• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.179-196
• /
• 2019

Recently, the "Smart Consumer" has been emerging. He or she is increasingly inclined to search for and purchase products by taking into account personal judgment or expert reviews rather than by relying on information delivered through manufacturers' advertising. This is especially true when purchasing cosmetics. Because cosmetics act directly on the skin, consumers respond seriously to dangerous chemical elements they contain or to skin problems they may cause. Above all, cosmetics should fit well with the purchaser's skin type. In addition, changes in global cosmetics consumer trends make it necessary to study this field. The desire to find one's own individualized cosmetics is being revealed to consumers around the world and is known as "Finding the Holy Grail." Many consumers show a deep interest in customized cosmetics with the cultural boom known as "K-Beauty" (an aspect of "Han-Ryu"), the growth of personal grooming, and the emergence of "self-culture" that includes "self-beauty" and "self-interior." These trends have led to the explosive popularity of cosmetics made in Korea in the Chinese and Southeast Asian markets. In order to meet the customized cosmetics needs of consumers, cosmetics manufacturers and related companies are responding by concentrating on delivering premium services through the convergence of ICT(Information, Communication and Technology). Despite the evolution of companies' responses regarding market trends toward customized cosmetics, there is no "Intelligent Data Platform" that deals holistically with consumers' skin condition experience and thus attaches emotions to products and services. To find the Holy Grail of customized cosmetics, it is important to acquire and analyze consumer data on what they want in order to address their experiences and emotions. The emotions consumers are addressing when purchasing cosmetics varies by their age, sex, skin type, and specific skin issues and influences what price is considered reasonable. Therefore, it is necessary to classify emotions regarding cosmetics by individual consumer. Because of its importance, consumer emotion analysis has been used for both services and products. Given the trends identified above, we judge that consumer emotion analysis can be used in our study. Therefore, we collected and indexed data on consumers' emotions regarding their cosmetics experiences focusing on consumers' language. We crawled the cosmetics emotion data from SNS (blog and Twitter) according to sales ranking ($1^{st}$ to $99^{th}$), focusing on the ample/serum category. A total of 357 emotional adjectives were collected, and we combined and abstracted similar or duplicate emotional adjectives. We conducted a "Consumer Sentiment Journey" workshop to build a "Consumer Sentiment Dictionary," and this resulted in a total of 76 emotional adjectives regarding cosmetics consumer experience. Using these 76 emotional adjectives, we performed clustering with the Self-Organizing Map (SOM) method. As a result of the analysis, we derived eight final clusters of cosmetics consumer sentiments. Using the vector values of each node for each cluster, the characteristics of each cluster were derived based on the top ten most frequently appearing consumer sentiments. Different characteristics were found in consumer sentiments in each cluster. We also developed a cosmetics experience pattern map. The study results confirmed that recommendation and classification systems that consider consumer emotions and sentiments are needed because each consumer differs in what he or she pursues and prefers. Furthermore, this study reaffirms that the application of emotion and sentiment analysis can be extended to various fields other than cosmetics, and it implies that consumer insights can be derived using these methods. They can be used not only to build a specialized sentiment dictionary using scientific processes and "Design Thinking Methodology," but we also expect that these methods can help us to understand consumers' psychological reactions and cognitive behaviors. If this study is further developed, we believe that it will be able to provide solutions based on consumer experience, and therefore that it can be developed as an aspect of marketing intelligence.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.1-25
• /
• 2020

Sentiment Analysis (SA) is a Natural Language Processing (NLP) task that analyzes the sentiments consumers or the public feel about an arbitrary object from written texts. Furthermore, Aspect-Based Sentiment Analysis (ABSA) is a fine-grained analysis of the sentiments towards each aspect of an object. Since having a more practical value in terms of business, ABSA is drawing attention from both academic and industrial organizations. When there is a review that says "The restaurant is expensive but the food is really fantastic", for example, the general SA evaluates the overall sentiment towards the 'restaurant' as 'positive', while ABSA identifies the restaurant's aspect 'price' as 'negative' and 'food' aspect as 'positive'. Thus, ABSA enables a more specific and effective marketing strategy. In order to perform ABSA, it is necessary to identify what are the aspect terms or