International Journal of Advance Foundation and Research in Computer (IJAFRC) Volume 1, Issue 10, October 2014. ISSN 2348 - 4853
Adaptive E-Learning System Based On Learning Interactivity. Mohammed Yaqub1 , A. M. Raid2 , H. M. El-Bakry3 , Haitham A. EL-Ghareeb3 Faculty of Computers and Information Sciences, Mansoura University , Egypt
[email protected],
[email protected],
[email protected],
[email protected] ABSTRACT This paper considers the affordances of social networking theories and tools to build new and effective e-learning practices. We argue that “connectivism” (social networking applied to learning and knowledge contexts) can lead to a reconceptualization of learning in which formal, non-formal and informal learning can be integrated as to build a potentially lifelong learning activities to be experienced in “personal learning environment. In order to provide a guide in the design, development and improvement both of personal learning environments and in the related learning activities we provide a knowledge flow model called Open Social Learning Network (OSLN) —a hybrid of the LMS and the personal learning environment (PLE)—is proposed as an alternative learning technology environment with the potential to leverage the affordances of the Web to improve learning dramatically and highlighting the stages of learning and the related enabling conditions. The derived model is applied in a possible scenario of formal learning in order to show how the learning process can be designed according to the presented theory. Index Terms : Open Social Learning Network OSLN, Learning Theory, Connectivism, Networked Learning, Collaboration Technologies, Collaborative Learning and Relationship Classification.
I.
INTRODUCTION
Learning is an active transaction between people as one person teaches and another learns . It is a shared experience because students explore new areas of knowledge together in such a way as to create a common core and concepts. Moreover, it is a common experience as student sacquire the same intellectual perspectives of certain learning areas. A social network approach to learning becomes important as it provides methods and measures to assess what is exchanged, shared, delivered and received among members of a network. It also makes possible to examine outcomes such as interpersonal ties, comprise learning relationships. Conducting effective eLearning in the age of Social Media is not without its problems. E-learning has emerged as an answer to provide freedom for learners from the highly controlled environment of traditional learning . However, E-Learning is not yet that competatively efficient. It has many drawbacks like its lack of peer interaction. It is the point that emphasizes contrast between student freedom and teacher control, which is amplified by social media. With the contrast created, teacher cannot fully control the way of learning anymore. Teacher can only influence students toward the best learning experience. E-learning is structured learning conducted over an electronic platform. But can generally be broken down into two categories: synchronous and asynchronous , Synchronous e-learning occurs in real time with participants actively communicating with each other. Synchronous e-learning might be conducted 7 | © 2014, IJAFRC All Rights Reserved
www.ijafrc.org
International Journal of Advance Foundation and Research in Computer (IJAFRC) Volume 1, Issue 10, October 2014. ISSN 2348 - 4853
by way of a webinar or a tele-video conference, Asynchronous e-learning does not occur in real time. Usually it involves an interactive learning tutorial or information database posted online and accessible at participants’ own convenience. E-Learning which breaks the traditional classroom based learning mode enables distributed e-learners to access various learning resources much more convenient and flexible. However, it also brings disadvantages due to distributed learning environment. Thus, how to provide personalized learning content is of high priority for e-learning applications. An effective way is to group learners with similar interests into the same community [1]. Through strengthening connections and inspiring communications among the learners, learning of the whole community will get promotion. To achieve a better performance and a higher scalability, the organizational structure of the community would better be both self-organizing and adaptive [2]. Based on the investigation on the behavior of real students, we found out that learners have strengthened trusts if they always share common evaluations or needs of learning re- sources [3]. In this paper, we present an improved E-Learner communities self-organizing algorithm relying on the earlier work by F. Yang [4]. II. RELATED WORK Networked learning is a term introduced around the mid-1990’s to refer to ways new communication technologies can influence teaching and learning. By networked learning we mean the use of c ICT to promote collaborative or cooperative connections between learners, their instructors, and learning resources. But, Social interaction is not, and has not historically been, because of limited to the level of online connectivity we have in the past. Communities of practice, personal learning networks and virtual learning environments have been around for years: they just existed without the same technology used today. Such networks began with in-person or mail correspondence and broadened through emails, forums, and chat rooms. Today internet and mobile technologies allow people to be in constant connection with the world at large [5][6]. This change is seen, for example, in virtual learning environments (VLEs). Combining technology