• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.141-154
• /
• 2019

Rapid growth of internet technology and social media is progressing. Data mining technology has evolved to enable unstructured document representations in a variety of applications. Sentiment analysis is an important technology that can distinguish poor or high-quality content through text data of products, and it has proliferated during text mining. Sentiment analysis mainly analyzes people's opinions in text data by assigning predefined data categories as positive and negative. This has been studied in various directions in terms of accuracy from simple rule-based to dictionary-based approaches using predefined labels. In fact, sentiment analysis is one of the most active researches in natural language processing and is widely studied in text mining. When real online reviews aren't available for others, it's not only easy to openly collect information, but it also affects your business. In marketing, real-world information from customers is gathered on websites, not surveys. Depending on whether the website's posts are positive or negative, the customer response is reflected in the sales and tries to identify the information. However, many reviews on a website are not always good, and difficult to identify. The earlier studies in this research area used the reviews data of the Amazon.com shopping mal, but the research data used in the recent studies uses the data for stock market trends, blogs, news articles, weather forecasts, IMDB, and facebook etc. However, the lack of accuracy is recognized because sentiment calculations are changed according to the subject, paragraph, sentiment lexicon direction, and sentence strength. This study aims to classify the polarity analysis of sentiment analysis into positive and negative categories and increase the prediction accuracy of the polarity analysis using the pretrained IMDB review data set. First, the text classification algorithm related to sentiment analysis adopts the popular machine learning algorithms such as NB (naive bayes), SVM (support vector machines), XGboost, RF (random forests), and Gradient Boost as comparative models. Second, deep learning has demonstrated discriminative features that can extract complex features of data. Representative algorithms are CNN (convolution neural networks), RNN (recurrent neural networks), LSTM (long-short term memory). CNN can be used similarly to BoW when processing a sentence in vector format, but does not consider sequential data attributes. RNN can handle well in order because it takes into account the time information of the data, but there is a long-term dependency on memory. To solve the problem of long-term dependence, LSTM is used. For the comparison, CNN and LSTM were chosen as simple deep learning models. In addition to classical machine learning algorithms, CNN, LSTM, and the integrated models were analyzed. Although there are many parameters for the algorithms, we examined the relationship between numerical value and precision to find the optimal combination. And, we tried to figure out how the models work well for sentiment analysis and how these models work. This study proposes integrated CNN and LSTM algorithms to extract the positive and negative features of text analysis. The reasons for mixing these two algorithms are as follows. CNN can extract features for the classification automatically by applying convolution layer and massively parallel processing. LSTM is not capable of highly parallel processing. Like faucets, the LSTM has input, output, and forget gates that can be moved and controlled at a desired time. These gates have the advantage of placing memory blocks on hidden nodes. The memory block of the LSTM may not store all the data, but it can solve the CNN's long-term dependency problem. Furthermore, when LSTM is used in CNN's pooling layer, it has an end-to-end structure, so that spatial and temporal features can be designed simultaneously. In combination with CNN-LSTM, 90.33% accuracy was measured. This is slower than CNN, but faster than LSTM. The presented model was more accurate than other models. In addition, each word embedding layer can be improved when training the kernel step by step. CNN-LSTM can improve the weakness of each model, and there is an advantage of improving the learning by layer using the end-to-end structure of LSTM. Based on these reasons, this study tries to enhance the classification accuracy of movie reviews using the integrated CNN-LSTM model.

• Journal of Global Scholars of Marketing Science
• /
• v.19 no.3
• /
• pp.37-48
• /
• 2009

