Sharing and re-using learning objects Using web-mining techniques and Clustering algorithms

doi:10.21203/rs.3.rs-2242303/v1

The development of learning objects and e-pedagogical practices has significantly influenced and changed the performance of e-learning systems. This development promotes a genuine sharing of resources and creates new opportunities for learners to explore them easily. Therefore, the need for a system of categorization of these objects becomes mandatory. In this vein, classification theories combined with web mining techniques can highlight the performance of these learning objects and make them very useful for learners. This study consists of two main phases. First, we extract metadata from learnings objects, using the algorithm of Web exploration techniques such as feature selection techniques, which are mainly implemented to find the best set of features that allow us to build useful models. The key role of feature selection in learning object classification is to identify pertinent features and eliminate redundant features from an excessively dimensional dataset. Second, we identify learning objects according to a particular form of similarity using Multi-Label Classification (MLC) based on Fuzzy C-Means (FCM) algorithms. As a clustering algorithm, FCM is used to perform classification accuracy according to Euclidean distance metrics as similarity measurement. Finally, to assess the effectiveness of learning objects with FCM, a series of experimental studies using a real-world dataset were conducted. The findings of this study indicate that the proposed approach exceeds the traditional approach and leads to viable results.

Learning Objects

Multi-Label Classification (MLC)

Web-based Mining Techniques

Fuzzy C-Means Clustering algorithm (FCM)

Machine Learning

The development of many distance-learning systems around the world and the growth of numerous massive open online courses contribute largely to sharing and re-using learning objects. This development of learning objects can also support teachers and their students alike by bridging specific learning needs. In this context, the classification of these objects can help learners easily release the most relevant information and select the most appropriate one for themselves. However, the vast majority of current e-learning environments are not structured to cover the efficiency of learning object properties and, consequently, do not provide the multiple uses and reuses of resources in different contexts. In this respect, the classification approach as a technique can be suggested to resolve this problem by exploring different metadata content for every learning object. The classification of learning objects, as described by the authors in [1], is a process of machine learning tasks which is used to structure a group of learning objects by means of different methods, including Bayesian classification, Support Vector Machine, etc. [2]. The term "Learning Objects" as a concept in an E-learning system was mentioned by Wayne Hodgins in 1994 [3], and since that time, several definitions have been proposed with different terminology like "Pedagogical Objects," "Content Objects," and "Knowledge Objects" to enrich this definition. In 2002, the Learning Technology Standards Committee of the Institute of Electrical and Electronics Engineers (known as IEEE) defined a learning object as "any entity, whether digital or not, that can be used for learning, education, or training." [4]

The purpose of this study is two-fold. First, it seeks to establish a theoretical model of learning objects' classification based on MLC approach combined with a Fuzzy Logic method. Second, it aims to suggest a new method of sharing objects based on classification by using web-mining techniques. This document is structured as follows: Section One provides an in-depth definition of the main ideas used in this article. Section two offers a summary of learning object classification methods. Section three will present our approach, and finally, section four will display the experimental results.

2.1. Learning Object

In recent years, there has been an intense debate about creating modern and effective digital teaching materials. These materials are often described as "Learning Objects". The main idea of the creation and schematization of learning objects as specific pedagogical tools is not far from the usual school materials, which are traditionally used by teachers in the classroom. What distinguishes the nature of learning objects from other types of documents is their digital form, their creation in a computer environment, but also their supply of special features that allow them to be searched in a specific repertoire. These objects, which are recognized in the international scientific community as learning object, present a significant diversity. In 2006, A. Robertson [5] attempted to schematize existing approaches: "For some, it is a numerical or non-numerical entity that can be indexed for learning purposes." Learning object can be associated with content objects [6], with educational objects [7], with information objects [8], and with knowledge objects [9]. As M. Dodani [10] encodes them, learning objects must have the following characteristics in order to function adequately at an individual level and in order to be easily and effectively used and transformed in different educational environments:

They are small, self-contained units of learning that offer a concept, information, or a process. These entities are distributed after having been previously tested and evaluated.
They are described by "metadata" that allows us to classify and search for them.
They are combined with other learning objects to create complex educational entities, such as a set of concepts.