and education, VLEs provide comprehensive course management tools and are often used in distance education. Traditionally, VLEs were simplistic and contained a lot of text, simple graphics, and included the lecturer’s notes in an eBook format. “Today, we have the ability to create very sophisticated and complex interactive virtual environments,” that include sound, video, and animation. These VLEs help students and teachers interact and communicate in ways previously not possible [7]. Users also change their behaviors towards the technology depending on their level of proficiency, personalization, and creativity [8]. Users are incredibly adept at creative applications of technology in ways it was not originally intended for. Educators demonstrate this by creatively using tools in the classroom such as Twitter, Pinterest, QR codes, or Skype that were created for other purposes entirely. Shirkey observes, “The social uses of our new media tools have been a big surprise, in part because the possibility of these uses wasn’t implicit in the tools themselves. The use of social technology is much less determined by the tool itself. When we use a network, the most important asset we get is access to one another. We want to be connected to one another, one that our use of social media actually engages”. In a
8 | © 2014, IJAFRC All Rights Reserved
www.ijafrc.org
International Journal of Advance Foundation and Research in Computer (IJAFRC) Volume 1, Issue 10, October 2014. ISSN 2348 - 4853
classroom environment, educators can use such tools to give their students access to the greater world [9]. A. Virtual learning environments (VLEs) Virtual learning environments (VLEs), sometimes called learning management systems or managed learning environment, create a controlled virtual learning space where teachers and students interact, post and submit homework, give and receive feedback from their peers, and link to course resources and information. VLEs typically include curriculum modules, assessment rubrics, discussion boards, external links to related resources, and profile information on participants. Common VLEs in education are Edmodo, Schoology, Blackboard, and Canvas. These platforms help educators create a place that allows students to share their work in a virtual representation of a physical room personalization [7]. B. Global collaboration Global collaboration takes such student engagement and learning outside the walls–or virtual walls–of the classroom and into the greater world. Learning communities, such as those established by communities or universities, provide a place for learners to pursue their interests, solve a problem, provide support, get feedback, or otherwise connect with people who share similar passions. Such constructivist interaction can be scaffolded in a classroom environment to allow students to work more independently and even help someone else solve a problem [10]. C. Adaptive-based learning (ABL) The objective of adaptive based learning is to conceive a system which can model the description of pedagogic resources and guide the learner in his formation according to his assets and to the pedagogic objective that is defined by the trainer, This pedagogy objective presents the capacities that the learner must have acquired at the end of the formation activity [11][12]. Adaptive e-Learning systems would be a good solution for better e-Learning[13].System such Moodle use adaptive e-learning which creates the best possible learning experience for students by emulating the talents of great educators. This is achieved by using technologies that adapt and shape teaching to the needs of the individual student. The process of applying rule mining over the Moodle data consists of the same four steps as the general data mining process [14]: •
Collect data. The LMS system is used by students and the usage and interaction information is stored in the database. We are going to use the students’ usage data of the Moodle system.
•
Preprocess the data. The data are cleaned and transformed into a mineable format. In order to preprocess the Moodle data we used the MySQL System Tray Monitor and Administrator tools [6] and the Open DB Preprocess task in the Weka Explorer [15].
•
Apply association rule mining. The data mining algorithms are applied to discover and summarize knowledge of interest to the teacher.
•
Interpret, evaluate and deploy the results. The obtained results or model are interpreted and used by the teacher for further actions. The teacher can use the discovered information for
9 | © 2014, IJAFRC All Rights Reserved
www.ijafrc.org
International Journal of Advance Foundation and Research in Computer (IJAFRC) Volume 1, Issue 10, October 2014. ISSN 2348 - 4853
making decision about the students and the Moodle activities of thecourse in order to improve the students’ learning[16]. Data preprocessing allows for transforming the original data into a suitable shape to be used by a particular data mining algorithm or framework. So, before applying a data mining algorithm, a number of general data preprocessing tasks has to be addressed (data cleaning, user identification, session identification, path completion, transaction identification, data transformation and enrichment, data integration, data reduction). Data preprocessing of LMS generated data has some specific issues [17]: •
Moodle and most of the LMS use user authentication (password protection) in which logs have entries identified by users since the users have to log-in, and sessions are already identified since users may also have to log-out. So, we can remove the typical user and session identification tasks of preprocessing data of web-based systems.
