• Asia Marketing Journal
• /
• v.13 no.4
• /
• pp.29-54
• /
• 2012

Recently, as film has been admitted as the artistic merit and higher value-added business, the past studies on film have been lively carried on various fields. Especially, the film business is thought to be value-added business and has explored the causes of influencing spectators. However, there are no researches enough to explain what induces the choice and diffusion of the film. The film is not only hedonic products but also typical example of experiential products. So how to process film formation plays important roles in explaining the procedures of forming preference on the film and the movies spread more widely. But the great part of study of films has been concentrated on exploring hedonic factors of influencing spectator's choice. Until now there is not enough study for the relationship between experiential information processing and film preference. To explain film's preference, our study focuses on preference fluency and processing fluency that can provide an insight for our question about the relationship. In this article, to explain the procedures of processing experiential information and forming preference on the film, our study focuses on finding the relationship between film's processing fluency and film's preference fluency and explores the factors that affect film's processing fluency. To achieve the goal of this study, we distinguish factors of film's conceptual fluency from factors of film's perceptual fluency and explore the paths from the factors to film's preference fluency. The factors which have effects on perceptual fluency are hypothesized to be distinction of image expression, distinction of sound expression, correspondence between actors' image and their role. The factors which have effect on conceptual fluency are supposed to be well-organized story, suitability of lines expression. The experiments in which students were sampled at 'C' university were conducted in 2010 (december). Data collection was proceeded through questionnaires. We test the hypothesized model by using structural equation modeling(Amos 17.0). The fit indices for the model are as follows : x²=416.266(df=213, p=0.00), GFI=0.855, AGFI=0.812, RMSEA =0.069, IFI=O.925, CFI=0.920, TLI=0.905. According to the guidelines, there is evidence that our measurement model fits data. The results of empirical study are as follows. The path from film's perceptual fluency to film's preference fluency is supported(estimate: 0.223, C.R: 2.641). The path from film's conceptual fluency to film's preference fluency is supported(estimate: 0.397, C.R: 4.863). The path from distinction of image expression to film's perceptual fluency is not supported(estimate: 0.113, C.R: 1.665). The path from distinction of sound expression to film's perceptual fluency is supported (estimate: 0.190, C.R: 2.042). The path from correspondence between actors' image and their role to film's perceptual fluency is supported(estimate: 0.686, C.R: 5.566). The path from well-organized story to film's conceptual fluency is supported(estimate: 0.396, C.R: 4.023). The path from suitability of lines expression to film's conceptual fluency is supported(estimate: 0.536, C.R: 5.441). Concludingly, our study explored the influencing factors of film's processing fluency inducing film's Preference fluency. First, film's perceptual fluency and film's conceptual fluency have positive effects on film's preference fluency. Second, distinction of image expression is not significant on film's perceptual fluency, but distinction of sound expression and image's correspondence of actors' image and their role have positive effects on film's perceptual fluency. Lastly, well-organized story and suitability of lines expression have positive effects on film's conceptual fluency.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.59-83
• /
• 2018

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.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.67-83
• /
• 2018

