It's not easy to renew old brand of over 50 years history to the tastes of new consumer of our time. Most of national brands that has a history of some 20 years in Korea have strove for continuation and growth of brand to no avails, which can be taken as a good example of current situation. For instance, C company, one of the National brand of US which has a history of 51 years, has made its position secure as a fashion group and based itself on a sound foundation by establishing new marketing strategy and completing successful brand renewal in the process of strategic M&A with Italian company. Those successful marketing strategies are as follows. 1) they regarded both market and consumer oriented marketing activity as company's highest priority strategy and put great emphasis upon concentration on target market and reestablishment of brand image of business casual wear. 2) Setting up and operating planning team composed of merchandizer alone in Milano, they set the direction of plan on the basis of concentrated research on potential item in market according to thorough market research done by buying office in Korea, branch office in Hong Kong and buyer in US prior to blueprint planning for season. 3) Great emphasis was placed on business which focused on intensive presentation of basic key item for apparel career women who are main consumer group in the midium-low prices market in US and on supplementation of size and color. they named this line 'collectibles' and helped their customer develop their own clothes plan without worrying about the change of color and fabric by supporting same fabric and color throughout the year and enabled them to add variation easily by supplementing new trend item. 4) Company set black as a main color that lots of apparel career women find easy to care and to express their own image and presented them with pebble which belongs to navy and beige and added fashion color such as wine and brown etc as season goes by. They constructed basic line in order for their customers to coordinate purchased item with new one or to add them to present collection, and to achieve efficient sale by setting up strategy which allows this cross coordination and changing pattern occasionally. 5) Though basic jacket for 99$, short slim skirt for 49$ are products within midium-low prices range, in the material planning stage aiming at production of item that has both resonable function appealing to consumer and is fashionable, synthetic material had to be used as a main source due to price competitiveness. Despite this situation, considering comfortable sense of fit and refined drape of silhouette that has no sign of cheap material, whole collectible line was divided into two items, which contributed to reduction of cost. In case of material that is composed of triacetate and polyester in 70 to 30 ratio, was used up to 4 million yard, which allowed drastic curtailment of cost accompanied by concentration. In case of 'collectibles' line, using Korean material mainly, C company chose to have their product sewed in Southeast Asian countries where transportation is well developed and both productivity and quality verified by operating global production system which aiming at cutdown of cost through outsourcing production from the country where labor cost is low and getting finished product. Polarization between present consumers telling us that consumers with the mind of middle classes in the past no longer exists between consumers who seek after only fine article of highest quality and wise consumers who are sensible enough to judge bubble on correlation between price and quality. To cope with this change in new consumer mind, apparel makes changing their policy so as to produce item that has reasonable quality and falls within affordable price range anywhere in the world. and they're striving to get out of difficult situation by operating global marketing strategy which stresses separation of planning, production and sale and sensibility of fashion shared worldwide. The marketing strategy of C company can be exemplified as a successful one.
With the increasing importance of sentiment analysis to grasp the needs of customers and the public, various types of deep learning models have been actively applied to English texts. In the sentiment analysis of English texts by deep learning, natural language sentences included in training and test datasets are usually converted into sequences of word vectors before being entered into the deep learning models. In this case, word vectors generally refer to vector representations of words obtained through splitting a sentence by space characters. There are several ways to derive word vectors, one of which is Word2Vec used for producing the 300 dimensional Google word vectors from about 100 billion words of Google News data. They have been widely used in the studies of sentiment analysis of reviews from various fields such as restaurants, movies, laptops, cameras, etc. Unlike English, morpheme plays an essential role in sentiment analysis and sentence structure analysis in Korean, which is a typical agglutinative language with developed postpositions and endings. A morpheme can be defined as the smallest meaningful unit of a language, and a word consists of one or more morphemes. For example, for a word '예쁘고', the morphemes are '예쁘(= adjective)' and '고(=connective ending)'. Reflecting the significance of Korean morphemes, it seems reasonable to adopt the morphemes as a basic unit in Korean sentiment analysis. Therefore, in this study, we use 'morpheme vector' as an input to a deep learning model rather than 'word vector' which is mainly used in English text. The morpheme vector refers to a vector representation for the morpheme and can be derived by applying an existent word vector derivation mechanism to the sentences divided into constituent morphemes. By the way, here come some questions as follows. What is the desirable range of POS(Part-Of-Speech) tags when deriving morpheme vectors for improving the classification accuracy of a deep learning model? Is it proper to apply a typical word vector model which primarily relies on the form of words to Korean with a high homonym ratio? Will the text preprocessing such as correcting spelling or spacing errors affect the classification accuracy, especially when drawing morpheme vectors from Korean product reviews with a lot of grammatical mistakes and variations? We seek to find empirical answers to these fundamental issues, which may be encountered first when applying various deep learning models to Korean texts. As a starting point, we summarized these issues as three central research questions as follows. First, which is better effective, to use morpheme vectors from grammatically correct texts of other domain than the analysis target, or to use morpheme vectors from considerably ungrammatical texts of the same domain, as the initial input of a deep learning model? Second, what is an appropriate morpheme vector derivation method for Korean regarding the range of POS tags, homonym, text preprocessing, minimum frequency? Third, can we get a satisfactory level of classification accuracy when applying deep learning to Korean sentiment analysis? As an approach to these research questions, we generate various types of morpheme vectors reflecting the research questions and then compare the classification accuracy through a non-static CNN(Convolutional Neural Network) model taking in the morpheme vectors. As for training and test datasets, Naver Shopping's 17,260 cosmetics product reviews are used. To derive morpheme vectors, we use data from the same domain as the target one and data from other domain; Naver shopping's about 2 million cosmetics product reviews and 520,000 Naver News data arguably corresponding to Google's News data. The six primary sets of morpheme vectors constructed in this study differ in terms of the following three criteria. First, they come from two types of data source; Naver news of high grammatical correctness and Naver shopping's cosmetics product reviews of low grammatical correctness. Second, they are distinguished in the degree of data preprocessing, namely, only splitting sentences or up to additional spelling and spacing corrections after sentence separation. Third, they vary concerning the form of input fed into a word vector model; whether the morphemes themselves are entered into a word vector model or with their POS tags attached. The morpheme vectors further vary depending on the consideration range of POS tags, the minimum frequency of morphemes included, and the random initialization range. All morpheme vectors are derived through CBOW(Continuous Bag-Of-Words) model with the context window 5 and the vector dimension 300. It seems that utilizing the same domain text even with a lower degree of grammatical correctness, performing spelling and spacing corrections as well as sentence splitting, and incorporating morphemes of any POS tags including incomprehensible category lead to the better classification accuracy. The POS tag attachment, which is devised for the high proportion of homonyms in Korean, and the minimum frequency standard for the morpheme to be included seem not to have any definite influence on the classification accuracy.