aspect categories included in the text, and judge the sentiments towards them. Accordingly, there exist four main areas in ABSA; aspect term extraction, aspect category detection, Aspect Term Sentiment Classification (ATSC), and Aspect Category Sentiment Classification (ACSC). It is usually conducted by extracting aspect terms and then performing ATSC to analyze sentiments for the given aspect terms, or by extracting aspect categories and then performing ACSC to analyze sentiments for the given aspect category. Here, an aspect category is expressed in one or more aspect terms, or indirectly inferred by other words. In the preceding example sentence, 'price' and 'food' are both aspect categories, and the aspect category 'food' is expressed by the aspect term 'food' included in the review. If the review sentence includes 'pasta', 'steak', or 'grilled chicken special', these can all be aspect terms for the aspect category 'food'. As such, an aspect category referred to by one or more specific aspect terms is called an explicit aspect. On the other hand, the aspect category like 'price', which does not have any specific aspect terms but can be indirectly guessed with an emotional word 'expensive,' is called an implicit aspect. So far, the 'aspect category' has been used to avoid confusion about 'aspect term'. From now on, we will consider 'aspect category' and 'aspect' as the same concept and use the word 'aspect' more for convenience. And one thing to note is that ATSC analyzes the sentiment towards given aspect terms, so it deals only with explicit aspects, and ACSC treats not only explicit aspects but also implicit aspects. This study seeks to find answers to the following issues ignored in the previous studies when applying the BERT pre-trained language model to ACSC and derives superior ACSC models. First, is it more effective to reflect the output vector of tokens for aspect categories than to use only the final output vector of [CLS] token as a classification vector? Second, is there any performance difference between QA (Question Answering) and NLI (Natural Language Inference) types in the sentence-pair configuration of input data? Third, is there any performance difference according to the order of sentence including aspect category in the QA or NLI type sentence-pair configuration of input data? To achieve these research objectives, we implemented 12 ACSC models and conducted experiments on 4 English benchmark datasets. As a result, ACSC models that provide performance beyond the existing studies without expanding the training dataset were derived. In addition, it was found that it is more effective to reflect the output vector of the aspect category token than to use only the output vector for the [CLS] token as a classification vector. It was also found that QA type input generally provides better performance than NLI, and the order of the sentence with the aspect category in QA type is irrelevant with performance. There may be some differences depending on the characteristics of the dataset, but when using NLI type sentence-pair input, placing the sentence containing the aspect category second seems to provide better performance. The new methodology for designing the ACSC model used in this study could be similarly applied to other studies such as ATSC.

• Korean Journal of Heritage: History & Science
• /
• v.44 no.4
• /
• pp.172-205
• /
• 2011

Go bears significant meanings in terms of cultural and entertaining functions in Asia Eastern such as China and Japan. Beyond the mere entertaining level, it produces philosophical and mythic discourse as well. As a part of effort to seek an identity of Korean traditional garden culture, this study traced back to find meanings of rock-go-board and taste for the arts which ancestors pursued in playing Go game, through analysis and interpretation of correlation among origin of place name, nearby scenery, carved letters and vicinal handed-down place name. At the same time, their position, shape and location types were interpreted through comprehensive research and analysis of stone-go-boards including rock-go-board. Particularly, it focused on the rock names related to Sundoism(仙道) Ideal world, fixed due to a connection between traces of Sundoism and places in a folk etymology. Series of this work is to highlight features of the immortal sceneries, one of traditional landscaping ideals, by understanding place identity and scenic features of where the rock-go-boards are carved. These works are expected to become foundation for promotion and preservation of the traditional landscaping remains. The contents of this study could be summarized as follows; First, round stone and square board for round sky and angled land, black and white color for harmony of yin and yang and 361paths for rotating sky are symbols projecting order of universe. Sayings of Gyuljungjirak(橘中之樂), Sangsansaho(商山四皓), Nangagosa(爛柯故事) formed based on the idea of eternity stand for union of sky and sun. It indicates Go game which matches life and nature spatiotemporally and elegant taste for arts pursuing beauty and leisure. Second, the stone-go-boards found through this research, are 18 in total. 