Measuring the emotion in words is valuable in that it analyzes emotions through language. However, it is difficult to find such measurements in low-resource languages. In this paper, we proposed a method to expand the affective lexicon by utilizing the context of words. The proposed model predicted the Valence and Arousal values of words using their dictionary definitions. In Study 1, we reviewed previous studies about the Korean affective lexicon and integrated data from these studies. The model was trained to minimize the MSE error between the Valence and Arousal values of the words and their predictions. We then checked the distribution of Valence and Arousal values of Korean vocabulary by applying our model to the Korean dictionary. In Study 2, a new affective lexicon was built to empirically validate our model. We found a negatively biased error pattern on model predictions and discussed why it happened.

There are numerous studies that show that the more learner actively participate in the learning process, the more they learn. Although the use of active learning to increase learning outcomes has been recently introduced in a variety of methods, empirical experiments are lacking. In this study, we introduce two frameworks of human active learning and then conducted two experiments to determine how these frameworks can be used as leaning tools. In experiment 1, we compared three types of active learning and passive learning in order to empirically confirm the effect of active learning. In experiment 2, based on the results of experiment 1, we explored through simulation on machine learning with the frameworks that the more active the learners are, the better outcomes can be obtained. Both experiments showed that active learning both also effective in human and machine learning. Therefore, our analyses of the two experiments fit within the taxonomy and classification of the frameworks of active learning. This result is further significant in that it gives practical implications on human and machine learning methods.

In mathematical cognition, problem difficulty is a central vari-able. In the present study, problem difficulty was operational-ized through five arithmetic operators — addition, subtrac-tion, multiplication, division, and modulo — and through thenumber of carries required to correctly solve a problem. Thepresent study collected data from human participants solvingarithmetic problems, and from multilayer perceptrons (MLPs)that learn arithmetic problems. Binary numeral problems werechosen in order to minimize other criteria that may affect prob-lem difficulty, such as problem familiarity and the problemsize effect. In both humans and MLPs, problem difficulty washighest for multiplication, followed by modulo and then sub-traction. The human study found that problem difficulty wasmonotonically increasing with respect to the number of car-ries, across all five operators. Furthermore, a strict increasewas also observed for addition in the MLP study

There are numerous studies that show that the more students actively participate in class, the more they learn. Despiteample evidence, education still relies on lecturers or professors. Although active learning to increase learners’ engagementhas recently been introduced in a variety of methods, quantitative and empirical experiments are lacking. In this study,we conducted two experiments in order to empirically confirm the effect of active learning on learning performance. Wecompared humans and machines to investigate that active learning is more effective than passive learning. In Experiment1, we compared watching a lecture, the passive form of learning with having a discussion, the active form of learning.Comparing students’ learning performance of each condition, results of the present study showed higher performancein active learning. In the additional experiment that imitated the human learning frameworks in machines, the activelearning framework performed better than the passive learning framework. Through the results of humans experiment andvalidation of machines experiment, we found that active learning have crucial effect on learning performance.