Abstract
The purpose of this article is the support of learning activities through the student affective awareness and more specifically through his/her anxiety level recognition. In learning activities besides the cognitive procedure, there is a mixture of student academic emotions revealed, which might be considered as important factors to student performance. Student anxiety recognition through bio-feedback, might be approved a significant support providing critical and on-time affective information which may improve self-regulation and teaching and coaching quality. The physiological reactions of the body, affects the conductivity of the skin, the skin temperature and the heart rate producing bio-signals that provide the opportunity to estimate some basic human emotional states. More specifically, high anxiety is usually resulting in increased human skin moisture, reducing the resistance and increasing the skin conductivity to electrical current. Human skin temperature is decreasing as anxiety is increasing. Also people under stressful conditions usually show increased heart rate values.
TopBackground
Affective computing is the scientific field providing support to emotion recognition and thus promoting the emotional intelligence.
The primary practical goal of affective computing is to create technologies that can monitor and respond to the affective states of the user (Picard, 1997).
The synthesis and analysis of emotions is an interdisciplinary scientific field consisting from the combination of computer science, psychology and cognitive science (Allen & Carifio, 1995).
Body language as facial expressions, posture and gestures can reveal the 55 percent of the emotional meaning of a message, the tone of the voice can represent the 38 percent of the emotion meaning and the remaining 7 percent can be communicated through explicit verbal channels (Mehrabian, 1969). There is good evidence that in psychophysiology research, the physiological activity associated with emotions can be systematically organized in affective valence and arousal (Bradley, 2000).
Affective computing uses many physiological techniques in order to collect bio-signals from human beings. Bio – signal processing and analysis, applying in most cases machine learning techniques, often leads to emotion detection and measuring.
Emotions are very important functions that affect students' motivation, behavior and performance.
Many researches started in 1950 (Zeidner, 1998) have considered with students anxiety during tests and produced sufficient knowledge that can inform the educational practice.
The influence of emotions during problem solving, and participation in educational activities is very important because it can affect positively or negatively the learning process (Allen & Carifio, 1995). Efforts to study difficult subjects at deeper levels of comprehension involve a complex coordination of cognitive processes and affective states (D’Mello, 2012). According to modern emotion theories, the strong or weak emotion arousal depends on how great a difficulty is and the valence, positive or negative, depends on how the person evaluates the inconvenience that has been appeared to him (Mandler, 1984b; Lazarus, 1991).
Key Terms in this Chapter
Regression: It is a statistical term concerning the analysis of relationship between different variables. Sensor: It is usually an electronic device taking a physical quantity as input and outputs an electronic signal which can be estimated and classified by human applications.
Bio-Signal: It is the electronic signal produced by a physiological reactions.
Bio-Feedback: It is the information gained by physiological processes which are detected by appropriate instruments.
Bio-Feedback Techniques: They are techniques suggested by psychologists. Through bio-feedback, a person is getting informed and when it is necessary he/she can apply these techniques in order to achieve self-regulation.
Affective State: They are considered psycho-physiological phenomena and they are represented in 2d dimensional model as valence and arousal. The term valence is the positive-to-negative evaluation of the current human state. The term arousal is dependent to the sympathetic nervous system state.
Machine Learning: It is a scientific field belonging to artificial intelligence and it mainly concerns mathematical processes and classification algorithms which are getting trained from data.
Arousal: It is relevant to the sympathetic nervous system state.
Appraisal Theory: According to this theory emotions are extracted from human evaluation of a current event.