•
Moodle and most of the LMSs record the students’ usage information not only in log files but also directly in relational databases.
D. Project-based learning (PBL) Project-Based Learning (PBL), a strategy that encourages students to explore a problem through driving questions and authentic experiences, can be an excellent means to a social constructivist end. PBL helps teachers blend technology with hands-on materials to create imaginative and challenging student activities [18]. III. THE PROPOSED FRAMWORK A. Proposed System In order to overcome the problem of traditional e-learning or adaptive e-learning, we proposed hybrid framework that satisfies the social e-learning framework but with some new features. Agent feature, each agent in the community holds a set of resources such (Profiles, Friendship, and Courses) which are rated by used algorithm. Collaborative feature, each user (student, teacher) has own sharing and chatting tool which introduce availability. Semantic Support feature, each student or teacher has supported with intelligent process which suggest the closest friends. Users can post messages to groups and upload shared content to the group. In many of these sites, links between users are public and can be crawled automatically to capture and study a large fraction of the connected user graph. Figure 1 shows proposed of open social learning network block diagram. B. System Modules and Algorithms 1. Clustering Module K-means is mostly used as the clustering algorithm in data science. This algorithm asks for a number of clusters to be the input parameters from the user side [19]. It gathers points around a predefined number of clusters, k. The idea is to help uncover clusters that occur in your data so you can investigate unusual or previously unknown patterns in your data. The selection of the k clusters is somewhat dependent on the data set you want to cluster. You can start out with a small number, run the algorithm, look at the results, increase the number of clusters, rerun the algorithm, look at the results, and so on [20]. In the proposed system, the first step after the request register or login to interface the system is doing the 10 | © 2014, IJAFRC All Rights Reserved
www.ijafrc.org
International Journal of Advance Foundation and Research in Computer (IJAFRC) Volume 1, Issue 10, October 2014. ISSN 2348 - 4853
offline clustering of the users based on the new information of the user profile. Initially we choose the learner courses interests as the clustering criteria. Figure 2 summarize the steps taken by k-means clustering algorithm to achieve required tasks.
Figure 1. Block Diagram of Proposed System Functional Specification Data set of learners profiles
Number of clusters (Courses)
Step 1: Choose initial K centers of clusters
Step 2: Compute Euclidian distance of each learner profile from each center
Step 3: Place each learner to cluster based on mean value
Step 4: Calculate the new center of each cluster
Repeat from step 2 to 4 until no change
Figure 2. Step by step K-means Clustering Approach
2. Classification Module A decision table (DT) - also termed an inference or logical tree - provides a schematic view of the inference process of a decision-making process. Each decision rule of a DT is composed of a premise (condition) and a conclusion (action). In its tree-like representation, the premises and conclusions are shown as nodes, and the branches of the tree connect the premises and the conclusions. The logical
11 | © 2014, IJAFRC All Rights Reserved
www.ijafrc.org
International Journal of Advance Foundation and Research in Computer (IJAFRC) Volume 1, Issue 10, October 2014. ISSN 2348 - 4853
operators “AND” and “OR” are used to reflect the structure of the if-then rules .figure 3 decision tree diagram for the sample above.
Figure 3. decision tree diagram for the sample above.
3. Association Rule Module A-priori is a seminal algorithm for mining frequent datasets for Boolean association rules[19]. A priori employs an iterative approach known as a level-wise search. Support and Confidence are the normal method used to measure the quality of association rule. Support and Confidence equations as in 3.2 and 3.3.[21] . equation (3.2)
equation (3.3)
4. Ranking Module Page Rank Algorithm A Course has a high PageRank R by the equation 3.4 if • there are many students linking or interesting to it • or, if there are some courses with a high PageRank linking to it equation (3.4) where •
Pi is the set of students profiles that link to course Ci
12 | © 2014, IJAFRC All Rights Reserved
www.ijafrc.org
International Journal of Advance Foundation and Research in Computer (IJAFRC) Volume 1, Issue 10, October 2014. ISSN 2348 - 4853
•
Lj is the number of students interested for course Cj
5. Online and Offline Component We can classify Open Social Learning Network OSLN components into part Online and Offline components that perform the required tasks before users are connected to the system, so when users ask for queries, OSLN can respond to them. Offline component consist of cluster the users and apply association rule on these clusters. Online component consist of ranking to generate lists, Figure 4 presents the classification of OSLN components.