The standardization of marketing has been one of the most focused research topics in international marketing. The term "global marketing" was often used to mean an internationally standardized marketing strategy based on similarities between foreign markets. Marketing standardization was discussed only within the context of traditional physical marketplaces. Since then, the digital "marketspace" of the Internet had emerged in the 90's, and it became one of the most important drivers of the globalization process opening new opportunities for the standardization of global marketing activities. On the other hand, the opinion that a greater adoption of the Internet by customers may lead to a higher degree of customization and differentiation of products rather than standardization is also quite popular. Considering this disagreement, it is notable that comprehensive studies which focus upon the marketing standardization especially in the context of global e-commerce are missing to a high degree. On this background, the two basic research questions being addressed in this study are: (1) To what extent do companies standardize their marketing in international e-commerce? (2) Is there an impact of marketing standardization on the performance (or success) of these companies? Following research hypotheses were generated based upon literature review: H 1: Internationally engaged e-commerce firms show a growing readiness for marketing standardization. H 2: Marketing standardization exerts positive effects on the success of companies in international e-commerce. H 3: In international e-commerce, marketing mix standardization exerts a stronger positive effect on the economic as well as the non-economic success of companies than marketing process standardization. H 4: The higher the non-economic success in international e-commerce firms, the higher the economic success. The data for this research were obtained from a questionnaire survey conducted from February to April 2005. The international e-commerce companies of various industries in Germany and all subsidiaries or headquarters of foreign e-commerce companies based in Germany were included in the survey. 118 out of 801 companies responded to the questionnaire. For structural equation modelling (SEM), the Partial-Least. Squares (PLS) approach in the version PLS-Graph 3.0 was applied (Chin 1998a; 2001). All of four research hypotheses were supported by result of data analysis. The results show that companies engaged in international e-commerce standardize in particular brand name, web page design, product positioning, and the product program to a high degree. The companies intend to intensify their efforts for marketing mix standardization in the future. In addition they want to standardize their marketing processes also to a higher degree, especially within the range of information systems, corporate language and online marketing control procedures. In this study, marketing standardization exerts a positive overall impact on company performance in international e-commerce. Standardization of marketing mix exerts a stronger positive impact on the non-economic success than standardization of marketing processes, which in turn contributes slightly stronger to the economic success. Furthermore, our findings give clear support to the assumption that the non-economic success is highly relevant to the economic success of the firm in international e-commerce. The empirical findings indicate that marketing standardization is relevant to the companies' success in international e-commerce. But marketing mix and marketing process standardization contribute to the firms' economic and non-economic success in different ways. The findings indicate that companies do standardize numerous elements of their marketing mix on the Internet. This practice is in part contrary to the popular concept of a "differentiated standardization" which argues that some elements of the marketing mix should be adapted locally and others should be standardized internationally. Furthermore, the findings suggest that the overall standardization of marketing -rather than the standardization of one particular marketing mix element - is what brings about a positive overall impact on success.

• Information Systems Review
• /
• v.20 no.2
• /
• pp.39-62
• /
• 2018

Thanks to the growth of computing power and the recent development of data analytics, researchers have started to work on the data produced by users through the Internet or social media. This study is in line with these recent research trends and attempts to adopt data analytical techniques. We focus on the impact of "internal marketing" factors on firm performance, which is typically studied through survey methodologies. We looked into the job review platform Jobplanet (www.jobplanet.co.kr), which is a website where employees and former employees anonymously review companies and their management. With web crawling processes, we collected over 40K data points and performed morphological analysis to classify employees' reviews for internal marketing data. We then implemented econometric analysis to see the relationship between internal marketing and market capitalization. Contrary to the findings of extant survey studies, internal marketing is positively related to a firm's market capitalization only within a limited area. In most of the areas, the relationships are negative. Particularly, female-friendly environment and human resource development (HRD) are the areas exhibiting positive relations with market capitalization in the manufacturing industry. In the service industry, most of the areas, such as employ welfare and work-life balance, are negatively related with market capitalization. When firm size is small (or the history is short), female-friendly environment positively affect firm performance. On the contrary, when firm size is big (or the history is long), most of the internal marketing factors are either negative or insignificant. We explain the theoretical contributions and managerial implications with these results.

• Information Systems Review
• /
• v.5 no.2
• /
• pp.71-90
• /
• 2003

Virtual communities have been suggested to play important roles such as attracting customers, building customer loyalty, and leading to commercial transactions. Little research in marketing has focused on virtual communities in spite of its importance indicated by many practitioners and conceptual studies. More specifically, little research has empirically examined factors of customer participation and its consequences. This research investigate if customers' participation motives in virtual communities affect their sense of community and if sense of community affects customers' loyalty towards and purchase intentions from the website offering the community service. One hundred ninety six questionnaires were collected from individuals who have participated in and have been involved in online activities in various virtual communities. Major results of this research can be summarized as follows. First, participation motives employed significantly affected customers' sense of community and more specifically, perceived ease of use and perceived playfulness had a large influence on the customers' sense of community. Second, customers' sense of community positively affected their loyalty toward the community and more specifically, membership and emotional connection had a large influence on loyalty. Third, customers' sense of community did not affect directly their purchase intentions. Fourth, customers' loyalty toward virtual communities had a significant, positive, although marginal, influence on their purchase intentions.