The Korean film industry with significant increase every year exceeded the number of cumulative audiences of 200 million people in 2013 finally. However, starting from 2015 the Korean film industry entered a period of low growth and experienced a negative growth after all in 2016. To overcome such difficulty, stakeholders like production company, distribution company, multiplex have attempted to maximize the market returns using strategies of predicting change of market and of responding to such market change immediately. Since a film is classified as one of experiential products, it is not easy to predict a box office record and the initial number of audiences before the film is released. And also, the number of audiences fluctuates with a variety of factors after the film is released. So, the production company and distribution company try to be guaranteed the number of screens at the opining time of a newly released by multiplex chains. However, the multiplex chains tend to open the screening schedule during only a week and then determine the number of screening of the forthcoming week based on the box office record and the evaluation of audiences. Many previous researches have conducted to deal with the prediction of box office records of films. In the early stage, the researches attempted to identify factors affecting the box office record. And nowadays, many studies have tried to apply various analytic techniques to the factors identified previously in order to improve the accuracy of prediction and to explain the effect of each factor instead of identifying new factors affecting the box office record. However, most of previous researches have limitations in that they used the total number of audiences from the opening to the end as a target variable, and this makes it difficult to predict and respond to the demand of market which changes dynamically. Therefore, the purpose of this study is to predict the weekly number of audiences of a newly released film so that the stakeholder can flexibly and elastically respond to the change of the number of audiences in the film. To that end, we considered the factors used in the previous studies affecting box office and developed new factors not used in previous studies such as the order of opening of movies, dynamics of sales. Along with the comprehensive factors, we used the machine learning method such as Random Forest, Multi Layer Perception, Support Vector Machine, and Naive Bays, to predict the number of cumulative visitors from the first week after a film release to the third week. At the point of the first and the second week, we predicted the cumulative number of visitors of the forthcoming week for a released film. And at the point of the third week, we predict the total number of visitors of the film. In addition, we predicted the total number of cumulative visitors also at the point of the both first week and second week using the same factors. As a result, we found the accuracy of predicting the number of visitors at the forthcoming week was higher than that of predicting the total number of them in all of three weeks, and also the accuracy of the Random Forest was the highest among the machine learning methods we used. This study has implications in that this study 1) considered various factors comprehensively which affect the box office record and merely addressed by other previous researches such as the weekly rating of audiences after release, the weekly rank of the film after release, and the weekly sales share after release, and 2) tried to predict and respond to the demand of market which changes dynamically by suggesting models which predicts the weekly number of audiences of newly released films so that the stakeholders can flexibly and elastically respond to the change of the number of audiences in the film.

• Korean Journal of Heritage: History & Science
• /
• v.39
• /
• pp.351-378
• /
• 2006

With the development of media, the methods for the documentation of intangible cultural heritage have been also developed and diversified. As well as the previous analogue ways of documentation, the have been recently applying new multi-media technologies focusing on digital pictures, sound sources, movies, etc. Among the new technologies, the documentation of intangible cultural heritage using the method of 'Motion Capture' has proved itself prominent especially in the fields that require three-dimensional documentation such as dances and performances. Motion Capture refers to the documentation technology which records the signals of the time varing positions derived from the sensors equipped on the surface of an object. It converts the signals from the sensors into digital data which can be plotted as points on the virtual coordinates of the computer and records the movement of the points during a certain period of time, as the object moves. It produces scientific data for the preservation of intangible cultural heritage, by displaying digital data which represents the virtual motion of a holder of an intangible cultural heritage. National Research Institute of Cultural Properties (NRICP) has been working on for the development of new documentation method for the Important Intangible Cultural Heritage designated by Korean government. This is to be done using 'motion capture' equipments which are also widely used for the computer graphics in movie or game industries. This project is designed to apply the motion capture technology for 3 years- from 2005 to 2007 - for 11 performances from 7 traditional dances of which body gestures have considerable values among the Important Intangible Cultural Heritage performances. This is to be supported by lottery funds. In 2005, the first year of the project, accumulated were data of single dances, such as Seungmu (monk's dance), Salpuri(a solo dance for spiritual cleansing dance), Taepyeongmu (dance of peace), which are relatively easy in terms of performing skills. In 2006, group dances, such as Jinju Geommu (Jinju sword dance), Seungjeonmu (dance for victory), Cheoyongmu (dance of Lord Cheoyong), etc., will be documented. In the last year of the project, 2007, education programme for comparative studies, analysis and transmission of intangible cultural heritage and three-dimensional contents for public service will be devised, based on the accumulated data, as well as the documentation of Hakyeonhwadae Habseolmu (crane dance combined with the lotus blossom dance). By describing the processes and results of motion capture documentation of Salpuri dance (Lee Mae-bang), Taepyeongmu (Kang seon-young) and Seungmu (Lee Mae-bang, Lee Ae-ju and Jung Jae-man) conducted in 2005, this report introduces a new approach for the documentation of intangible cultural heritage. During the first year of the project, two questions have been raised. First, how can we capture motions of a holder (dancer) without cutoffs during quite a long performance? After many times of tests, the motion capture system proved itself stable with continuous results. Second, how can we reproduce the accurate motion without the re-targeting process? The project re-created the most accurate motion of the dancer's gestures, applying the new technology to drew out the shape of the dancers's body digital data before the motion capture process for the first time in Korea. The accurate three-dimensional body models for four holders obtained by the body scanning enhanced the accuracy of the motion capture of the dance.