In practice, a learning object can be a web page, an image, a simulation, a test, or any other type of element involved in learning. Learning objects are not limited to courses or training content. A learning object can also refer to a procedure or guidelines to help the learner on his academic pathway.

The Learning Technology Standards Committee (LTSC) has defined the concept of «learning objects» as "Any entity, digital or not, that can be utilised for learning, education, or training is characterised as a learning object," [11], In his Ph.D. thesis, David Wiley analysed the design of learning objects and came up with his own definition, which was "any digital resource that can be reused to promote learning" [12]. In the organizational context, learning objects are generally defined in the terminology of the LMS or LCMS vendor. Chapman and Hall [13], note that in this context, there is no coherent definition of a learning object; "...each of the companies using the learning object metaphor has its own defined relationship and characteristics for what constitutes a learning object." An example of such a model is shown in Fig. 1.

This model illustrates the idea of a layered model that is often found in e-learning scenarios. Each layer represents a new level of abstraction, starting with a very concrete data object that encompasses exactly one element. In this model, the bottom layer consists of raw data, such as textual data, videos, presentations, etc. This data can be collected in a "Reusable Learning Object". Chapman and Hall concluded their research by saying, "We hope to see better definitions and common standards for learning objects in the future."

The learning object technology can be viewed at four different levels:

The object technology itself, including the model of the reference used to label, or meta-label, the item.
The technology related to the repository in which the objects are being collected, including the database technology and/or the content management technology of the learning object [13];
The technology for referential-related services, such as searching, browsing, previewing, and downloading tools.
The technology to support the exchange or interaction of learning objects among systems and repositories

Learning objects have a number of functions in the current blended learning system. The prospective learning objects can be acquired through contracts with software developers, and also be procured through the exchange and sharing of digital materials that are being entered by course designers, course presenters, and course participants into the databases of learning content management systems, such as LMS, SAP, and CMS (course management systems) [14] (Fig. 2).

2.2. Classification of Learning Object in E-learning System

Many studies [15] [16] used classification techniques to classify learning objects detected in e-learning systems. In [17], the authors shed light on the main classifiers that have been proven efficient in e-learning systems. The authors then propose a model that combines decision trees, neural networks, and naive Bayesian methods into a single module [18]. In 2015, several studies on the classification of learning objects have been conducted, using different resources and properties. In 2019, authors [20] introduced a new concept of learning object classification based on Long Short-Term Memory (LSTM) and the Random Forest classification approach. In this article, the authors provide an overview of the application of data mining methods in the e-learning process with web-based learning. However, with MLC paradigms, only nine papers in the literature have developed learning objects in e-learning systems. These papers offer a variety of approaches for incorporating feature-label correlations into learning objects' metadata in order to improve accessibility and recommendation at the same time. This work concentrates on how to modify formal single-label classifiers to multiple labels. Working on a model for multi-label classification and ranking of learning objects, the authors of [21] associated the concept of searching learning objects marked by Learning Object Metadata (LOM). More specifically, the model provides a methodology that shows the task of multi-label mapping of learning objects into different kinds of inquiries. In [22], researchers identify learning items by comparing and contrasting four MLC systems. The authors of [23] investigate hierarchical multi-label categorization in the context of recommender systems. They propose a hierarchical multi-label metadata categorization with a machine-learning method to enhance the search and classification of educational resources. Additionally, this study contributes to previous research by providing a hierarchical multi-label learning object dataset in an appropriate format. Table 1 presents a review of the significant research articles that have adopted MLC methods.

Table 1

Summary of the significant studies that applied MLC methods on the learning objects.
Perspective question	Description
González et al (2017) [24]	Automatic classification of learning objects to reducing the number of used features
Batista et al.(2011) [25]	A System for multi-label classification of learning objects.
López et al (2012) [26]	A model for multi-label classification and ranking of learning objects
Carrillo et al (2013) [27]	Multi-label classification for recommender systems
Birzniece et al (2014) [28]	Application of interactive classification system in university study course comparison
Aldrees et al (2016) [29]	Comparative evaluation of four multi-label classification algorithms in classifying learning objects
Xie et al (2018) [30]	Multi-label Green's Function Criterion inspired Transfer Annotation System
Tan et al (2019) [31]	Label Enhancement Manifold Learning Algorithm for Multi-label Image Classification