Figure 4. Offline and online components of OSLN
6. System Layer Architecture
13 | © 2014, IJAFRC All Rights Reserved
www.ijafrc.org
International Journal of Advance Foundation and Research in Computer (IJAFRC) Volume 1, Issue 10, October 2014. ISSN 2348 - 4853
Figure 5. System Layer Architecture
7. Sequence Diagram
Figure 6. Sequence Diagram of OSLN B. System Evaluation 1. Prediction Accuracy Concept
14 | © 2014, IJAFRC All Rights Reserved
www.ijafrc.org
International Journal of Advance Foundation and Research in Computer (IJAFRC) Volume 1, Issue 10, October 2014. ISSN 2348 - 4853
Prediction accuracy is typically independent of the user interface, and can thus be measured in an offline experiments. Measuring prediction accuracy in a user study measures the accuracy given a recommendation or suggestion. This is the difference concept from the prediction of user behavior without suggestion, and is closer to the true accuracy in real system. 2. Precision and Recall Concept Precision and recall are the basic measures used in evaluating search strategies. RECALL is the ratio of the number of relevant records retrieved to the total number of relevant records in the database. It is usually expressed as a percentage as shown in figure 4.10 . PRECISION is the ratio of the number of relevant records retrieved to the total number of irrelevant and relevant records retrieved. It is usually expressed as a percentage as shown in figure 5 .
Figure 5. Chart of Precision and Recall Concept
3. Measurements using Precision and Recall
Precision =
Recall = Table 1. Result of Precision and Recall
Cluster Name Introduction to programming Data Structure Algorithms C++ Java Oracle Object Oriented Security SQL server Weighted Avg.
15 | © 2014, IJAFRC All Rights Reserved
Precision 0.941
Recall 0.866
0.883 0.833 0.756 0.953 0.879 0.923 0.778 0.793 0.859
0.722 0.754 0.756 0.884 0.821 0.842 0.688 0.674 0.778
www.ijafrc.org
International Journal of Advance Foundation and Research in Computer (IJAFRC) Volume 1, Issue 10, October 2014. ISSN 2348 - 4853
1.2 1 0.8 0.6 0.4 0.2 0
Figure 7. Chart Result of Precision and Recall Table 2. Weighted list of Interested Courses
Course Name
Interested Weights
Introduction to programming
99
Data Structure
61
Algorithms
50
C++
41
Java
75
Oracle
50
Object Oriented
25
Security
42
SQL server
57
Table 3. Weighted list of Association Courses based on A-priori Algorithm Course Name
A-priori Weights
Introduction to programming Data Structure Algorithms C++ Java Oracle Object Oriented Security SQL server
54 1 55 55 86 86 54 1 1
16 | © 2014, IJAFRC All Rights Reserved
www.ijafrc.org
International Journal of Advance Foundation and Research in Computer (IJAFRC) Volume 1, Issue 10, October 2014. ISSN 2348 - 4853 Table 4. Weighted list of Courses Based on Page Rank Algorithm
Course Name Introduction to programming Data Structure Algorithms C++ Java Oracle Object Oriented Security SQL server
Page Rank Weights 9 6 5 4 7 5 2 4 5
IV. REFERENCES
[1]
R. Shen, F. Yang, and P. Han, A dynamic self-organizing e-learner communities with improved multi-agent matchmaking algorithm. The 16th Australian Joint Conference on Artificial Intelligence 2003, pp. 590–600.
[2]
P. Turner and N. Jennings, Improving the scalability of multi-agent systems. the First International Workshop on Infrastructure for Scalable Multi-Agent Systems 2006, pp. 246–262.
[3]
D. O. Hebb, The Organization of Behaviour 1999.
[4]
F. Yang, Analysis, Design and Implementation of Personalized Recommendation Algorithms Supporting Self-organized Communities. PhD thesis 2005.