• (The) Research of the performance art and culture
• /
• no.35
• /
• pp.61-92
• /
• 2017

During the Japanese colonial era, traditional music performances were gradually diminishing and weakening in the particular condition of colonization. Meanwhile, from the time of enlightenment, Western genre performances were becoming vitalized with the influence of Western civilization that began to be spread steadily throughout the society. In that situation, traditional music performances tended to be mixed performances accompanied by Western ones, not independent performances. Mostly, they were accompanied by Western music, and also, they were performed along with other genres like plays, lectures, movies, dances, or magic, too. Such form of mixed performances accompanied by Western genres became even more vitalized in the 1920's and came to be positioned as a form of traditional music performances. Therefore, research on the forms of mixed performances between Western genres and traditional music is meaningful in examining the forms of traditional music performances that have not been studied in the history of Korean modern music and understanding the trends of traditional music performances which were generally found in the Japanese colonial era. However, such research has hardly been conducted concretely yet. Accordingly, concerning the forms of mixed performances between Western genres and traditional music in the 1920's, this author considered the background of vitalizing mixed performances between Western genres and traditional music mainly with newspaper articles of the time and their formal characteristics. Regarding the background of vitalizing the forms of mixed performances between Western genres and traditional music, from the 1920's, the forms of mixed performances between Western genres and traditional music became more vitalized than before. The causes of that may include the increase of groups hosting or sponsoring such performances from the 1920's and also the dramatic increase of such performances in general. Moreover, the increased performances were conducted in the forms of mixed performances mainly in order to satisfy the people's needs becoming diversified with the distribution of Western civilization. Concerning the formal characteristics of mixed performances between Western genres and traditional music, this researcher classified western genres performed with traditional music and examined what characteristics were found in such mixed performances of tradition music by the types of Western genres respectively. First, in the mixed performances type of western-type genre and traditional music, the number of programs for the western music had significant portion in general, and there were certain ensemble of the western music and traditional musical instrument that was rare at this period of time, and it also had the characteristics of classifying two genres to perform for each title or date. Second, in the mixed performances type of the drama and traditional music, the traditional music is directly participated in the drama with the similar type to the theater, or performed independently from the drama with the role of interlude performance for the stage conversion of the drama to have the characteristics of performing in audience publicity or entertainment. Third, in the mixed performances type of the lecture and traditional music, the traditional music is played before or after the lecture to play the role to set the atmosphere and entertainment for the lecture as displaying the feature to perform for the audience attraction. And, fourth, in the mixed performances type of the movie and traditional music, the traditional music sometimes directly participated in the movie or had the features of independent performance, and there was a characteristic to perform for the entertainment after showing a movie.

• Journal of Global Scholars of Marketing Science
• /
• v.19 no.4
• /
• pp.1-10
• /
• 2009

