Adaptive Learning Support System Based on Automatic Recommendation of Personalized Review Materials

Okubo, Fumiya; Shiino, Tetsuya; Minematsu, Toshio; Taniguchi, Yuta; Shimada, Atsushi

doi:10.1109/tlt.2022.3225206

Cited by 14 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some words ("stämband", "förtäting", and "förtunning") (English translation: "vocal cords", "thickening", and "thinning") are lacking inflectional forms. The results indicate that: (1) other non-core domain conceptual words can also provide useful information to the sentence embeddings, which explains why the original ConceptNet Numberbatch model performs better; (2) the training data of ConceptNet for the Swedish language is not large enough to cover all words' inflectional forms, compound words, and phrases.…”

Section: Evaluation Of Conceptnet With Domain-specific Concept Filteringmentioning

confidence: 99%

“…To that end, educational recommendation systems play a crucial role in enhancing the accessibility of relevant content, user engagement, and the effectiveness of learning resource usage by filtering contents, finding items of interest, and suggesting useful learning resources that can meet curriculum goals, users' needs, and profiles. There have been several efforts to develop educational recommendation systems for different purposes, for instance, to provide personalized recommendations of remedial learning materials [1] or to provide a personalized review module [2], while others have proposed different solutions for recommending external learning material in the form of Wikipedia pages and YouTube videos [3][4][5]. In this study, we focus on educational content recommendations based on textbook content and exercises.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating Embeddings from Pre-Trained Language Models and Knowledge Graphs for Educational Content Recommendation

Li,

Henriksson,

Duneld

et al. 2023

Future Internet

View full text Add to dashboard Cite

Educational content recommendation is a cornerstone of AI-enhanced learning. In particular, to facilitate navigating the diverse learning resources available on learning platforms, methods are needed for automatically linking learning materials, e.g., in order to recommend textbook content based on exercises. Such methods are typically based on semantic textual similarity (STS) and the use of embeddings for text representation. However, it remains unclear what types of embeddings should be used for this task. In this study, we carry out an extensive empirical evaluation of embeddings derived from three different types of models: (i) static embeddings trained using a concept-based knowledge graph, (ii) contextual embeddings from a pre-trained language model, and (iii) contextual embeddings from a large language model (LLM). In addition to evaluating the models individually, various ensembles are explored based on different strategies for combining two models in an early vs. late fusion fashion. The evaluation is carried out using digital textbooks in Swedish for three different subjects and two types of exercises. The results show that using contextual embeddings from an LLM leads to superior performance compared to the other models, and that there is no significant improvement when combining these with static embeddings trained using a knowledge graph. When using embeddings derived from a smaller language model, however, it helps to combine them with knowledge graph embeddings. The performance of the best-performing model is high for both types of exercises, resulting in a mean Recall@3 of 0.96 and 0.95 and a mean MRR of 0.87 and 0.86 for quizzes and study questions, respectively, demonstrating the feasibility of using STS based on text embeddings for educational content recommendation. The ability to link digital learning materials in an unsupervised manner—relying only on readily available pre-trained models—facilitates the development of AI-enhanced learning.

show abstract

Section: Evaluation Of Conceptnet With Domain-specific Concept Filteringmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evaluating Embeddings from Pre-Trained Language Models and Knowledge Graphs for Educational Content Recommendation

Li,

Henriksson,

Duneld

et al. 2023

Future Internet

View full text Add to dashboard Cite

show abstract

“…Furthermore, a use case of creating and running this kind of specific type of educational escape room as an evaluation activity is presented in the context of a course of an engineering degree at College, as well as an additional project-based learning activity. In addition to the boost in results achieved, a measurement of the engagement level of the students has also been performed [8], which is a primary source of enhancing academic performance when the magnitude measured is high enough [9].…”

Section: Introductionmentioning

confidence: 99%

A Generic Multilevel Structure for Educational Escape Rooms

Roig,

Alcaraz,

Gilly

et al. 2024

Education Sciences

View full text Add to dashboard Cite

The use of active learning activities for evaluation purposes has been reported to improve results in all areas within the education field. In this paper we describe a generic multilevel structure for educational escape rooms, along with a use case where such a design was applied for assessment in a course within the STEM area. Furthermore, a project-based learning activity was also added to complement that assessment. The results obtained expose an increase in both academic performance and success rate, where the percentage rises in both cases go in line to the literature. Additionally, a high level of engagement was measured during those active learning activities, which is reported to lead to better performance and improved learning. Hence, this high engagement seems to be the primary source of the increments experienced.

show abstract

“…The use of gamification to drive active learning in on-site classes has been widely spread in recent years as a way to enhance learners' engagement [1]. The introduction of game design elements within nongame contexts makes possible to enhance motivation in education, which leads to better performance according to what is appreciated by learning analytics [2]. Furthermore, gamification may be seen as a driving force to achieve the Sustainability Development Goal 4, sponsored by United Nations, related to ensuring inclusive and equitable quality education [3].…”

Section: Introductionmentioning

confidence: 99%

Using Escape Rooms as Evaluation Tool in Active Learning Contexts

et al. 2023

View full text Add to dashboard Cite

The adoption of the active learning paradigm presents a series of challenges and uncertainties. However, its adoption may result in better academic results and a more engaging attitude towards learning. In this sense, this paper presents a case scenario in which such a change of paradigm has been deployed, where escape rooms have been introduced as an assessment tool in an active learning context. The way to move through those escape rooms is by taking a series of questionnaires based on the knowledge acquired, such that failing a test keeps the group in the same position and passing it makes them move according to the grades obtained. Surveys and comments offered by students show they were more motivated and engaged after this task, and an improvement in academic performance has been detected.

show abstract

Adaptive Learning Support System Based on Automatic Recommendation of Personalized Review Materials

Cited by 14 publications

References 37 publications

Evaluating Embeddings from Pre-Trained Language Models and Knowledge Graphs for Educational Content Recommendation

Evaluating Embeddings from Pre-Trained Language Models and Knowledge Graphs for Educational Content Recommendation

A Generic Multilevel Structure for Educational Escape Rooms

Using Escape Rooms as Evaluation Tool in Active Learning Contexts

Contact Info

Product

Resources

About