Towards a pragmatic modeling of learner’s complex system by reflecting Boulding’s typology at the affective computing space

Many times within the educational setting, statements like “I can’t do this” and “I’m not good at this” are common during the learning effort. In most of cases, these thoughts are not being addressed, despite the importance of their source, i.e., learners’ affective states of confusion, frustration, and hopelessness. The polished form of the educational material presented in the class by the teachers omits the natural steps of making mistakes (feeling confused), recovering from them (overcoming frustration), deconstructing what went wrong (not becoming dispirited), and starting over again (with hope and maybe even enthusiasm) [9]. Nevertheless, learning naturally involves failure and becomes a host of associated affective responses.

Emotional intelligence, that is the ability to identify, assess, and manage emotions of one’s self and of others, plays a crucial role in learning processes and, particularly, in the capability of extracting the information that is most important [6]. Furthermore, a number of studies by neuroscientists, cognitive scientists and psychologists have shown that emotion is of major importance in rational and intelligent thinking.

Within the aforementioned perspective, there is a clear necessity to view learning as a person’s ability to construct new knowledge based upon what s/he already knows or believes to be true [4], by performing model-based reasoning, recursion, and cognitive assessment, i.e., metacognition, without neglecting, though, the influence of emerged affective states. The latter could then lead the system of external representation of knowledge (e.g., teacher and/or ICT-based educational supporting system) to respond in an appropriate-adaptive manner (e.g., modulate the pace, alter and/or redefine the direction or complexity of the presentation). Towards such direction, Kort et al.[9] have tried to form a model that describes the range of various emotional states during learning. In particular, they defined a xyz-space, where the x-axis corresponds to an Emotion Axis, symbolizing an n-vector of all relevant emotion axes, thus, allowing multi-dimensional combinations of emotions. For example, the x-axis could represent (from negative valence, i.e., more unpleasant, emotions to positive valence, i.e., more pleasant, emotions): {Anxiety – Confidence: anxiety – worry – discomfort – comfort – hopeful – confident}, {Boredom – Fascination: ennui – boredom – indifference – interest – curiosity – intrigue}, {Frustration – Euphoria: frustration – puzzled – confusion – insight – enlightened – epiphany}, {Dispirited – Encouraged: dispirited – disappointed – dissatisfied – satisfied – thrilled – enthusiastic}, {Terror – Enchanted: Terror – Dread- Apprehension – Calm – Anticipatory – Excited}. The y-axis refers to the Learning Axis, symbolizing the construction of knowledge upward, and the discarding of misconceptions downward. In addition, the z-axis denotes the Knowledge Axis, adopting an excelsior spiral when evolving/developing knowledge. In building a complete and correct mental model associated with a learning opportunity, the learner may experience multiple cycles around the xyz-plane until completion of the learning exercise. In this trajectory, each orbit represents the time evolution of the learning cycle, gradually moving up the knowledge z-axis.

For full text: click here

(Author: Sofia J. Hadjileontiadou, Georgia N. Nikolaidou, Leontios J. Hadjileontiadis

Published by Sciedu Press)