The purpose of this study was to categorize the gap between coffee shop 'importance' (as perceived by customers before patronizing the coffee shop) and 'satisfaction' (perception of customers after patronizing the coffee shop) as positive or negative and to analyze the effect of these gaps on purchasing behavior. To do this, I used the gap between importance and satisfaction regarding the choice of a coffee shop as the explanatory variable and performed an empirical analysis of the direction and size of the effect of the gap on purchasing behavior (overall satisfaction, willingness-to-revisit) by applying the Ordered Probit Model (OPM). A previous study that used IPA to evaluate the effects of gaps estimated the direction and size of a quadrant but failed to analyze the effect of gaps on customers. In this study, I evaluated the effects of positive and negative gaps on customer satisfaction and willingness-to-revisit. Using OPM, I quantified the effect of positive and negative gaps on overall customer satisfaction and willingness-to-revisit. Per-head expenditure, frequency of visits, and coffee-purchasing place had the most positive effects on overall customer satisfaction. Frequency of visits, followed by per-head expenditure and then coffee-purchasing place, had the most positive impact on willingness-to-visit. Thus per-head expenditure and frequency of visits had the greatest positive effects on overall satisfaction and willingness-to-revisit. This finding implies that the higher the actual satisfaction (gap) of customers who spend KRW5,000 or more once or more per week at coffee shops is, the higher their overall satisfaction and willingness-to-revisit are. Despite the fact that economical efficiency had a significant effect on overall satisfaction and willingness-to-revisit, college and university students still use coffee shops and are willing to spend KRW5,000 because they do not only purchase coffee as a product itself, but use the coffee shop for other activities, such as working, meeting friends, or relaxing. College and university students also access the Internet in coffee shops via personal laptops, watch movies, and study; thus, coffee shops should provide their customers with the appropriate facilities and services. The fact that a positive gap for coffee shop brand had a positive effect on willingness-to-revisit implies that the higher the level of customer satisfaction, the greater the willingness-to-revisit. A negative gap for this factor, on the other hand, implies that the lower the level of customer satisfaction, the lower the willingness-to-revisit. Thus, the brand factor has a comparatively greater effect on satisfaction than the other factors evaluated in this study. Given that the domestic coffee culture is becoming more upscale and college/university students are sensitive to this trend, students are attentive to brands. In most upscale coffee shops in Korea, the outer wall is built out of glass that can be opened, the interiors are exotic with an open kitchen. These upscale coffee shops function as landmarks and match the taste of college/university students. Coffee shops in Korea have become a cultural brand. To make customers feel that coffee shops are upscale, good quality establishments and measures to provide better services in terms of brand factor should be instituted. The intensified competition among coffee shop brands in Korea as a result of the booming industry indicates that provision of additional services is needed to differentiate competitors. These customers can also use a scanner free of charge. Another strategy that can be used to boost brands could be to provide and operate a seminar room for seminars and group study. If coffee shops adopt these types of strategies, college/university students would be more likely to consider the expenses they incur worthwhile and, subsequently, they would be more likely to be satisfied with the brands of these coffee shops, with an associated increase in their willingness-to-revisit. Gender and study year had the most negative effects on overall satisfaction and willingness-to-revisit. Female students were more likely to be satisfied and be willing to return than male students, and third and fourth-year students were more likely to be satisfied and willing-to-return than first or second-year students. Students who drink coffee, read books, and use laptops alone at coffee shops are easily noticeable. High-grade students tend to visit coffee shops alone in order to use their time efficiently for self-development and to find jobs. The economical efficiency factor had the greatest effect on overall satisfaction and willingness-to-revisit in terms of a positive gap. The higher the actual satisfaction (gap) of students with the price of the coffee, the greater their overall satisfaction and willingness-to-revisit. Economical efficiency with a negative gap had a negative effect on willingness-to-revisit, which implies that a less negative gap will result in a greater willingness-to-revisit. Amid worsening market conditions, coffee shops located around colleges/universities are using strategies, such as a point or membership card, strategic alliances with credit-card companies, development of a set menu or seasonal menu, and free coffee-shot services to increase their competitive edge. Product power also had a negative effect in terms of a negative gap, which indicates that a higher negative gap will result in a lower willingness-to-revisit. Because there are many more customers that enjoy coffee in this decade, as compared to previous decades, the new generation of customers, namely college/university students, want various menu items in addition to coffee, and coffee shops should, therefore, add side menu items, such as waffles, rice cakes, cakes, sandwiches, and salads. For example, Starbucks Korea is making efforts to enhance product power by selling rice cakes flavored in strawberry, wormwood, and pumpkin, and providing coffee or cream free of charge. In summary, coffee shops should focus on increasing their economical efficiency, brand, and product power to enhance the satisfaction of college/university students. Because shops adjacent to colleges or universities enjoy a locational advantage, providing differentiated services in terms of economical efficiency, brand, and product power, is likely to increase customer satisfaction and return visits. Coffee shop brands should, therefore, be innovative and embrace change to meet their customers' desires. Because this study only targeted college/university students in Seoul, comparative studies targeting diverse regions and age groups are required to generalize the findings and recommendations of this study.