• Journal of Distribution Science
• /
• v.9 no.3
• /
• pp.47-54
• /
• 2011

This paper presents exploratory research on consumer awareness and attitudesabout organic food, for which consumer demand continues to increase the paper also assesses consumers' organic food distribution channel preferences. By conducting a literature review, a case study has been carried out in order to glean customer behavior, market condition and typesof distribution channels, and development of specialty stores for organic foods. The early research indicates that consumer awareness and customer attitudes toward organic food are mostly positive however, organic food's high price, as well as a lack of organic food stores, cause a negative effect on consumers' purchase intention. Secondly, the U.S. organic food retail channel consists of such mainstream supermarket/grocery stores and leading natural and organic food supermarket chains as Whole Foods, Trader Joe's, and Sunflower Farmers Market. For the current retail distribution of organic food in Korea, off-line stores are composed of direct management stores and franchise chains. Most of the organic food retail distribution operates through the Internet shopping mall, and are commonly located at retail distribution centers as multi-channel, shop-in-shop stores. Moreover, unlike in the U.S., association and consumers' cooperatives (Co-Ops), and such other member-direct retail stores as Hansallim, iCOOP, Nature Dream,and online shopping malls, are all active in Korea. Thirdly, as a result of an analysis of the present state of the organic food retail channel, as well as building a case for organic food specialty stores, the distinctive featuresand rapid growth of such unique organic food stores as Whole Foods Market, or Trader Joe's successful downsizing strategies, as well as Sunflower Farmers Market low-price approach, show steady industry growth. Moreover, as a result of a case studyof such domestic representative organic food specialty stores as "Olga" and "Chorokmaeul," a similar management style to the United States' "Whole Foods Market" and "Trader Joe's," respectively, can be seen. Similar to the U.S. market, Korean organic food markets should also implement active retail distribution opportunities, allowing consumers to select from various diverse and differentiated choices. In order to accomplish this goal, it is necessary to prepare such measures as sustaining reasonable prices, securing various suppliers for unique products,and improving consumer trust through advertisement strategies that are suitable for each company's branding processes.

• The Journal of Industrial Distribution & Business
• /
• v.10 no.10
• /
• pp.35-44
• /
• 2019

Purpose - This study focuses on the continuance intention of O2O fresh agricultural products e-commerce. By literature review, this paper looks through the classical theories which are often applied to study use behavior and continuance intention on the electronic commerce area. Ultimately based on the expectancy theory, Technology acceptance model, success model as well as trust model, a model of the continuance intention of fresh products O2O electronic commerce application is established. Research design, data, and methodology - Among users Chinese consumers have been chosen who have use experience as the research objects. From October 2, 2018 to November 2, 2018, 685 questionnaires in total were collected by the online release and collection. Expect for the negative questionnaires, the remaining 650 pieces of data are statistically analyzed. The collected data were firstly be analyzed by SPSS Ver. 25 on its frequency, reliability and exploratory factors. Then AMOS Ver. 25 is applied to the Confirmatory Factor Analysis, Discriminant Validity and hypothesis testing of the Structural Equation Modeling. Finally, the following research conclusions could be obtained from the hypothesis testing. Results - Firstly, in the extended IS model, quality factor for hypothesis testing, service quality, information quality and delivery quality have obviously present positive influences on satisfaction respectively. Secondly, in the hypothesis testing part of ECM-ISC model and UTAUT model, all hypotheses have presented accepted results. Especially from expectation confirmation to usefulness perception, the influence factor achieves 12.603, In the hypothesis of continuance intention, the influence factor of social influence on continuance intention is 7.748 and also it is the most remarkable one. Conclusions - The results show that the service quality of O2O fresh agricultural products e-commerce has the greatest impact on satisfaction, while the perceived usefulness of consumers has the most significant impact on O2O fresh agricultural products for sustainable use intention. This thesis makes up for the blank of O2O fresh food e-commerce for sustainable use intentions, and provides a theoretical basis for consumers' sustainable use behavior, and practical enlightenment for the sustainable development of O2O fresh agricultural products e-commerce.