Based on the historical and present research contexts, a number of questions and challenges can be determined that can provide the foundation for the research questions in this research study. The use of learning objects can be related to issues of what is being reused, also stating the level of detail and granularity: how is the material being used again, focused on duplicating, connecting, blending, and publishing the material. Questions also emerge for the various actors that are involved as to who reuses what. The question of where material is being reused addresses the exchange of material among people, as well as organisations and their systems, but also the distinctions among learning situations. The content product development lifecycle defines when a material is available for reuse. All of these issues can be considered from a more organised and collaborative perspective. Table 2 illustrates how the common learning object questions can be seen from their structural and relational perspectives by taking them as insights.

Table 2

General Questions Related to Learning Objects.
Perspective question	Description
Why?	What is the purpose of the reuse? Why would humans need to invest time and effort during the different stages of a learning object's life cycle?
Who?	Who is engaged in the Reusability process?
What?	What is the gradation and the type of material being reused?
Where?	Where does reuse fit in terms of systems?

All of these questions, as well as other common questions, will be asked in different ways, and will discuss learning objects at different points in their development.

In this article, our first thought started with the idea that semantically similar terms are used in similar contexts. This arises the question of how we can manipulate e-learning resources like courses, videos, and pedagogical support in a flexible manner. Additionally, how can we explore and reuse these resources efficiently in different areas? For the first question, we have used object learning philosophy, in which every resource can be analysed and schematized according to IEEE learning objects standardisation, such as metadata, taxon, identifier, etc. To explore this metadata, our interest is focused on FCM Clustering Algorithm, web data mining and machine learning algorithms. For the second question, we thought of using MLC in order to reuse them in different contexts.

4.1. Web Data Mining

The Web Data Mining concept was defined in 1996 as "a new generation of computational theories and tools to assist humans in extracting useful information (knowledge) from the rapidly growing volumes of digital data"[32]. The fundamental objectives of web data mining can be summarized as follows: they bring into the fore front invisible information, they take into account the volume of web data, they also transform the massive amount of web data into expert knowledge, and they provide valuable knowledge to the users despite the numerous attempts to characterize this field. The term "web data mining process" is frequently used with a combination of different techniques from various disciplines, including data analysis, artificial intelligence, and machine learning [33]. A typical process of web data mining can be described in three successive steps: data preparation or pre-processing data, discovering patterns and analyzing patterns. The pre-processing phase includes cleaning operations needed for the metadata of learning object normalization. In other words, it reduces the data dimension by implementing different tasks, allowing the elimination of extra information like stop words, double adjectives, etc. In the second phase, all information already prepared in the pre-processing step deals with the extraction methods in which all data is labelled using machine learning algorithms. Finally, in the analyzing process, the set of appropriate patterns will be presented by degree of similarities [34].

4.2. Fuzzy C-Means Clustering Algorithm

Clustering is a statistical analysis method that is used to organize raw data into homogeneous silos [35]. Within each cluster, data is grouped according to a common characteristic. The clustering tool is an algorithm that measures the proximity between each element based on defined criteria. The purpose of clustering algorithms is to make sense of data and extract value from large amounts of structured or unstructured data. These algorithms allow the segmentation of data based on its properties or functionality and help to group them into different clusters based on their similarities. There are two types of clustering: hierarchical clustering and non-hierarchical clustering [36]. This explains that Fuzzy C-Means clustering is an unsupervised non-hierarchical clustering algorithm that tries to partition a finite collection of elements into a collection of fuzzy clusters with respect to some given criterion [37]. The algorithm of fuzzy c-mean clustering can be summarized as follows: In the beginning, it fixes the value of c (number of clusters) and selects a value of m (generally m takes a value between 1.25 and 2), and initializes the partition matrix Dij, then compute cluster centers, which will be repeated until the maximum convergence is reached.

