Personalized Instructional Path Generation for Chinese Language Education Incorporating Reinforcement Learning
Bibliographic record
Abstract
Personalized learning, in which learners set their own pace and select their own resources according to their own learning needs and characteristics, is the trend of Chinese education and teaching.In this paper, we design a personalized teaching path recommendation model for Chinese education based on reinforcement learning.The knowledge tracking prediction model LTKT is designed to integrate multiple knowledge points as information dimensions for model learning in the data preprocessing stage.The sparse self-attention mechanism is introduced into the encoder and decoder structure and embedded with location coding containing absolute and relative distances to enhance the model's perception of location information.Finally, the RL4ALPR algorithm is designed to model the changing knowledge level, the candidate learning item filtering algorithm is used to narrow down the scope of the recommended learning items, the reinforcement learning algorithm assumes the role of a recommender, and the degree of change in the knowledge level of the learner is regarded as a reward for the improvement of the reinforcement learning recommendation strategy.Simulation experiments are conducted on datasets such as ASSISTments and compared with baseline models such as KNN, GRU4Rec, Random, etc.The model in this paper has an F1 value and an AUC of 0.635 and 0.956 respectively in the evaluation of learning effect, which are the highest among the models.The study makes a useful exploration for the informatization of Chinese education and teaching.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".