An intelligent help system to support teachers to author learning sessions in decision-making in network design
Bibliographic record
Abstract
This research focuses on the application of principles and techniques of artificial intelligence for the generation, testing and recommendation of teaching materials, and for providing Web-based context-sensitive help to teachers engaged in authoring Educational Adaptive Hypermedia (EAH). We study how to apply Machine Learning (ML) techniques to support teachers in authoring learning sessions. This investigation also studies the use of data related to teachers to support the recommendation of teaching materials and the adaptation of Web-based help. Our research also pays attention to the teacher's problems in authoring learning sessions for teaching decision-making in network design. Specifically, this research addresses two problems that university teachers face when they are authoring teaching materials for their courses: lack of time to create teaching materials and lack of time to learn how to use the authoring tools that reduce the time required for creating materials. Regarding these problems, this investigation answers the following questions: (1) What can be the general structure and functionality of an assistant to support teachers authoring learning session in decision-making? (2) Which specific functionalities and characteristics of an authoring tool can allow implementer teachers to adapt teaching material according to their pedagogical goals? (3) How can the assistant generate and recommend examples to support teaching decision-making? (4) How does the assistant make decisions about which kind of help content to show, and which media to use for displaying the content? (5) How does the assistant learn to help teachers in a personalized or customized way? These questions are intended to address and solve the problem of time needed to create adapted case studies for teaching decision-making in network design. Another goal is to reduce the time required to learn the use of an authoring tool to create teaching materials. Consequently, our main idea is to help teachers use a tool rather than teach how to use it. The solution that we created is a Web-based assistant, ARIALE (Authoring Resources for Implementing Adaptive Learning Environments), that supports teachers during the authoring process. ARIALE, is made up of an authoring tool for the creation of learning sessions to teach network design, and an intelligent help system to support the use of the authoring tool. This intelligent help system has two main functions: (1) Generating, testing and recommending examples and learning session to teachers. (2) Offering adaptive context-sensitive help about how to use the authoring tool. We consider that the recommendation of learning sessions and examples, the automatic generation of examples, and the learning of the teacher's decisions related to teaching style and help, are the most important aspects that make our research different, innovative and advantageous in comparison with other studies developed previously. In addition, ARIALE provides context adaptive Web-based help according to the teacher's experience. Our system uses a probabilistic recommender supported by techniques of artificial intelligence, such as classification learning (Bayesian classifier) and Case-Based Reasoning (CBR), to reduce the complexity of finding an appropriate learning session or example for a particular teacher. The recommendation in ARIALE is also based on the automatic generation of examples according to the teacher's preferences, on the addition and reuse of existing examples in a case base, and on the learning of the teacher's decisions related to which examples to use. ARIALE keeps, classifies and uses data related to each teacher's attributes, learning and experience using examples. Decisions about how to provide recommendations and adapt help are based on teacher's data stored in a Teacher Model, and ARIALE learns from these decisions to improve future support to teachers. Data related to used examples models each teacher's teaching style. Each style evolves according examples changes. This view of the Teacher Model is new and helpful, because each teacher must follow a static Pedagogical Model in a classical EAH; instead, our Teacher Model is a knowledge base that allows our system to make more flexible and vary the Pedagogical Model. Our idea of providing more personalized problem-solving support is a new one and is a step forward to support more intelligent collaboration between teachers, beyond the simple sharing of examples between them. Keywords. Automatic case generation, Recommender System, Machine Learning, Case Base Reasoning, Intelligent Help, Adaptive Help, Web-based Help, Adaptive Hypermedia, Human-Computer Interaction
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".