3 of those(16.1%), Gangjin Weolnamsaji, Yangsan Sohanjeong and Banryongdae ones were classified into movable Seokguk and 15(83.9%) including Banghakdong were turned out to be non-movable rock-go-boards carved on natural rocks. Third, upon the result of materializing location types of rock-go-boards, 15 are mountain stream type(83.9%) and 3 are rock peak type(16.1%). Among those, the one at Sobaeksam Sinseonbong is located at the highest place(1,389m). Considering the fact that all of 15 rock-go-boards were found at mountainous areas lower than 500m, it is recognizable that where the Go-boards are the parts of the living space, not far from secular world. Fourth, there are 7 Sunjang(巡將) Go with 17 Hwajeoms(花點), which is a traditional Go board type, but their existences, numbers and shapes of Hwajeom appear variously. Based on the fact, it is recognizable that culture of making go-board had been handed down for an extended period of time. Among the studied rock-goboards, the biggest one was Muju Sasunam[$80(82)cm{\times}80(82)cm$] while the smallest one was Yangsan Sohandjeong Seokguk ($40cm{\times}40cm$). The dimension of length and breadth are both $49cm{\times}48cm$ on average, which is realistic size for actual Go play. Fifth, the biggest bed rock, an under-masonry with carved Go-board on it, was one in Muju Sasunam[$8.7m{\times}7.5m(65.25m^2)$], followed by ones in Hoengseong Chuiseok[$7.8m{\times}6.3m(49.14m^2$] and Goisan Sungukam[$6.7m{\times}5.7m(37.14m^2)$]. Meanwhile, the smallest rock-go-board was turned out to be one in Seoul Banghak-dong. There was no consistency in directions of the Go-boards, which gives a hint that geographical features and sceneries of locations were considered first and then these were carved toward an optimal direction corresponding to the conditions. Sixth, rock-go-boards were all located in valleys and peaks of mountains with breathtaking scenery. It seems closely related to ancestors' taste for arts. Particularly, rock-go-boards are apprehended as facilities related to taste for arts for having leisure in many mountains and big streams under the idea of union of sky and human as a primitive communal line. Go became a medium of hermits, which is a traditional image of Go-game, and symbol of amusement and entertainment with the idea that Go is an essence of scholar culture enabling to reach the Tao of turning back to nature. Seventh, the further ancient time going back to, the more dreamlike the Go-boards are. It is an evident for that Sundoism, which used to be unacceptable once, became more visible and realistic. Considering the high relation between rock-go-boards and Sundoism relevant names such as Sundoism peak in Danyang Sobaeksan, 4 hermits rock in Muju and Sundoism hermit rock in Jangsu, Sundoism hermit rocks and rock-go-boards are sceneries and observation spots to express a communication of worship and longing for Sundoism. Eighth, 3 elements-physical environment such as location type of the rock-go-boards, human activities concentrated on 8 sceneries and Dongcheongugok(洞天九曲) setup and relevancy to Confucian scholars, as well as 'Sangsansaho' motif and 'Nangagosa' symbolic meaning were used as interpretation tools in order to judge the place identity. Upon the result, spatial investigation is required with respect to Sunyoodongcheon(仙遊洞天) concept based on enjoyment to unify with the nature rather than Dongcheongugok concept of neo-Confucian, for Dongcheon and Dongmoon(洞門) motives carved around the rock-go-boards. Generally, places where mountain stream type rock-go-boards were formed were hermit spaces of Confucianism or Sundoism. They are considered to have compromised one other with the change of times. Particularly, in the rock-go-board at the mountain peak, sublimity-oriented advent of Sundoism is considered as a significant factor to control place identity. Ninth, including where the rock-go-boards were established, the vicinal areas are well-known as parts of Dongcheongugok and Palkyung(八景) mostly. In addition, many of Sundoism relevant expressions were discovered even in the neighboring carvings written by scholars and nobility, which means sophisticated taste based on longing for Sundoism world played a significant role in making go-board. The rock-go-board is an integration of cultural phenomena naturally managed by seclusion of scholars in the Joseon Dynasty as well as remains and essence of Korean traditional landscaping. Some rock-go-boards out of 17 discovered in South Korea, including ones in Sobaeksan Sinsunbong, Banghak-dong, Chungju Gongili, Muju Sasunam, Yangsan Eogokdong Banryongdae Seokguk, are damaged such as cracks in rocks or fainted lines by hardships of time and hand stains. Worse yet, in case of Eunyang Bangudae Jipcheongjeong board, it is very difficult to identify the shape due to being buried. Rock-go-boards are valuable sculptures in terms of cultural asset and artwork since they reflect ancestors' love for nature and longing for Sundoism world. Therefore, they should be maintained properly with right preservation method. Not only rock-boards itself but also peripheral places are excellent cultural heritages and crucial cultural assets. In addition, vicinal sceneries of where rock-goboards and pavilion spots are the representative remains of embracing prototype of Korean traditional landscaping and major parts of cultural properties.