• Environmental and Resource Economics Review
• /
• v.30 no.3
• /
• pp.395-433
• /
• 2021

This paper aims to examine the effects of homeownership and residential types on the economic values of urban green spaces. Green open spaces as public goods provide positive externalities that are comprised of pecuniary and technological externalities. Seoul, South Korea, is used as a case study using choice experiments, with split-sample online respondents of 1,000. The study results evidenced that the differentiation between the two types of externalities is imperative for equitable provisions and efficient management of various urban open spaces. There is a positively significant and substantial impact of homeownership for apartment dwellers, ceteris paribus, but not for house dwellers. For apartments, the efficiency loss can be reduced by increasing green spaces up to the critical point where the marginal cost is at equilibrium with tenants' marginal values. For non-apartment houses, it is not homeownership but the monthly household income that has a significant impact on the amenity value. In general, public benefits from green spaces are equivalent to 16% to 33% of the current residential prices on average for a view or access. Different residential types do not cause a significant impact on the access values. Residential profiles for green spaces were developed, together with tailor-made policy suggestions.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.238-249
• /
• 2021

This research aims to present effective influencer marketing strategies against a heavy blow in Korean influencer marketing industry because of the paid advertisement controversy and the reinforcement of regulations for online advertisement. By investigating the effects of influencer reputation, which is composed of communication skills, influence, authenticity and professionalism on marketing effect, as well as the mediating effect of parasocial relationship, the study provides some implications for influencer selecting. The effect of economic interests is examined under 4 experimental conditions of paid advertisements, brand collaboration, brand gifts and organic review to figure out how to arrange an appropriate sponsorship plan. According to results of PLS structural equation analysis, it shows that the influence and authenticity of an influencer have a significant positive effect on marketing effect and the mediating effect of parasocial relationship is partially proved. It seems that the effect of influencer reputation on marketing effect is significantly differentiated in different contexts, which confirms the moderating effect of economic interest. Distinguish from previous studies, this study focuses on types of economic interest rather than a simple comparison between sponsorship disclosure versus no disclosure and makes contributions to expanding reputation research. Meanwhile, findings of this study could give some practical implications for marketing practitioners in planning influencer marketing.

• Korea Trade Review
• /
• v.43 no.5
• /
• pp.203-232
• /
• 2018

Gobizkorea is an online B2B matching platform operated by the Small & Medium Business Corporation. Gobizkorea provides an opportunity for resource-poor SMEs to promote their products and exploit new market opportunities at low cost. The successful operation of Gobizkorea will contribute to the increased exports of Korean SMEs. Accordingly, the present study examined determinants of foreign buyer loyalty toward Gobizkorea.com focusing on country image, e-service quality, and satisfaction. One hundred two survey questionnaires were collected from U.S. buyers registered with Gobizkorea.com. Exploratory and confirmatory factor analysis confirmed three dimensions of e-service quality including information & efficiency, reliability & privacy, and prompt communication & delivery. The path analysis results showed that the country image of Korea significantly and positively affected these three dimensions of e-service quality. Information & efficiency and reliability & privacy positively influenced buyer satisfaction. Reliability & privacy and satisfaction had a positive impact on buyer loyalty. This study enhances the understanding of the foreign buyers use of the domestic e-market platform by examining of determinants of U.S. buyer loyalty toward Gobizkorea.

• Korea Trade Review
• /
• v.42 no.2
• /
• pp.251-276
• /
• 2017

The utilization of Digital and Social Network has become be a key success factor in business operations as information technologies evolve rapidly. This study is to identity the relationship between ICT & digital utilization, global orientation and export marketing capability in Korean SMEs. Survey data of Korean SMEs in south regional areas was collected and analyzed for empirical hypothesis test by PLS structural equation method. The key findings are as follows. First, ICT utilization such as SNS, homepage and online portal does not impact directly on export marketing capability. It means that SMEs would not still take advantage of utilization of social network availability. Second, ICT utilization has positive influences on global market orientation and global network orientation. Finally, both global market orientation and network have significant impacts on export marketing capability. In conclusion, global orientation has full-mediation effects on relationship between ICT capability and global marketing. This study provides evidences and some practical insights that digital utilization have indirect influences on global marketing through global markets and network orientation in Korean SMEs. In information technology era, ICT utilization will play an important role in the process of SMEs' internationalization. Therefore, for sustainable growth and survival SMEs should manage and intensify ICT capability more strategically as one of core competence. The value of ICT capability in SMEs would be depended on their strategic perspectives toward digitalization. Additional empirical research about digital capability based on larger sample will be needed.