From ideal to reality: segmentation, annotation, and recommendation, the vital trajectory of intelligent micro learning

Abstract

The soaring development of Web technologies and mobile devices has blurred time-space boundaries of people's daily activities. Such development together with the lifelong learning requirement give birth to a new learning style, micro learning. Micro learning aims to effectively utilize learners' fragmented time to carry out personalized learning activities through online education resources. The whole workflow of a micro learning system can be separated into three processing stages: micro learning material generation, learning materials annotation and personalized learning materials delivery. Our micro learning framework is firstly introduced in this paper from a higher perspective. Then we will review representative segmentation and annotation strategies in the e-learning domain. As the core part of the micro learning service, we further investigate several the state-of-the-art recommendation strategies, such as soft computing, transfer learning, reinforcement learning, and context-aware techniques. From a research contribution perspective, this paper serves as a basis to depict and understand the challenges in the data sources and data mining for the research of micro learning.

Deep-Cross-Attention Recommendation Model for Knowledge Sharing Micro Learning Service

“…As a novel online learning style, micro learning aims to utilize users' fragmented spare time by helping them to carry out effective personalized learning activities [1][2][3]. Such online learning activities could be formal, informal, and non-formal [4], and online knowledge sharing is one way of non-formal learning.…”

“…Such online learning activities could be formal, informal, and non-formal [4], and online knowledge sharing is one way of non-formal learning. Quora, 1 Zhihu, 2 and Stackoverflow 3 are the most representative and successful online knowledge platforms, where users share knowledge by asking and answering questions. In the meantime, the online platforms continuously recommend questions and topics to the users based on their interests, background, and learning requirements.…”

Attention-Based Knowledge Tracing with Heterogeneous Information Network Embedding

“…For example, the sparsity of students' behavior. Specifically, students usually use fragmented time to study, which only spend little time on the platform [4]. As a result, each student may only practice a small part of the test questions in system so that the mastery of a large part of knowledge is still unknown, which affects the knowledge tracing and limits the further application.…”

Refinement and augmentation for data in micro open learning activities with an evolutionary rule generator

“…Ultimately, ARM is utilized to discover and produce machine‐understandable knowledge that can further give rise to the segmentation of non‐micro learning OERs into chunks with much shorter time length, automatic annotation of micro OERs and construction of adaptive mechanisms (Lin, Sun, Cui et al ., 2019).…”

“…As investigated in our pilot studies (Lin, Sun, Cui, et al ., 2019; Lin, Sun, Shen, et al ., 2019b), the unsatisfactory availability, readiness and quality of existing educational data, especially for micro open learning, considerably put off the lift of implementation of data‐hungry AI into the current micro OER delivery. Consequently, improving both the quantity and quality of existing data are placed at the central of research of adaptive micro open learning.…”