Recognition of Conative and Affective Behavior in Web Learning using Digital Gestures

It is reasonably easy to understand a student when in a classroom. Learners can be uniquely identified, content can be specifically presented, and advancement can be individually supervised, maintained, and reviewed on a regular basis. In addition, study has found that conventional classroom (mainly of cognitive type) solution, are not always workable in the online setting. Lately, companies offering web-learning courses often tend to elucidate on conative and affective attributes of learners. These attributes are more stable over different online learning circumstances. These companies are discovering the requirement to set their focal point on the conative and affective factors that influence learning. Many contemporary researchers have extended their research on learning and memory constructs (and associated measures) to include conative and affective but very few have successfully deciphered these perspectives into technology. Human gestures are nothing but psychosomatic motions, which evolve due to the communication between the mind and body. These Human gestures give rise to digital gestures in an online environment. Keyboard press, mouse movement, page tracking, hyperlink usage, scrolling rate etc. are some of the web usage characteristics. Web Mining is a way to search for "interesting" relationships in web data. It has immense potential in discovering some decisive knowledge like conative and affective elements that will help the company provide learners with better learning experience. Primarily they need to identify the dominant power of emotions and intentions on learning, and then, seek personalized solutions to revolutionize the presentation of learning. This paper highlights on how conative and affective attributes of a learner can be transformed to real-time data and analyzed using Web Mining. Finally, our approach would be to discover several learners with similar psychological characteristics and their grouping will help us achieve mass customization.