• Journal of Internet Computing and Services
• /
• v.21 no.3
• /
• pp.123-131
• /
• 2020

Along with the rapid development of artificial intelligence technology, natural language processing, which deals with human language, is also actively studied. In particular, BERT, a language model recently proposed by Google, has been performing well in many areas of natural language processing by providing pre-trained model using a large number of corpus. Although BERT supports multilingual model, we should use the pre-trained model using large amounts of Korean corpus because there are limitations when we apply the original pre-trained BERT model directly to Korean. Also, text contains not only vocabulary, grammar, but contextual meanings such as the relation between the front and the rear, and situation. In the existing natural language processing field, research has been conducted mainly on vocabulary or grammatical meaning. Accurate identification of contextual information embedded in text plays an important role in understanding context. Knowledge graphs, which are linked using the relationship of words, have the advantage of being able to learn context easily from computer. In this paper, we propose a system to extract Korean contextual information using pre-trained BERT model with Korean language corpus and knowledge graph. We build models that can extract person, relationship, emotion, space, and time information that is important in the text and validate the proposed system through experiments.

• Archives of design research
• /
• v.18 no.1 s.59
• /
• pp.69-80
• /
• 2005

So far, there have been mary studies on human emotions and the emotional side of products in the field of emotional engineering. Contemporary emotion-related researches have focused mainly on the relationship between product aesthetics and the emotional responses elicited by the products, but little is known about emotions elicited from using the products. In this study we have extracted some emotional words that can come up during user interaction with a product and reveal emotional changes. Firstly, we assembled a set of emotional words that were sufficient to represent a general overview of Korean emotions, collected from various literature studies in the field of psychology, linguistics, emotional engineering. Secondly, we found emotional words from collecting user opinion on the website. In this study, we used heavy traffic websites such as shopping mall and mania sites. Finally the emotional words were collected from verbal protocols by using Think Aloud technique. The collected words were integrated according to standards and they were applied on evaluation survey twice for evaluating their appropriateness. This survey was conducted for identification of emotional expressions while using a product. Finally, we extracted 88 emotional words for measuring user's emotions expressed while using products. And we categorized the 88 words to form 6 groups by using factor analysis. The 6 categories that were extracted as a result of this study, such as aesthetics, satisfaction in usability, novelty, uncomfortable- ness, pleasure and excellence were found to be user's representative emotions expressed while using products. It is expected that emotional words and user's representative emotions extracted in this study will be used as subjective evaluation data that is required to measure user's emotional changes while using a product.

• Management & Information Systems Review
• /
• v.39 no.1
• /
• pp.75-91
• /
• 2020

The purpose of this study is to examine the application of in-depth interviews in terms of exploration on the basis of the theoretical basis of various aspects of consumer empathy, and the question of whether the consumer can expand to the process of self empathy. Most studies related to consumer empathy divide the responsive dimension of consumer empathy into rational and emotional dimension based on empathy theory, and look at the empathic response perceived by consumers to the stimulus presented from the current point of view. In this study, however, we want to go one step further and confirm that the consumers themselves can ultimately go to the self-empathy stage by forming a creative street of reproduction and redevelopment. As a result of exploratory research through in-depth interviews, it was indirectly confirmed that consumer's empathetic response to specific marketing stimulus exists at the level of creative and self-empathetic as well as the emphasis of previous studies. Based on these findings, this study confirmed that consumer empathetic responses could go beyond a single dimension to form a multidimensional structure and move toward an expanded structure of empathic self-creation. This suggests that consumers' empathic responses should be grasped in terms of continuity of empathic responses rather than explained in a specific dimension. Although this study is meaningful as an early research of exploratory nature, it is necessary to supplement various content validity and refine the research method through subsequent studies. This study is expected to expand the understanding that consumer's empathy can be extended to other people's empathy and to be self-empathy.

• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.47-67
• /
• 2021

The purpose of this study is to identify antecedent factors influencing the two-sided consumption intention tendencies observed in MZ generation from the viewpoint of consumption value in the cosmetic consumption scene of fashion houses. In order to verify the research model and hypotheses proposed in this study at the level of statistical significance. a survey was conducted for MZ generation, and data collected from a total of 286 samples were analyzed through a structural equation model. As a result. emotional and social consumption value was identified as a variable that had a great influence on the consumption intention of MZ generation. First, self-esteem had an effect on the emotion consumption value at the statistical significance level. Second, materialism had a significant influence on emotional and social consumption values. Third, public self-consciousness was found to have an effect on social consumption value. That is, MZ generation pursues the beauty trend presented by the fashion house's beauty brand and perceives it as a high consumption value. In addition, it was confirmed that MZ generation exhibited a conspicuous consumption tendency that they could be socially differentiated by using fashion house cosmetics.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.179-188
• /
• 2023

Recently, fake news disguises the form of news content and appears whenever important events occur, causing social confusion. Accordingly, artificial intelligence technology is used as a research to detect fake news. Fake news detection approaches such as automatically recognizing and blocking fake news through natural language processing or detecting social media influencer accounts that spread false information by combining with network causal inference could be implemented through deep learning. However, fake news detection is classified as a difficult problem to solve among many natural language processing fields. Due to the variety of forms and expressions of fake news, the difficulty of feature extraction is high, and there are various limitations, such as that one feature may have different meanings depending on the category to which the news belongs. In this paper, emotional change patterns are presented as an additional identification criterion for detecting fake news. We propose a model with improved performance by applying a convolutional neural network to a fake news data set to perform analysis based on content characteristics and additionally analyze emotional change patterns. Sentimental polarity is calculated for the sentences constituting the news and the result value dependent on the sentence order can be obtained by applying long-term and short-term memory. This is defined as a pattern of emotional change and combined with the content characteristics of news to be used as an independent variable in the proposed model for fake news detection. We train the proposed model and comparison model by deep learning and conduct an experiment using a fake news data set to confirm that emotion change patterns can improve fake news detection performance.

• Archives of design research
• /
• v.18 no.3 s.61
• /
• pp.199-208
• /
• 2005

This study analysis if the concepts of kitsch and vernacular remains as cultural elements for product design. Because their function and aesthetic value have vivid possibilities for general product design fields. For the purpose, this study limits its range within post modernism, kitsch, and vernacular, and analyzes their relationships. Against functionalism, post modernism had cultural pluralisms to approach into popular styles, and some of them was amusing design. That post modernism designs stimulated human beings' emotion by decorations or some symbolic forms from specific objects is similar to the symbolism, regionalism, or pluralism of kitsch or vernacular. Kitsch is a free style that is not limited in any specific trends. It is a Meta culture that has influenced into various fields including design, so kitsch does not have a parallel position with a product or design. In product design, kitsch is the behavior and result of imitating existing objects' images. It could have amusement according to which objects are imitated. So if human beings feel amusement by kitsch, it could be same as the direction of post modernism. Kitsch is determined by design atmospheres. They cannot be specified abjectly, and can be different according to people. With symbolism and regionalism, kitsch and vernacular appeared according to people's needs. While kitsch is consumer's tastes-oriented, vernacular is cultural tradition-oriented. Kitsch has symbolism that specifies products' functions or design concepts, and it is a communication method between human being and products. Because vernacular is province-oriented, it has a lot of styles according to regional living environments and cultural differences. So vernacular design reflects continued traditional lifestyles. By restorative memory, regionalism, cultural pluralism, amusement, and symbolism, kitsch and vernacular could be understood the sub or parallel concepts of post modernism. They might be easily miss-understood mixed concepts that have western and national characters. But in kitsch and vernacular concept, modernizing pas by using the pluralism of post modernism should be considered positive. So, the range of the further study is also supposed to be focused on more widened fields to, to establish cultural identification in design.