4.3. Multi-Label Classification approach

MLC is an automatic process that uses analysis techniques in order to label objects and classify them by topic. This approach uses a supervised learning method where a feature may be connected with multiple labels. It is opposed to single-label classification when each feature is associated only with a single class (label). Furthermore, MLC is widely used in real-world problems such as bioinformatics, e-commerce, and so on. Due to their efficiency with the huge size of data and the difficulties of assigning a single label to objects, MLC plays an important role in the process of learning object classification. However, few and insufficient studies have explored the MLC problem in the e-learning area.

Our methodology is composed of two stages, as indicated in Fig. 3. In the first phase, known as the learning phase, our algorithm generates a list of learning objects based on the extraction performed by web mining techniques and the similarity executed by FCM. In the second phase, our algorithm classifies the learning objects listed in the first phase according to the degree of similarity and labels them with multi-label classification in order to reuse objects and propose the top recommendations to the learners. With this approach, we expect two objectives: the improvement of the similarity of the terms analysed and extracted by the web mining and the optimization of the metadata of each learning object to facilitate its use.

6.1. Corpora Summary

Different companies’ data has been selected to conduct the present study. This data consists of presentation, practice, and conceptual models of learning objects with a variety of categories. Table 2 shows the descriptions of learning objects used in our studies.

Table 3

A description of the learning objects used in our research.
Lo Type	Explantation	Example
Presentation Object	Transmit specific information about specific subject.	Theories of E-learning system
Practice Object	Practice with feedback	Quiz, exercises, QCM.
Conceptual model	Summer of some subjects with related concepts.	Visual representation of phenomena

The companies from which the data is collected include the Moodle datasets, the Blackboard datasets, and the Schoology datasets.

Moodle is a free and open-source learning platform. It offers specific solutions to various educational needs, like Moodle App, Moodle Education, Moodle Net, Moodle Workplace, and Certified Integrations [38].
Blackboard is one of the most popular names in the digital learning area. The platform provides the core learning management features. It can also manage online and blended classes [39].
Schoology platform aims to provide all the tools that professors need to design lessons, communicate with their students, and collaborate with other educators.

6.2. Experimental Procedure and Performance Measure

To evaluate the performance of our approach, we used a set of indicators in the form of mathematical rules, such as classification accuracy (1), precision (2), recall (3), and F1-measure (4). These indicators are generally used to examine the performance of any proposed system compared to the existing ones. The following are descriptions of these indicators:

Classification Accuracy

Classification accuracy shows how many of the predictions are correct.

$$Accuracy=\frac{Number of correct predictions}{Number of all predictions}$$ (1)

In some situations, accuracy serves as a good measure, while in others, it appears insufficient. For instance, a prediction accuracy of 94% indicates that 94 out of 100 samples were successfully anticipated without prior knowledge of which tasks were properly predicted.

Precision and Recall

By going beyond classification accuracy, precision, and recall measures, they give us a clearer picture of how to evaluate models. The task and our objectives will determine which one we should favour.

Precision measures how good our model is when the prediction is positive.

$$Precision=\frac{TP}{TP+FP}$$ (2)

With:

TP (True positive): Predicting positive object as positive (ok)

FP (False positive): Predicting negative object as positive (not ok)

Recall measures how good our model is at correctly predicting positive classes.

$$Recall=\frac{TP}{TP+FN}$$ (3)

With:

FN (False negative): Predicting positive class as negative (not ok)

F1_measure is calculated as follows:

$$F1\_measure=\frac{2.Precison.Recall}{precision+Recall}$$ (4)

6.3. Dimensionality Reduction

The selection criterion is mainly aimed at selecting the most relevant model that suggests the most appropriate learning objects. For this, classification techniques are very beneficial, both for the management systems that contain these objects and for the learners, who will benefit from a simple and fast search. In addition to this, with a good classifier, the initial data will be transformed into a new dimension by ignoring the massive data that is not appropriate.

In our article, we will evaluate the validity of our approach by comparing its indicators of performance (PR: precision, RE: recall, and F1-measure) to the traditional machine learning algorithms for classification and suggestion like SVM and Naive Bayesian. For this concern, we will use Python as a software platform, which has all these machine learning algorithms already programmed. In our approach, we will first test the performance of the data with SVM, and then we will move to test the same data with SVM combined with multi-labeled classification and FCM. To confirm the precision of our suggested approach, the same data was used with NB ( Naive Bayesian) and NB combined with Multi-labeled classification and FCM. The results appear in Table 2 and show that our approach performs better for the classification of learning objects compared to other learning algorithms in different corpora. The computed results of different classifiers in Table 3 confirm that the results of SVM combined with the fuzzy logic clustering method and multi-ladled classification for data reduction are generally better than NB and its variants.

