• Information Systems Review
• /
• v.23 no.3
• /
• pp.51-75
• /
• 2021

Global e-commerce websites offer personalized recommendation services to gain sustainable competitiveness. Existing studies have offered personalized recommendation services using quantitative preferences such as ratings. However, offering personalized recommendation services using only quantitative data has raised the problem of decreasing recommendation performance. For example, a user gave a five-star rating but wrote a review that the user was unsatisfied with hotel service and cleanliness. In such cases, has problems where quantitative and qualitative preferences are inconsistent. Recently, a growing number of studies have considered review data simultaneously to improve the limitations of existing personalized recommendation service studies. Therefore, in this study, we identify review and rating mismatches and build a new user profile to offer personalized recommendation services. To this end, we use deep learning algorithms such as CNN, LSTM, CNN + LSTM, which have been widely used in sentiment analysis studies. And extract sentiment features from reviews and compare with quantitative preferences. To evaluate the performance of the proposed methodology in this study, we collect user preference information using real-world hotel data from the world's largest travel platform TripAdvisor. Experiments show that the proposed methodology in this study outperforms the existing other methodologies, using only existing quantitative preferences.

• Journal of Distribution Research
• /
• v.16 no.1
• /
• pp.95-115
• /
• 2011

Food service is the major part of franchise business in Korea, accounting for 69.9% of the brands in the market. As the food service industry becomes mature, many franchisees have struggled to survive in the market. In general, consumers have higher levels of expectation toward service quality of franchised outlets compared that of (non-franchised) independent ones. They also tend to believe that franchisees deliver standardized service at the uniform food price, regardless of their locations. Such beliefs seem to be important reasons that consumers prefer franchised outlets to independent ones. Nevertheless, few studies examined the impact of qualify features of franchisees on customer satisfaction so far. To this end, this study examined the characteristics of various quality features of franchisees in the food service industry, regarding their relationship with customer satisfaction and dissatisfaction. The quality perception of heavy-users was also compared with that of light-users in order to find insights for developing differentiated marketing strategy for the two segments. Customer satisfaction has been understood as a one-dimensional construct while there are recent studies that insist two-dimensional nature of the construct. In this regard, Kano et al. (1984) suggested to categorize quality features of a product or service into five types, based on their relation to customer satisfaction and dissatisfaction: Must-be quality, Attractive quality, One-dimensional quality, Indifferent quality, and Reverse quality. According to the Kano model, customers are more dissatisfied when Must-be quality(M) are not fulfilled, but their satisfaction does not arise above neutral no matter how fully the quality fulfilled. In comparison, customers are more satisfied with a full provision of Attactive quality(A) but manage to accept its dysfunction. One-dimensional quality(O) results in satisfaction when fulfilled and dissatisfaction when not fulfilled. For Indifferent quality(I), its presence or absence influences neither customer satisfaction nor dissatisfaction. Lastly, Reverse quality(R) refers to the features whose high degree of achievement results in customer dissatisfaction rather than satisfaction. Meanwhile, the basic guidelines of the Kano model have a limitation in that the quality type of each feature is simply determined by calculating the mode statistics. In order to overcome such limitation, the relative importance of each feature on customer satisfaction (Better value; b) and dissatisfaction (Worse value; w) were calculated following the formulas below (Timko, 1993). The Better value indicates how much customer satisfaction is increased by providing the quality feature in question. In contrast, the Worse value indicates how much customer dissatisfaction is decreased by providing the quality feature. Better = (A + O)/(A+O+M+I) Worse = (O+M)/(A+O+M+I)(-1) An on-line survey was performed in order to understand the nature of quality features of franchisees in the food service industry by applying the Kano Model. A total of twenty quality features (refer to the Table 2) were identified as the result of literature review in franchise business and a pre-test with fifty college students in Seoul. The potential respondents of our main survey was limited to the customers who have visited more than two restaurants/stores of the same franchise brand. Survey invitation e-mails were sent out to the panels of a market research company and a total of 257 responses were used for analysis. Following the guidelines of Kano model, each of the twenty quality features was classified into one of the five types based on customers' responses to a set of questions: "(1) how do you feel if the following quality feature is fulfilled in the franchise restaurant that you visit," and "(2) how do you feel if the following quality feature is not fulfilled in the franchise restaurant that you visit." The analyses revealed that customers' dissatisfaction with franchisees is commonly associated with the poor level of cleanliness of the store (w=-0.872), kindness of the staffs(w=-0.890), conveniences such as parking lot and restroom(w=-0.669), and expertise of the staffs(w=-0.492). Such quality features were categorized as Must-be quality in this study. While standardization or uniformity across franchisees has been emphasized in franchise business, this study found that consumers are interested only in uniformity of price across franchisees(w=-0.608), but not interested in standardizations of menu items, interior designs, customer service procedures, and food tastes. Customers appeared to be more satisfied when the franchise brand has promotional events such as giveaways(b=0.767), good accessibility(b=0.699), customer loyalty programs(b=0.659), award winning history(b=0.641), and outlets in the overseas market(b=0.506). The results are summarized in a matrix form in Table 1. Better(b) and Worse(w) index indicate relative importance of each quality feature on customer satisfaction and dissatisfaction, respectively. Meanwhile, there were differences in perceiving the quality features between light users and heavy users of any specific franchise brand in the food service industry. Expertise of the staffs was labeled as Must-be quality for heavy users but Indifferent quality for light users. Light users seemed indifferent to overseas expansion of the brand and offering new menu items on a regular basis, while heavy users appeared to perceive them as Attractive quality. Such difference may come from their different levels of involvement when they eat out. The results are shown in Table 2. The findings of this study help practitioners understand the quality features they need to focus on to strengthen the competitive power in the food service market. Above all, removing the factors that cause customer dissatisfaction seems to be the most critical for franchisees. To retain loyal customers of the franchise brand, it is also recommended for franchisor to invest resources in the development of new menu items as well as training programs for the staffs. Lastly, if resources allow, promotional events, loyalty programs, overseas expansion, award-winning history can be considered as tools for attracting more customers to the business.