• Journal of Global Scholars of Marketing Science
• /
• v.20 no.2
• /
• pp.219-230
• /
• 2010

Digital content makes big changes to our daily lives while bringing opportunities and challenges for companies. Creative firms integrate pictures, texts, videos, audios, and data by digitalization to develop new products or services and create digital experiences to promote their brands. Most articles on digital content contribute to the basic concept or development of marketing it in literature. Actually, compared with traditional value chains for common products or services, the digital content industry seems to have more potential value. Because quite a bit of digital content is free to the consumer, price is not necessarily perceived as an indicator of the quality or value of information (Rowley 2008). It becomes evident that a current theme in digital content is the issue of "value," and research on customers' perceived value of digital content is a necessity. This article argues that experiential value has an advantage in customers' evaluations of digital content. Two different but related contributions to the understanding of "value" of digital content are made here. First, based on the comparison of digital content with products and services, the article proposes two key characteristics that make experiential strategy available for digital content: intangibility and near-zero reproduction cost. On top of that, based on the discussion of the gap between company's idealized value and customer's perceived value, this article emphasizes that digital content prices and pricing of digital content is different from products and services. As a result of intangibility, prices may not reflect customer value. Moreover, the cost of digital content in the development stage may be very high while reproduction costs shrink dramatically. Moreover, because of the value gap mentioned before, the pricing polices vary for different digital contents. For example, flat price policy is generally used for movies and music (Magiera 2001; Netherby 2002), while for continuous demand, digital content such as online games and anti-virus programs involves a more complicated matter of utility and competitive price levels. Digital content companies have to explore various kinds of strategies to overcome this gap. Rethinking marketing solutions such as advertisements, images, and word-of-mouth and their effect on customers' perceived value becomes essential. China's digital content industry is becoming more and more globalized and drawing special attention from different countries and regions that have respective competitive advantages. The 2008-2009 Annual Report on the Development of China's Digital Content Industry (CCIDConsulting 2009) indicates that, with the driven power of domestic demand and governmental policy support, the country's digital content industry maintained a fast growth of some 30 percent in 2008, obviously indicating the initial stage of industry expansion. In China, anti-virus programs and other software programs which need to be updated use a quarter-based pricing policy. Customers can download a trial version for free and use it for six months or a year. If they want to use it longer, continuous payment is needed. They examine the excellence of the digital content during this trial period and decide whether to pay for continued usage. For China’s music and movie industries, as a result of initial development, experiential strategy has not been much applied, even though firms in other countries find the trial experience and explore important strategies(such as customers listening to music for several seconds for free before downloading it). For the above reasons, anti-virus program may be a representative for digital content industry in China and an exploratory study of the advantage of experiential value in customer's perceived value of digital content is done in the anti-virus market of China. In order to enhance the reliability of the survey data, this study focused on people who were experienced users of anti-virus programs. The empirical results revealed that experiential value has a positive effect on customers' perceived value of digital content. In other words, because digital content is intangible and the reproduction costs are nearly zero, customers' evaluations are based heavily on their experience. Moreover, image and word-of-mouth do not have a positive effect on perceived value, only on experiential value. That is to say, a digital content value chain is different from that of a general product or service. Experiential value has a notable advantage and mediates the effect of image and word-of-mouth on perceived value. The results of this study help provide an understanding of why free digital content downloads exist in developing countries. Customers can perceive the value of digital content only by using and experiencing it. This is also why such governments support the development of digital content. Other developing countries whose digital content business is also in the beginning stage can make use of the suggestions here. Moreover, based on the advantage of experiential strategy, companies should make more of an effort to invest in customers' experience. As a result of the characteristics and value gap of digital content, customers perceive more value in the intangible digital content only by experiencing what they really want. Moreover, because of the near-zero reproduction costs, companies can perhaps use experiential strategy to enhance customer understanding of digital content.