Table 4

Comparison of Different Machine Learning Methods Using FNN and FCM
DataSet	Moodle			Blackboard			Schoolary
	PR	RE	F1	PR	RE	F1	PR	RE	F1
SVM	90,03	53,04	87,5	94,52	67,87	89,10	89,45	51,87	89,01
NB	84,19	45,90	77,3	83,22	58,43	79,5	87,16	49,67	81,23
SVM + Fuzzy C-Means + multi-label	92,07	58,81	91,4	95,52	72,87	90,01	89,89	57,43	90,98
NB + Fuzzy C-Means + multi-label	87,37	49,56	83,1	85,01	64,94	79,9	87,34	51,25	90,01

This paper has addressed the problem of classification of learning objects based on multi-label classification and Fuzzy C-Means in order to improve the recommendation of these objects to learners and to facilitate their handling and sharing by e-learning systems. For this purpose, we have organized all these e-learning resources into the IEEE learning objects standard. Then we have used web mining techniques to explore them, especially in their metadata. Our objective behind the use of the multi-label classification approach in the e-learning system is to make all the learning objects reusable in different contexts. Moreover, the multi-label classification approach may enhance the performance of top n-recommendations. The Fuzzy C-Means technique is used mainly to calculate the similarity between learning objects and consequently reduce the massive data by ignoring the ones that are not appropriate. To examine the efficacy of our proposed approach, we have used data sources from three platform systems (Moodle, Blackboard, and Schoology), which are considered the best sources in the world. To evaluate the performance of the proposed approach, we have used the most widely known indicators in the area of classification and recommendation, such as precision, recall, and F1-measure. Using Python preprogramed libraries, we have compared the experimental implementation of the traditional machine learning algorithms like SVM and NB on proposed data to our approach. The results of this study showed that the proposed method increases the classification of learning objects better than the conventional techniques.

Competing interests

The authors, whose names are listed immediately below, certify that they have NO affiliations with or involvement in any organization or entity with any financial interest, or nonfinancial interest in the subject matter or materials discussed in this manuscript.

Author names: Meryem Amane, Karima Aissaoui, Mohammed Berrada

• Authors contributions

In this article, authors enhance the accuracy of recommendation of e-learning courses based on Multi-Label Classification, Fuzzy C-Means Algorithm and Web Mining Techniques.

• Availability of supporting data

The authors declare the availability of data.

• Funding

This research did not receive any specific grant from funding agencies in the public, business, or non-profit agencies sectors.

• Acknowledgements

The authors gratefully acknowledge the support of Dr Mounir Ben Lahcen (MG) full professor at Sidi Mohamed Ben Abdallah University, Fez, Morocco for his cooperation and his technical assistance during the study.

- Authors' information

MERYEM AMANE is a Ph.D. student at Sidi Mohammed Ben Abdellah University, Fez, Morocco. She is graduated from National School of Applied Sciences of Fez. Actually, she prepared her thesis on E-learning emerged with new technologies like big data and cloud computing to enhance E-learning environments. Her current research is essentially interested in how to include E-learning, educational data mining, and recommender systems in new LMS.

KARIMA AISSAOUI Professor at the faculty of sciences, Mohammed Premier University, Oujda, Morroco. Recieved the ph.D. degree in computer sciences from Mohammed premier University. Her current research interests include Educational, Technology, Higher Education, Teaching Methods, and Computing in Social science, Databases and Software Engineering.

Mohammed BERRADA received the Ph.D. degree in computer sciences from the Faculty of Sciences, Sidi Mohammed Ben Abdellah University, Fez, Morocco, in 2008. He is currently a Professor of computer sciences and the Manager of the IT Department, National School of Applied Sciences of Fez. His current research interests include artificial intelligence, e-learning, enterprise architecture, and Web services.