• 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 Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.97-117
• /
• 2020

Product evaluation criteria is an indicator describing attributes or values of products, which enable users or manufacturers measure and understand the products. When companies analyze their products or compare them with competitors, appropriate criteria must be selected for objective evaluation. The criteria should show the features of products that consumers considered when they purchased, used and evaluated the products. However, current evaluation criteria do not reflect different consumers' opinion from product to product. Previous studies tried to used online reviews from e-commerce sites that reflect consumer opinions to extract the features and topics of products and use them as evaluation criteria. However, there is still a limit that they produce irrelevant criteria to products due to extracted or improper words are not refined. To overcome this limitation, this research suggests LDA-k-NN model which extracts possible criteria words from online reviews by using LDA and refines them with k-nearest neighbor. Proposed approach starts with preparation phase, which is constructed with 6 steps. At first, it collects review data from e-commerce websites. Most e-commerce websites classify their selling items by high-level, middle-level, and low-level categories. Review data for preparation phase are gathered from each middle-level category and collapsed later, which is to present single high-level category. Next, nouns, adjectives, adverbs, and verbs are extracted from reviews by getting part of speech information using morpheme analysis module. After preprocessing, words per each topic from review are shown with LDA and only nouns in topic words are chosen as potential words for criteria. Then, words are tagged based on possibility of criteria for each middle-level category. Next, every tagged word is vectorized by pre-trained word embedding model. Finally, k-nearest neighbor case-based approach is used to classify each word with tags. After setting up preparation phase, criteria extraction phase is conducted with low-level categories. This phase starts with crawling reviews in the corresponding low-level category. Same preprocessing as preparation phase is conducted using morpheme analysis module and LDA. Possible criteria words are extracted by getting nouns from the data and vectorized by pre-trained word embedding model. Finally, evaluation criteria are extracted by refining possible criteria words using k-nearest neighbor approach and reference proportion of each word in the words set. To evaluate the performance of the proposed model, an experiment was conducted with review on '11st', one of the biggest e-commerce companies in Korea. Review data were from 'Electronics/Digital' section, one of high-level categories in 11st. For performance evaluation of suggested model, three other models were used for comparing with the suggested model; actual criteria of 11st, a model that extracts nouns by morpheme analysis module and refines them according to word frequency, and a model that extracts nouns from LDA topics and refines them by word frequency. The performance evaluation was set to predict evaluation criteria of 10 low-level categories with the suggested model and 3 models above. Criteria words extracted from each model were combined into a single words set and it was used for survey questionnaires. In the survey, respondents chose every item they consider as appropriate criteria for each category. Each model got its score when chosen words were extracted from that model. The suggested model had higher scores than other models in 8 out of 10 low-level categories. By conducting paired t-tests on scores of each model, we confirmed that the suggested model shows better performance in 26 tests out of 30. In addition, the suggested model was the best model in terms of accuracy. This research proposes evaluation criteria extracting method that combines topic extraction using LDA and refinement with k-nearest neighbor approach. This method overcomes the limits of previous dictionary-based models and frequency-based refinement models. This study can contribute to improve review analysis for deriving business insights in e-commerce market.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.27 no.3
• /
• pp.248-258
• /
• 2005