• Asia pacific journal of information systems
• /
• v.21 no.1
• /
• pp.103-122
• /
• 2011

Recently, numerous documents have been made available electronically. Internet search engines and digital libraries commonly return query results containing hundreds or even thousands of documents. In this situation, it is virtually impossible for users to examine complete documents to determine whether they might be useful for them. For this reason, some on-line documents are accompanied by a list of keywords specified by the authors in an effort to guide the users by facilitating the filtering process. In this way, a set of keywords is often considered a condensed version of the whole document and therefore plays an important role for document retrieval, Web page retrieval, document clustering, summarization, text mining, and so on. Since many academic journals ask the authors to provide a list of five or six keywords on the first page of an article, keywords are most familiar in the context of journal articles. However, many other types of documents could not benefit from the use of keywords, including Web pages, email messages, news reports, magazine articles, and business papers. Although the potential benefit is large, the implementation itself is the obstacle; manually assigning keywords to all documents is a daunting task, or even impractical in that it is extremely tedious and time-consuming requiring a certain level of domain knowledge. Therefore, it is highly desirable to automate the keyword generation process. There are mainly two approaches to achieving this aim: keyword assignment approach and keyword extraction approach. Both approaches use machine learning methods and require, for training purposes, a set of documents with keywords already attached. In the former approach, there is a given set of vocabulary, and the aim is to match them to the texts. In other words, the keywords assignment approach seeks to select the words from a controlled vocabulary that best describes a document. Although this approach is domain dependent and is not easy to transfer and expand, it can generate implicit keywords that do not appear in a document. On the other hand, in the latter approach, the aim is to extract keywords with respect to their relevance in the text without prior vocabulary. In this approach, automatic keyword generation is treated as a classification task, and keywords are commonly extracted based on supervised learning techniques. Thus, keyword extraction algorithms classify candidate keywords in a document into positive or negative examples. Several systems such as Extractor and Kea were developed using keyword extraction approach. Most indicative words in a document are selected as keywords for that document and as a result, keywords extraction is limited to terms that appear in the document. Therefore, keywords extraction cannot generate implicit keywords that are not included in a document. According to the experiment results of Turney, about 64% to 90% of keywords assigned by the authors can be found in the full text of an article. Inversely, it also means that 10% to 36% of the keywords assigned by the authors do not appear in the article, which cannot be generated through keyword extraction algorithms. Our preliminary experiment result also shows that 37% of keywords assigned by the authors are not included in the full text. This is the reason why we have decided to adopt the keyword assignment approach. In this paper, we propose a new approach for automatic keyword assignment namely IVSM(Inverse Vector Space Model). The model is based on a vector space model. which is a conventional information retrieval model that represents documents and queries by vectors in a multidimensional space. IVSM generates an appropriate keyword set for a specific document by measuring the distance between the document and the keyword sets. The keyword assignment process of IVSM is as follows: (1) calculating the vector length of each keyword set based on each keyword weight; (2) preprocessing and parsing a target document that does not have keywords; (3) calculating the vector length of the target document based on the term frequency; (4) measuring the cosine similarity between each keyword set and the target document; and (5) generating keywords that have high similarity scores. Two keyword generation systems were implemented applying IVSM: IVSM system for Web-based community service and stand-alone IVSM system. Firstly, the IVSM system is implemented in a community service for sharing knowledge and opinions on current trends such as fashion, movies, social problems, and health information. The stand-alone IVSM system is dedicated to generating keywords for academic papers, and, indeed, it has been tested through a number of academic papers including those published by the Korean Association of Shipping and Logistics, the Korea Research Academy of Distribution Information, the Korea Logistics Society, the Korea Logistics Research Association, and the Korea Port Economic Association. We measured the performance of IVSM by the number of matches between the IVSM-generated keywords and the author-assigned keywords. According to our experiment, the precisions of IVSM applied to Web-based community service and academic journals were 0.75 and 0.71, respectively. The performance of both systems is much better than that of baseline systems that generate keywords based on simple probability. Also, IVSM shows comparable performance to Extractor that is a representative system of keyword extraction approach developed by Turney. As electronic documents increase, we expect that IVSM proposed in this paper can be applied to many electronic documents in Web-based community and digital library.