Churchill, Daniel. 2007. Towards a useful classification of learning objects. Educational Technology Research and Development 55: 479–497
Basahel S, Basahel A (2018) An empirical study of challenges in online distance education in Saudi Arabia. International Journal of Information Technology 10:289–302.
Convertini V.N., Bruno G. (2012) Classification of Learning Objects. In: Seel N.M. (eds) Encyclopedia of the Sciences of Learning. Springer, Boston, MA.
McGreal, R. (2004). Learning objects: A practical definition. International Journal of Instructional Technology and Distance Learning (IJITDL), 9(1).
Robertson, A., & Collerette, P. (2005). L’abandon scolaire au secondaire: prévention et interventions. Revue des sciences de l'éducation, 31(3), 687-707.
Dani, D., Agrawal, G. Evaluating the Quality of Indian School Education boards’ websites using multi criteria decision making models. Int. j. inf. tecnol. 13, 1–9 (2021).
Friesen, Norm. 2001. What are Educational Objects? Interactive Learning Environments - INTERACT LEARN ENVIRON 9: 219–230.
Clark, Ruth Colvin. 1998. Recycling knowledge with learning objects. training and development-alexandria-american society for training and development 52. american society for training and development: 60–63.
McGreal, R. (2004, September 4). Learning objects: A practical definition. International Journal of Instructional Technology and Distance Learning (IJITDL), 9(1). Retrieved September 24, 2004, from http://www.itdl.org/Journal/Sep_04/article02.htm.
Dodani, Mahesh. 2002. The dark side of object learning: learning objects. Journal of Object Technology 1: 37–42.
"IEEE Standard for Learning Object Metadata," in IEEE Std 1484.12.1-2002 , vol., no., pp.1-40, 6 Sept. 2002.
Wiley, D. A. (2000). Connecting learning objects to instructional design theory: A definition, a metaphor, and a taxonomy. The instructional use of learning objects, 2830(435), 1-35.
Chapman, B., & Hall, B. (2001). Learning content management systems. Sunnyvale, CA: Brandon-Hall.com.
Margaryan, A., Collis, B., & Cooke, A. (2004). Activity-based blended learning. Human resource development international, 7(2), 265-274.
Joy, Jeevamol, and Renumol Vemballiveli Govinda Pillai. 2021. Review and classification of content recommenders in E-learning environment. Journal of King Saud University- Computer and Information Sciences.
Sarker, Iqbal H. 2021. Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions. SN Computer Science 2: 420.
Džeroski, Sašo, Panče Pano v, and Bernard Ženko. 2009. Machine Learning, Ensemble Methods in. In Encyclopedia of Complexity and Systems Science, ed. Robert A. Meyers, 5317–5325. New York, NY: Springer New York.
Kasaei, S. Hamidreza, Miguel Oliveira, Gi Hyun Lim, Luís Seabra Lopes, and Ana Maria Tomé. 2015. Interactive Open-Ended Learning for 3D Object Recognition: An Approach and Experiments. Journal of Intelligent & Robotic Systems 80: 537–553.
Verbert, Katrien, and erik duval. 2008. ALOCOM: A generic content model for learning objects. Int. J. on Digital Libraries 9: 41–63.
Joy, Jeevamol, and Renumol Vemballiveli Govinda Pillai. 2021. Review and classification of content recommenders in E-learning environment. Journal of King Saud University- Computer and Information Sciences.
Sarker, Iqbal H. 2021. Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions. SN Computer Science 2: 420.
Klašnja-Milićević, Aleksandra, Mirjana Ivanović, Boban Vesin, and Zoran Budimac. 2018. Enhancing e-learning systems with personalized recommendation based on collaborative tagging techniques. Applied Intelligence 48: 1519–1535
González, P., Gibaja, E., Zapata, A., Menéndez, V. H., & Romero, C. (2017, June). Towards automatic classification of learning objects: Reducing the number of used features. In Proc. 10th Int. Conf. Educ. Data Mining (pp. 394-395).