The challenging task of classifying the fibro-osseous(FO) lesions has been previously attempted but only in the past 15 years has the entire spectrum of diversity been appreciated. For the clinicians, it is hard to clearly diagnose the lesions before operations. The purpose of this study was to review the literature about fibro-osseous lesions of the jaws and to analyse our clinical cases. As the results of the review of clinical features, radiography and histopathologic findings of sixteen cases of fibro-osseous lesions, we could elucidate diagnostic aids for treatment of benign FO lesion in jaws. Six patients involving fibrous dysplasia complained the facial swelling and facial asymmetry. The radiographic features of the lesions showed ground-glass radiopacity mostly and the histologic findings showed typically Chinese character-shaped trabeculae without osteoblastic rimming in the fibrous stroma. Six patients with ossifying fibroma were notified as swollen buccal cheek state. Their radiographic findings showed cortical expanded radiolucent lesion with sclerotic defined border, which was contrast to the normal adjacent bone. The lesions showed variant radiolucent lesions. Histological findings were revealed as cellular fibrous stroma with woven bones, variable patterns of calcifications. Three patients with cemental dysplasia didn't have specific complaints. Well circumscribed radiopaque lesions on mandibular molar area were observed. Cementum-like ossicles with fibrous stroma were found on microscopic findings. A osteoblastoma case with jaw pain was found. The radiographic feature was a mottled, dense radiopacity with osteolytic border on mandibular molar area. Under microscopy trabecule of osteoid with vascular network were predominantly found. Numerous osteoblast cells with woven bone were found. These clinical, radiographic and microscopic findings of benign fibrous-osseous lesions would suggest diagnostic criteria for each entity of FO lesions.

• Ecology and Resilient Infrastructure
• /
• v.2 no.2
• /
• pp.118-127
• /
• 2015

Because streams have a great diversity of morphological features according to their reaches, it is necessary to classify the types of streams in order to assess their characteristics of channel. In addition, a quantitative assessment system for channel characteristics should be reflected in the stream type properties. Therefore, this study compares two stream classification system (Rosgen's and Yamamoto's) to review their applicability on Korean streams, and the two classification systems were applied on the Nam River. In order for the mean bed slope and the longitudinal connectivity of the provincial and national streams to be reflected in the assessment system of channel characteristics, the Yamamoto system is considered highly adaptable in the stream geomorphology side. In addition, it has been found the Rosgen system has a low correlation of bed slope compared to the Yamamoto system in the view of bed materials. On the other hand, the Yamamoto system was found to be capable of reflecting sediment sorting (hydraulic sorting) of the bed slope. According to the results obtained at the Nam River, the Rosgen system could not classify a type of stream by relationship between bed material and bed slope, but the Yamamoto system can verify the correlation of stream type. However, further review is needed with respect to the applicability of natural rivers. Three types of stream that can be applied to the assessment system of channel characteristics were proposed.

