Bridging learning analytics and Cognitive Computing for Big Data classification in micro-learning video collections

Dessı̀, Danilo; Fenu, Gianni; Marras, Mirko; Recupero, Diego Reforgiato

doi:10.1016/j.chb.2018.03.004

Cited by 70 publications

(37 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, for the micro learning service, the content of a learning resource could be in video, text, or audio format. Hence, many studies [26,[31][32][33][34] heavily relied on their annotation strategies on OCR and ASR techniques. In these research works, non-textual information was firstly transformed to textual counterparts, then NLP techniques were applied for the following annotation process.…”

Section: Model-based Annotation Strategymentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2019

View full text Add to dashboard Cite

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.

show abstract

Section: Model-based Annotation Strategymentioning

confidence: 99%

“…Fuzzy Set [34,36,40,41] Shows satisfactory performance in handling the incomplete or imprecise information, which is very significant in modelling a real-life problem.…”

Section: Uncertainty Representation and Modellingmentioning

confidence: 99%

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

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In [15], the authors use cognitive systems for the automated classification of learning videos, with special reference to MOOCs, i.e., exploiting the capabilities of Automatic Speech Recognition (ASR) and Optical Character Recognition (OCR) services to extract text from audio and visual frames so to be able to perform classifications based on taxonomies. Further developments of this work led the authors to find a solution overcoming traditional termbased methods, which analyzes the content of large video collections by means of cognitive services such as: (i) Speech-to-Text tool to get video transcripts, and (ii) the use of Natural Language Processing (NLP) methods to extract semantic concepts and keywords from the above video transcripts [16].…”

Section: The Impact Of Cognitive Computing On E-learningmentioning

confidence: 99%

Collaborative E-learning Environments with Cognitive Computing and Big Data

Coccoli¹,

Maresca²,

Molinari³

2019

JVLC

View full text Add to dashboard Cite

The actual scenario of e-learning environments and techniques is fast-changing from both the technology side and the users' perspective. In this vein, applications and services as well as methodologies are evolving rapidly, running after the more recent innovations and thus adopting distributed cloud architectures to provide the most advanced solutions. In this situation, two influential technological factors emerge: the former is cognitive computing, which can provide learners and teachers with innovative services enhancing the whole learning process, also introducing improvements in human-machine interactions; the latter is a new wave of big data derived from heterogeneous sources, which impacts on educational tasks and acts as enabler for the development of new analytics-based models, for both management activities and education tasks. Concurrently, from the side of learning techniques, these phenomena are revamping collaborative models so that we should talk about communities rather than classrooms. In these circumstances, it seems that current Learning Management Systems (LMS) may need a redesign. In this respect, the paper outlines the evolutionary trends of Technology-Enhanced Learning (TEL) environments and presents the results achieved within two experiences carried on in two Italian universities.

show abstract

“…Dessi et al exploit the capability of Automatic Speech Recognition (ASR) and Optical Character Recognition (OCR) services to extract text from audio and visual frames so to be able to perform a classification based on a taxonomy. Further development of their work led the authors to find a solution to analyze the content of large video collections, overcoming traditional term-based methods by means of cognitive services such as a Speech-to-Text tool to get video transcripts and the use of Natural Language Processing (NLP) methods to extract semantic concepts and keywords from the above video transcripts [16].…”

Section: B the Impact Of Cognitive Computing On E-learningmentioning

confidence: 99%

When E-Learning Meets Big Data, Cognitive Computing, and Collaborative Environments

Coccoli¹,

Maresca²,

Molinari³

2019

International Conferences on Distributed Multimedia Systems

View full text Add to dashboard Cite

The e-learning scenario is fast-changing in all of its main aspects from both the technology side and the users' perspective. In this vein, applications and services as well as methodologies are evolving rapidly running after the more recent innovations, through the adoption of novel infrastructures and distributed architectures, to provide the most advanced solutions. In this situation, we observe that the more influential technological factors are two. The former is the availability of a new wave of big data also inherent educational tasks, which can be considered a powerful source for all the people involved in the educational process and acts as enabler for the development of new models for both management and education, based on analytics. The latter is cognitive computing, which can provide learners and teachers with innovative services enhancing the whole learning process, also introducing new capabilities to improve human machine interactions. In these circumstances, it seems that Learning Management Systems (LMS) have reached their maturity stage and they may need a redesign. In this respect, the paper outlines the evolutionary trends of Technology Enhanced Learning (TEL) and presents the results achieved within two experiences carried on in two Italian universities.

show abstract

Bridging learning analytics and Cognitive Computing for Big Data classification in micro-learning video collections

Cited by 70 publications

References 22 publications

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

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

Collaborative E-learning Environments with Cognitive Computing and Big Data

When E-Learning Meets Big Data, Cognitive Computing, and Collaborative Environments

Contact Info

Product

Resources

About