Affective Behaviour analysis of Students

Web mining of educational content to identify the affective behavior of students like the moods, feelings and participation levels. Some of the aspects which are used to measure have been listed below:

.Session statistics: basic statistics about sessions such as average session length in time or in number of requests.
· Session patterns: the determination of student learning processes extracted from navigation and request
behaviour.
· Time series of session data: the analysis of the development of session statistics and session patterns over a
period of time.

.Behaviour patterns data: to analyze the various expressions of the students depending upon the challenges given to them and their expressions capture by either physical recording or their digital abstraction of images, video.

Tools such as discussion forums, Search engines which collect a large volume of information can also be used to identify the affective behaviour patterns of students.

Components of Educational Data Mining

Data mining has come of age. Data mining took its birth from the data which is accumulated in hundreds of thousands to millions of customer information at one location which has guaranteed consistent access and consistent storage: the data warehouse. the metaphors between data warehouse and data mining can be confusing. the philosophy that ties these two together is the data repository presented to data mining tools. Data warehousing helps you build ‘data mountains’, where as Data mining helps you to extract essential and vital information by building cubes, data marts from these ‘data mountains’ that is useful to your areas of interest.

Some of the Data Mining Algorithms includes:

a. Knowledge Discovery

i. Decision Trees

a. CART (Classification & Regression Trees)

b. CHAID (Chi Square Automated Initialization Decision Tree)

ii. Neural Networks

b. Prediction

i. Nearest Neighbor & K-nearest neighbor

ii. Clustering

c. Genetic Algorithms

Selecting the right data mining algorithm depending upon Model structure, Search and retrieval method and Validation requirements of the situation.

Use of LMS(Learning Management System) in Educational Data Mining

Learning management systems have made the life simpler by managing a centralized accessibility of all the requirements of an instructor, student and content management. Some of well known Learning Management System include Moodle, Sakai, WebCT, WhiteBoard, Brihaspati-3. The main aim of building a LMS is to achieve a collabrative learning atmosphere, where students can exchange there ideas, share resources and instructors can create content for the students and post at a centralized repository for the content to be available in a well organized way. some of basic qualities of a Learning Management System includes the following:

1. Course Management -course enrollment, course updates, curriculum design, types of Assignments.

2. Content Management- content design, type of content, wiki, discussion forum, groups, chats, hot potato, organize content repositories.

3. Student Management-student enrollments, profiles, student learning tools, blogs.

4. Grading and Evaluation Management- rubrics, assessment tools, grading reports, monitoring of student response, maintenance of student database repositories.

5. Institute and Administration Management- Institute authorization, institute administration, resource monitoring, database backups, recovery and restoration of content.

These are some of major functionalities most of the Learning Management system possess. So, rather than setting up individual systems for each and every functionality, all of them can be managed very well under a central repository through LMS.

What is Educational Data Mining?

Educational Data Mining is an emerging discipline, concerned with developing methods for exploring the unique types of data that come from educational settings, and using those methods to better understand students, and the settings which they learn in.

Whether educational data is taken from students’ use of interactive learning environments, computer-supported collaborative learning, or administrative data from schools and universities, it often has multiple levels of meaningful hierarchy, which often need to be determined by properties in the data itself, rather than in advance. Issues of time, sequence, and context also play important roles in the study of educational data.

And the theme is to support collaboration and scientific development in this new discipline, through the organization of workshops and mailing lists, as well as the development of community resources to support the sharing of data and techniques.