Batista, V.F.L., Pintado, F.P., Gil, A.B., Rodríguez, S., Moreno, M.N. (2011). A System for Multi-label Classification of Learning Objects. In: Corchado, E., Snášel, V., Sedano, J., Hassanien, A.E., Calvo, J.L., Ślȩzak, D. (eds) Soft Computing Models in Industrial and Environmental Applications, 6th International Conference SOCO 2011. Advances in Intelligent and Soft Computing, vol 87. Springer, Berlin, Heidelberg.
López, V. F., De La Prieta, F., Ogihara, M., & Wong, D. D. (2012). A model for multi-label classification and ranking of learning objects. Expert Systems with Applications, 39(10), 8878-8884.
Carrillo, D., López, V. F., & Moreno, M. N. (2013). Multi-label classification for recommender systems. Trends in Practical Applications of Agents and Multiagent Systems, 181-188.
Birzniece, I., Rudzajs, P., Kalibatiene, D., Vasilecas, O., & Rencis, E. (2015). Application of Interactive Classification System in University Study Course Comparison. Informatics in Education, 14(1), 13-34.
Aldrees, A., & Chikh, A. (2016). Comparative evaluation of four multi‐label classification algorithms in classifying learning objects. Computer Applications in Engineering Education, 24(4), 651-660.
Xie, Y., Wang, X., Jiang, D., Xu, X., Bao, G., & Xu, R. (2018, May). Multi-label Green's Function Criterion inspired Transfer Annotation System. In 2018 IEEE 22nd International Conference on Computer Supported Cooperative Work in Design ((CSCWD)) (pp. 737-742). IEEE.
Tan, C., & Ji, G. (2020, December). Label Enhancement Manifold Learning Algorithm for Multi-label Image Classification. In 2020 Eighth International Conference on Advanced Cloud and Big Data (CBD) (pp. 96-102). IEEE.
Fayyad, U., Piatetsky-Shapiro, G., & Smyth, P. (1996). From Data Mining to Knowledge Discovery in Databases. AI Magazine, 17(3), 37.
Zschech, Patrick; Horn, Richard; Höschele, Daniel; Janiesch, Christian; and Heinrich, Kai (2020) "Intelligent User Assistance for Automated Data Mining Method Selection," Business & Information Systems Engineering: Vol. 62: Iss. 3, 227-247.
Janiesch, C., Zschech, P. & Heinrich, K. Machine learning and deep learning. Electron Markets 31, 685–695(2021).
Harikrishna, J., Rupa, C., Gireesh, R. (2022). Deep Learning-Based Real-Time Object Classification and Recognition Using Supervised Learning Approach. In: Shakya, S., Balas, V.E., Kamolphiwong, S., Du, KL. (eds) Sentimental Analysis and Deep Learning. Advances in Intelligent Systems and Computing, vol 1408. Springer, Singapore
Yasunori, Endo, Hamasuna Yukihiro, Yamashiro Makito, and Miyamoto Sadaaki. 2009. On semi-supervised Fuzzy C-Means clustering. In , 1119–1124. IEEE.
Berry, Michael W, Azlinah Mohamed, and Bee Wah Yap. 2019. Supervised and unsupervised learning for data science. Springer
Bulaeva, Marina N., Olga I. Vaganova, Margarita I. Koldina, Anna V. Lapshova, and Anna V. Khizhnyi. 2018. Preparation of Bachelors of Professional Training Using MOODLE. In The Impact of Information on Modern Humans, ed. Elena G. Popkova, 406–411. Cham: Springer International Publishing.
Craig, I. D. 1988. Blackboard systems. Artificial Intelligence Review 2: 103–118.

No competing interests reported.

Sharing and re-using learning objects Using web-mining techniques and Clustering algorithms

Status:

Version 1

Abstract

Figures

1. Introduction

2. Literature Review

2.1. Learning Object

2.2. Classification of Learning Object in E-learning System

3. Current Challenges

4. Research Work

4.1. Web Data Mining

4.2. Fuzzy C-Means Clustering Algorithm

4.3. Multi-Label Classification approach

5. Methodology

6. Evaluation And Discussion

6.1. Corpora Summary

6.2. Experimental Procedure and Performance Measure

6.3. Dimensionality Reduction

7. Conclusion

Declarations

References

Additional Declarations

Status:

Version 1