• Asia Marketing Journal
• /
• v.14 no.2
• /
• pp.97-125
• /
• 2012

Companies recently introduce art collaborated products incorporating culture into a product. Art collaborated products include incorporating famous movies and/or design of an artist into a newly launched product. The introduction of art collaborated products are gradually increasing. However, research for this trend is relatively scarce. Although research concerning design has discussed a number of different factors as playing a role in influencing responses to design including culture, fashion, innate preferences, etc.), only limited attention has been paid to the processes by which consumers generate responses to product designs. People with different characteristics may respond differently. When people encounter these art products, they may become curious, may think that these products are unique, novel and innovative. People tend to show different levels of curiosity when they encounter new and novel objects, which they have rarely seen or experienced. Curiosity is defined as a desire for acquiring new knowledge and new sensory experience. Previous studies demonstrated that curiosity motivates individuals to engage in exploratory behaviors. People also show different levels of need for uniqueness, which is defined as being different from others or becoming distinctive among a larger group. Individual's need for uniqueness results from signals conveyed by the material objects that individuals choose to display. Recently, researcher have developed the need for uniqueness with three distinct constructs. These three concepts include creative choice, unpopular choice, and avoidance of similarity. Creative choice is a trait tendency of an individual by expressing or differentiating himself from others through consumptions of unique products. Unpopular choice is related to an individual's tendency to consume products, which deviates from group norms. Avoidance of similarity is linked to the avoidance of consumption behavior of products that are not famous. Past research implies that people with different levels of need for uniqueness show different motivational processes. Previous research also demonstrates that different customer emotions may be derived when consumers are exposed to these art collaborated products. Research tradition has been investigated three different emotional responses such as pleasure, arousal, and dominance. Pleasure is defined as the degree to which a person feels good, joyful, happy, or satisfied in a situation. Arousal is defined as the extent to which a person feels stimulated, active, or excited. Dominance is defined as the extent that a person feels powerful vis-a-vis the environment that surrounds him/her. Previous research show that complex, speedy, and surprising stimuli may excite consumers and thus make them more pleased and engaged in their approach behavior. However, the current study identified these emotional responses as positive emotion, negative emotion, and arousal. These derived emotions may lead consumers to approach and/or avoidance behaviors. In addition, males and females tend to respond differently when they are exposed to art collaboration products. Building on this research tradition, the current study aims to investigate the inter-relationships between individual traits such as curiosity and need for uniqueness and individual's emotional responses including positive and negative emotion and arousal when people encounter various art collaborated products. Emotional responses are proposed to influence purchase intention. Additionally, previous studies show that male and females respond differently to similar stimuli. Accordingly, gender difference are proposed to moderate the links between individual traits and emotional responses. These research aims of the current study may contribute to extending our knowledge in terms of (1) which individual characteristics are related to different emotions, and (2) how these different emotional responses inter-connected to future purchase intention of arts collaborated products. In addition, (3) the different responses to these arts collaborated products by males and females will guide managers how to concoct different strategies to these segments. The questionnaire for the present study was adopted from the previous literature and validated with a pilot test. The survey was conducted in Daegu, a third largest city in South Korea, for three weeks during June and July 2011. Most respondents were in their twenties and thirties. 350 questionnaires were distributed and among them 300 were proved to be valid (valid response rate of 85.7%). Survey questionnaires from valid 300 respondents are used to test hypotheses proposed. The structural equation model (SEM) was used to validate the research model. The measurement and structural model was tested using LISREL 8.7. The measurement model test demonstrated that consistency, convergent validity, and discriminat validity of the measurement items were acceptable. The results from the structural model demonstrate that curiosity has a positive impact on positive emotion, but not on negative emotion and arousal. Need for uniqueness has three different sub-concepts such as creative choice, unpopular choice, and avoidance of similarity. The results show that creative choice has a positive effect on arousal and positive emotion, but has a negative impact on negative emotion. Unpopular choice has a positive effect on arousal, but on neither positive nor negative emotions. Avoidance of similarity has no impact on neither emotions nor arousal. The results also demonstrated that gender has a moderating influence. Males show more negative emotion to creative and unpopular choices. Implications and future research directions are discussed in conclusion.

• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.77-110
• /
• 2017

Recently, the diversification and individualization of consumption patterns through the web and mobile devices based on the Internet have been rapid. As this happens, the efficient operation of the offline store, which is a traditional distribution channel, has become more important. In order to raise both the sales and profits of stores, stores need to supply and sell the most attractive products to consumers in a timely manner. However, there is a lack of research on which SKUs, out of many products, can increase sales probability and reduce inventory costs. In particular, if a company sells products through multiple in-store stores across multiple locations, it would be helpful to increase sales and profitability of stores if SKUs appealing to customers are recommended. In this study, the recommender system (recommender system such as collaborative filtering and hybrid filtering), which has been used for personalization recommendation, is suggested by SKU recommendation method of a store unit of a distribution company that handles a homogeneous brand through a plurality of sales stores by country and region. We calculated the similarity of each store by using the purchase data of each store's handling items, filtering the collaboration according to the sales history of each store by each SKU, and finally recommending the individual SKU to the store. In addition, the store is classified into four clusters through PCA (Principal Component Analysis) and cluster analysis (Clustering) using the store profile data. The recommendation system is implemented by the hybrid filtering method that applies the collaborative filtering in each cluster and measured the performance of both methods based on actual sales data. Most of the existing recommendation systems have been studied by recommending items such as movies and music to the users. In practice, industrial applications have also become popular. In the meantime, there has been little research on recommending SKUs for each store by applying these recommendation systems, which have been mainly dealt with in the field of personalization services, to the store units of distributors handling similar brands. If the recommendation method of the existing recommendation methodology was 'the individual field', this study expanded the scope of the store beyond the individual domain through a plurality of sales stores by country and region and dealt with the store unit of the distribution company handling the same brand SKU while suggesting a recommendation method. In addition, if the existing recommendation system is limited to online, it is recommended to apply the data mining technique to develop an algorithm suitable for expanding to the store area rather than expanding the utilization range offline and analyzing based on the existing individual. The significance of the results of this study is that the personalization recommendation algorithm is applied to a plurality of sales outlets handling the same brand. A meaningful result is derived and a concrete methodology that can be constructed and used as a system for actual companies is proposed. It is also meaningful that this is the first attempt to expand the research area of the academic field related to the existing recommendation system, which was focused on the personalization domain, to a sales store of a company handling the same brand. From 05 to 03 in 2014, the number of stores' sales volume of the top 100 SKUs are limited to 52 SKUs by collaborative filtering and the hybrid filtering method SKU recommended. We compared the performance of the two recommendation methods by totaling the sales results. The reason for comparing the two recommendation methods is that the recommendation method of this study is defined as the reference model in which offline collaborative filtering is applied to demonstrate higher performance than the existing recommendation method. The results of this model are compared with the Hybrid filtering method, which is a model that reflects the characteristics of the offline store view. The proposed method showed a higher performance than the existing recommendation method. The proposed method was proved by using actual sales data of large Korean apparel companies. In this study, we propose a method to extend the recommendation system of the individual level to the group level and to efficiently approach it. In addition to the theoretical framework, which is of great value.