• The Journal of Engineering Geology
• /
• v.33 no.4
• /
• pp.725-736
• /
• 2023

The compliance of deep geological disposal facilities for high-level radioactive waste with safety objectives requires consideration of uncertainties owing to temporal changes in the disposal system. A comprehensive review and analysis of the characteristics of this evolution should be undertaken to identify the effects on multiple barriers and the biosphere. We analyzed the evolution of the buffer, backfill, plug, and closure regions during the early phase of the post-closure period as part of a long-term performance assessment for an operating license application for a deep geological repository in Finland. Degradation mechanisms generally expected in engineered barriers were considered, and long-term evolution features were examined for use in performance assessments. The importance of evolution features was classified into six categories based on the design of the Finnish case. Results are expected to be useful as a technical basis for performance and safety assessment in developing the Korean deep geological disposal system for high-level radioactive waste. However, for a more detailed review and evaluation of each feature, it is necessary to obtain data for the final disposal site and facility-specific design, and to assess its impact in advance.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.1-19
• /
• 2022

Social media-based communication has become crucial part of our personal and official lives. Therefore, it is no surprise that social media sentiment analysis has emerged an important way of detecting potential customers' sentiment trends for all kinds of companies. However, social media sentiment analysis suffers from huge number of sentiment features obtained in the process of conducting the sentiment analysis. In this sense, this study proposes a novel method by using Bayesian Network. In this model MBFS (Markov Blanket-based Feature Selection) is used to reduce the number of sentiment features. To show the validity of our proposed model, we utilized online review data from Yelp, a famous social media about restaurant, bars, beauty salons evaluation and recommendation. We used a number of benchmarking feature selection methods like correlation-based feature selection, information gain, and gain ratio. A number of machine learning classifiers were also used for our validation tasks, like TAN, NBN, Sons & Spouses BN (Bayesian Network), Augmented Markov Blanket. Furthermore, we conducted Bayesian Network-based what-if analysis to see how the knowledge map between target node and related explanatory nodes could yield meaningful glimpse into what is going on in sentiments underlying the target dataset.

• THE INTERNATIONAL COMMERCE & LAW REVIEW
• /
• v.39
• /
• pp.59-85
• /
• 2008

An independent bank guarantee(aka an independent guarantee) is provided as an security on a principal obligor's performance of his obligation, and a guarantor should pay the guaranteed amount only upon a beneficiary's written demand. A standby letter of credit has been used in the United States, since it was construed that a bank should not issue a guarantee. There was wide misunderstanding that a standby letter of credit differs from an independent bank guarantee. However, a standby letter of credit is the same security as an independent bank guarantee, and in international business a standby letter of credit is not differentiated from a independent bank guarantee. An independent bank guarantee are independent from the underlying contract, unconditional, and irrevocable. And a guarantor should pay upon written demand without proving a principal obligor breaches the underlying contract. These features of an independent bank guarantee has been abused in international transactions. Thus it has been proposed that some exceptions to the features of an independent bank guarantee should be allowed. United Nations Convention on Independent Guarantees and Standby Letter of Credit(1995) stipulates some exceptions to payment obligation. Export bond insurance, a part of export insurances, operated by the Korea Export Insurance Corporation under the Export Insurance Act, is used as a security for unfair calling by a beneficiary under an independent bank guarantee. Most of the export subsides by the government are prohibited under WTO's Agreement on Subsidies and Countervailing Measures. However, as export insurance is allowed under the WTO, it operates a significant role in enhancing the export. In the event that export bond insurance is provided for a guarantor, an obligor who is subject to recourse by a guarantor, can be exempt from the recourse in case of unfair calling. The Korea Export Insurance Corporation, an insurer, bears unfair calling risk by a beneficiary. Generally it is understood that a demand shall be made before the expiry of an independent bank guarantee. However this is not absolutely true, it shall be decided by URDG, ISP98, the governing law.

• Journal of Digital Convergence
• /
• v.14 no.5
• /
• pp.385-390
• /
• 2016

Cultural industry consists of a national own value and life style known as the cultural characteristics, and it has decorative and practical features so it covers necessaries and items of personal preference that the public use. Craft Culture Industry means the craft industry where goods with cultural features of traditional art are made based on specific region and surroundings, which is a series of process in which inherent traditional and cultural elements are produced, representing cultural industry. With the review on issues and solutions in each section of Craft Culture Industry, it would help solve the problem when developing Craft Culture Industry. This study examines the popularity and status of the craft cultural products and figures out the current situation of the domestic cultural industry and the development plan.