper: E-Commerce and Advertising I”)
Reviewer for PLOS ONE (2020), AERA Open (2020), Knowledge-Based Systems (2020), International Conference on Educational Data Mining (2020), International Conference on Learning Analytics and Knowledge (2020), ACM Conference on Learning @ Scale (2019), International Conference on Learning Analytics and Knowledge (2019), International Conference on Educational Data Mining (2019), International Conference on Artificial Intelligence in Education (2019), and Ecommerce Commerce Research (2016)
Student Volunteer at the 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
In my spare time, I love singing, creating, and outdoor sports. Thanks for visiting!
University of California, BerkeleySeptember 2017 - October 2018  Visiting Student Researcher,   Computational Approaches to Human Learning Lab (CAHL)
Research focuses on Learning Analytics and Recommender Systems.
Developed machine learning algorithms for UC Berkeley Personalized Course Guidance and Recommender System AskOski to help improve students' learning outcomes.
Designed a goal-based recommendation framework to help students achieve their educational goals, e.g., achieving a high grade on a hard course or passing a quiz. Applied the framework to Massive Open Online Courses (MOOCs) contexts, personalizing learning materials (pages or videos) within a course to help prepare for the next quiz in that course.
Designed a representative learning algorithm to offer similar-course and serendipitous-course recommendations. Conducted a user study of 70 UC Berkeley undergraduates to evaluate the system and shed light on the system design.
Collaborated with development team to help create and maintain the ‘Explore’ function of AskOski, which has been monthly used by around 15\% of the 30,000 UC Berkeley undergrads.
Tsinghua UniversitySeptember 2014 - June 2020  Ph.D.,    Management Science and Engineering,   School of Economics and Management
Research focuses on developing computational methods to management problems, such as in marketing contexts.
Teaching Assistant: “Managing in the Age of Big Data”(2016, 2017, 2019), "Practical Strategic Management"(2019), “Data Structure”(2017), “Data, Model and Decision”(2016), “Knowledge Management in the Age of Big Data”(2015)
Invited talk at the Institute for Operations Research and the Management Sciences (INFORMS) Annual Meeting 2019, Oct 2019, Seattle, WA, USA.
ACM SIGKDD Student Travel Award (Granted by ACM SIGKDD, 2019)
First-class Scholarship (Granted by Tsinghua University, 2018)
Government Scholarship for PhD students to conduct research abroad (Granted by Chinese Scholarship Council, 2017)
Beijing Language and Culture University September 2010 - June 2014  B.S.,    Information Management and Information Systems,   School of Information Sciences
Ranked the 1st among 54 students throughout four years.
Beijing Excellent Graduate (Granted by Ministry of Education, Beijing, 2014).
Honorable Mention in the 2013 Mathematical Contest in Modeling (Granted by the Consortium for Mathematics and its Application of the USA, 2013).
National Scholarship (Granted by Ministry of Education, China, 2013, 2011).
First Prize at National Computer Science Design Contest (Granted by Ministry of Education, China, 2013).
Beijing Merit Student (Granted by Ministry of Education, Beijing, 2011).
- Time Slice Imputation for Personalized Goal-based Recommendation in Higher Education by Weijie Jiang and Zachary A. Pardos. Proceedings of the 13th ACM Conference on Recommender Systems (RecSys 19). ACM, pp 506-511 (2019).
- Combating the Filter Bubble: Designing for Serendipity in a University Course Recommendation System by Zachary A. Pardos and Weijie Jiang. The 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining Workshop on Deep Learning for Education (KDD 19 DL4ED Workshop). [code]
- Combination of Convolutional and Recurrent Neural Network for Sentiment Analysis of Short Texts by Xingyou Wang, Weijie Jiang and Zhiyong Luo. Proceedings of the 26th International Conference on Computational Linguistics (COLING 16). ACM, pp 2428-2437 (2016).
- Evaluations of representative learning methods on various course prediction tasks by Weijie Jiang and Zachary Pardos. Proceedings of the 13th International Conference on Educational Data Mining (EDM 20), pp 115-125 (2020). [presentation][code]
- Designing for Serendipity in a University Course Recommendation System by Zachary A. Pardos and Weijie Jiang. Proceedings of the 10th International Conference on Learning Analytics and Knowledge (LAK 20), ACM. pp 350-359 (2020)[code]
- A Dynamic Bayesian Network based Collaborative Filtering Model for Multi-stage Recommendation by Weijie Jiang, Qiang Wei and Guoqing Chen. Proceedings of the 10th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT 17). Springer, pp 290-301 (2017).
- Connectionist Recommendation in the Wild: On the utility, scrutability, and scalability of neural networks for personalized course guidance by Zachary A. Pardos, Zihao Fan and Weijie Jiang. User Modeling and User-Adapted Interaction (UMUAI). Springer. pp 1-39, (2019).
- A Dynamic Bayesian Network Based Multi- Period Recommendation Method Considering Consumer Preference and Stage Conversion by Weijie Jiang, Qiang Wei and Guoqing Chen. Major revison, Information Systems Research. INFORMS.
Microsoft Research Asia (MSRA)November 2013 - June 2014
Improved Microsoft Kinect’s multi-person handshapes classification accuracy for hand-controlled games.
Extracted skeleton of hands from depth information by the deep sensor as training samples for neural networks. Normalized the depth value of each pixel in handshape figures. Fed skeletons to Convolutional Neural Network (CNN) for pose recognition. Employed “Bootstrap” strategy to mine hard training examples.
The approach has been embedded in Microsoft Kinect for multiple handshapes recognition, reaching an accuracy of 99.8%, and won the “Star of Tomorrow” Internship Award of Excellence.
I had been a member of the university choir, and won "The Top Ten Singers" award in my school. I am also a big fan of Tom and Jerry and Rick and Morty. My favorite animal is Labrador Retriever. Beach is the best place for me to relax and meditate. Here are my favorite singers, movies and books.
Hachiko: A Dog's Tale
Léon: The Professional
Why We Work (Barry Schwartz)
The Seat of the Soul (Gary Zukav)
Be Your Personal Best (KaiFu Li)