[5]
De Laat, M. F., Lally, V., Lipponen, L., & Simons, P. R. J. , "Analysing student engagement with learning and tutoring activities in networked learning communities: A multi-method approach". International Journal of Web-Based Communities 2(4),2006.
[6]
De Laat, M. F., Lally, V., Lipponen, L., & Simons, P. R. J. ," Patterns of interaction in a networked learning community: Squaring the circle", International Journal of Computer-Supported Collaborative Learning. DOI 10.1007/s11412-007-9006-4,2007.
[7]
Clark, S., & Maher, M. L. ,"The role of place in designing a learner centred virtual learning environment”, In B. D. Vries, J. P. V. Leeuwen, & H. Achten (Eds.), Computer Aided Architectural Design: Futures 2001 (pp. 187–200). Springer 2001.
[8]
Conole, G., Galley, R., & Culver, J. ,"Frameworks for understanding the nature of interactions, networking, and community in a social networking site for academic practice", The International Review of Research in Open and Distance Learning, 12(3), 119–138,2010.
[9]
Shirky, C. , "Cognitive surplus: Creativity and generosity in a connected age". New York, NY: Penguin Press. Retrieved from http://d4tc.parsons.edu/week07/ClayShirkyChap1.pdf,2010 .
17 | © 2014, IJAFRC All Rights Reserved
www.ijafrc.org
International Journal of Advance Foundation and Research in Computer (IJAFRC) Volume 1, Issue 10, October 2014. ISSN 2348 - 4853
[10]
Hill, J. R., "Learning communities: Theoretical foundations for making connections", In D. Jonassen & S. Land (Eds.), Theoretical Foundations of Learning Environments (2nd ed., pp. 268- 285). New York, NY: Routledge,2012.
[11]
Samia Azough,,Mostafa Bellafkih,El Houssine Bouyakhf," Adaptive E-learning using Genetic Algorithms", International Journal of Computer Science and Network Security(IJCSNS), VOL.10 No.7,2010.
[12]
Marcus, N., Ben-Naim, D., Bain, M. ,"Instructional Support For Teachers and Guided Feedback For Students In An Adaptive eLearning Environment", In: Eighth International Conference on Information Technology: New Generations (ITNG), 2011 Institute of Electrical and Electronics Engineers (IEEE),2011.
[13]
A. M. Riad , Hamdy K. El-Minir , Haitham A. El-Ghareeb," Review of e-Learning Systems Convergence from Traditional Systems to Services based Adaptive and Intelligent Systems" Journal of Convergence Information Technology Vol 4, No 2,2009.
[14]
Enrique Garcia, Cristobal Romero1, Sebastian Ventura, Carlos de Castro1, Toon Calders," Mining learner profile utilizing association rule for web-based learning diagnosis ", www.elsevier.com/locate/eswa, Expert Systems with Applications 33 ,pp.13,2007 .
[15]
Weka, available at http://www.cs.waikato.ac.nz/ml/weka/ (accessed March 16), 2009.
[16]
Moodle, available at http://moodle.org/, (accessed March 16),2009.
[17]
Eisenberg, M. ,"Educational technology", reimagined. New Directions for Youth Development, 2010(128), 25–33. doi:10.1002/yd.372,2010.
[18]
Land, S., Hannafin, M., & Oliver, K., (2012),"Student-Centered learning environments", In D. Jonassen & S. Land (Eds.), Theoretical Foundations of Learning Environments (2nd ed., pp. 3– 25). New York, NY: Routledge, 2012.
[19]
Vignesh Prajapati , "Big Data Analytics with R and Hadoop" , Packt Publishing, 2013, ISBN 978-178216-328-2.
[20]
Kevin Schmidt, and Christopher Phillips, "Programming Elastic Map Reduce", Printed in the United States of America, Published by O’Reilly Media, Inc., 1005 Gravenstein Highway North, Sebastopol,2014 , CA 95472, ISBN: 978-1-449-36362-8.
[21]
B. Sunita and L. Lobo, “Best Combination of Machine Learning Algorithms for Course Recommendation System in E-learning”, International Journal of Computer Applications, 2012.
18 | © 2014, IJAFRC All Rights Reserved
www.ijafrc.org
