A Brief Study on Analyzing Student’s Emotions with the Help of Educational Data Mining

Abstract

Recently, the idea has reached toward considering the emotions in the learning procedure which prompts to design an innovative framework that empowers correlative analysis and classifications of various emotional variations of an individual. There is an absence of teaching pedagogues to distinguish the standard articulations of people. In the past decade, research articles have recorded the lacking properties and attempt to recognize the equivalent benefit to overcome the difficulties. This enhances the part of identifying emotions as a device to perceive the sentiments of understudies while learning. This article encompasses the record of all analytical examinations of student’s emotions by applying different strategies, models, calculations and devices. This article wraps the considered works and gives the examination of qualities, shortcomings, openings, whose parts are addressed and the future work to be accomplished.

1 Introduction

‘Emotion’ is for the most part insinuated as a state of mind of a person, which has been distinctively involved with slants, consideration, and social retaliation. Emotion produces anatomical and psychological alterations. Initially, emotions or the state of feelings toward a certain occurrence of events proposed to empower reasonable practices reliant on past experiences.

At the present time, feelings impact our life decisions consistently with or without our understanding. It has been watched every once in a while that most of the part fail at disguising our sentiments. Even though, it is not possible to present our emotions explicitly to establish a connection of a specific inclination toward a feeling through our activities. The outward appearance and non-verbal communication moreover will in general be an important strategy for delineating our inclination explicitly without knowing.

Learning style basically applies to the way a person tries to learn a specific topic, thereby resulting in gaining knowledge. Hence, various individuals try to grasp in unique ways. Although people may have a combination of non-similar ways of learning, still some have a prevalent style of getting the hang of contingent upon the conditions while others may have an alternative learning style. Data mining refers to a computing technique that enables the user to extract valuable information from a pool of data, a lot of which might be irrelevant to the user. Nowadays, the use of DM in the education arena is incipient and gives birth to the educational data mining (EDM) research field [1].

Educational data mining (EDM) enables paradigm-oriented learning which is used to draft models, methods and approaches to explore context information of educational amends. The increase of technology use in educational systems has led to the storage of large amounts of student data, which makes it important to use EDM to improve teaching and learning processes [2, 3]. EDM is useful in many different areas including identifying student emotions, identifying priority learning needs for different groups of students. By analyzing student emotions may reveal a relationship between a student’s grade in a particular course and the interest the student has in that particular course. It discovers examples and makes expectations that describe students’ practices and accomplishments, area information content, evaluations, enlightening functionalities and applications [4, 5].

In the beginning, it looks at the course of action of EDM to learn and set the informational condition as demonstrated by the learner’s profile before teaching to a class. In the initial stage where the student interacts with the system, it would be beneficial if the EDM secures log information and breaks down their importance to propose recommendations. The following stage requires the EDM to evaluate the given training data which can be, for instance, the comprehensibility of the predictions.

The layout of the article is organized into three segments. Section 1 includes the introduction. Section 2 describes the supported survey of relating research along with the tools used, and finally, Sect. 3 concludes the research work.

2 Literature Survey

Table 1 summarizes the various survey articles observed for recognizing the student emotion, whose concepts have been incorporated into our study.

Table 1 Summary of various survey

Table 2 shows the various tools applied in a student emotion recognition system.

Table 2 Tools utilized for student emotion recognition system

3 Conclusion

In this article, the insightful investigation of learner’s feelings through educational information mining was discussed. The problems regarding learner’s emotions are adjuring to be addressed have been investigated and examined, the models applied to depict various feelings, the classification procedures and various tools utilized in past research, examining the given work, its qualities and shortcomings are considered. The future degree drawn from the examination can be fused.

The use of various techniques of data mining such as the multi-layer perceptron (MLP) was suggested. The accuracies of the various concepts and tools of emotions in the aforementioned field and depending upon the metric were obtained, and the most optimal technique/algorithm to accomplish the desired outcomes and results of this research work were recommended.