• 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 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.

• 한국노년학
• /
• v.37 no.2
• /
• pp.309-328
• /
• 2017

The purpose of this study is to develop a perceived elderly stigma scale for intergenerational research and practice. Although negative stereotypes on elderly population have worsened physical and psychological health of older people, there has been a lack of systematic efforts to measure and monitor stigmatic perception and behavior of younger generation on elderly people. We initially constructed a 34-item perceived elderly stigma scale, by integrating the processes of literature review and exploratory item generation. After confirming the face validity of the scale, a 31-item perceived elderly stigma scale was tested with 252 adults recruited from an online research panel. The result of an exploratory factor analysis suggests a 5-factor solution with 28 items: ability, personality, appearance, authoritarian dependancy, and family-obsession. The convergent/discriminant validity was confirmed by examining its relationships with ageism, elderly discrimination, attitude toward elderly, and respect for elderly. After a series of refinement and empirical tests, the perceived elderly stigma scale would contribute to understanding the current state of elderly discrimination in our society and to develop necessary policies and promotion strategies to eliminate intergenerational conflicts.

• Information Systems Review
• /
• v.22 no.3
• /
• pp.143-156
• /
• 2020

Price promotion is one of the most frequently marketing strategies with a long history. According to various studies, the effect of price promotion is controversial. Some studies have argued that price promotion has a positive effect, while others have found that it has no effect or rather has a negative effect. This study aims to examine the effect of price promotion in a subscription-based service. First, we check the effect of price promotion on the repurchase of the consumer. And we investigate how this effect varies depending on the characteristics of the consumer. Using the data from one of the music streaming service in South Korea, the effect of consumers' price promotion experience, demographic characteristics, and behavioral characteristics on their repurchase is analyzed through logistic regression analysis. As a result of the study, it is found that consumers' experience of price promotion has a positive effect on repurchase. In addition, the positive effect of price promotion is relatively greater in younger and female consumers. This study has implications in that it not only confirmed the positive effect of price promotion in a subscription-based environment but also empirically confirmed that the characteristics of consumers should be considered when performing price promotion.

• Information Systems Review
• /
• v.24 no.2
• /
• pp.1-20
• /
• 2022

Researchers are making contradictory claims through the concept of superstars and long tails about how the development of IT technology affects demand distribution. Unlike previous studies that focused on changes in demand from a macro point of view, this study explored whether the relationship between a company's marketing activities and consumer response differs depending on the product location (i.e., superstar vs. long tail) from a micro point of view. Based on the marketing mix framework, hypotheses were developed based on the relevant literature. In the case of empirical analysis, 2,835 daily data from 63 Korean films were tested using the quantile regression method. As a result of the analysis, it was found that the influence of marketing mix factors on sales varies depending on the location of the product. Specifically, the appeal breadth of the film and the effect of owned media are enhanced in superstar products, and the effect of acquisition media in long-tail products is enhanced and the negative effects of competition are mitigated. Unlike previous studies that focused on macroscopic changes in demand distribution, this study suggested marketing activities suitable for practitioners through microscopic analysis.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.1-22
• /
• 2021

Aspect Based Sentiment Analysis (ABSA), which analyzes sentiment based on aspects that appear in the text, is drawing attention because it can be used in various business industries. ABSA is a study that analyzes sentiment by aspects for multiple aspects that a text has. It is being studied in various forms depending on the purpose, such as analyzing all targets or just aspects and sentiments. Here, the aspect refers to the property of a target, and the target refers to the text that causes the sentiment. For example, for restaurant reviews, you could set the aspect into food taste, food price, quality of service, mood of the restaurant, etc. Also, if there is a review that says, "The pasta was delicious, but the salad was not," the words "steak" and "salad," which are directly mentioned in the sentence, become the "target." So far, in ABSA, most studies have analyzed sentiment only based on aspects or targets. However, even with the same aspects or targets, sentiment analysis may be inaccurate. Instances would be when aspects or sentiment are divided or when sentiment exists without a target. For example, sentences like, "Pizza and the salad were good, but the steak was disappointing." Although the aspect of this sentence is limited to "food," conflicting sentiments coexist. In addition, in the case of sentences such as "Shrimp was delicious, but the price was extravagant," although the target here is "shrimp," there are opposite sentiments coexisting that are dependent on the aspect. Finally, in sentences like "The food arrived too late and is cold now." there is no target (NULL), but it transmits a negative sentiment toward the aspect "service." Like this, failure to consider both aspects and targets - when sentiment or aspect is divided or when sentiment exists without a target - creates a dual dependency problem. To address this problem, this research analyzes sentiment by considering both aspects and targets (Target-Aspect-Sentiment Detection, hereby TASD). This study detected the limitations of existing research in the field of TASD: local contexts are not fully captured, and the number of epochs and batch size dramatically lowers the F1-score. The current model excels in spotting overall context and relations between each word. However, it struggles with phrases in the local context and is relatively slow when learning. Therefore, this study tries to improve the model's performance. To achieve the objective of this research, we additionally used auxiliary loss in aspect-sentiment classification by constructing CNN(Convolutional Neural Network) layers parallel to existing models. If existing models have analyzed aspect-sentiment through BERT encoding, Pooler, and Linear layers, this research added CNN layer-adaptive average pooling to existing models, and learning was progressed by adding additional loss values for aspect-sentiment to existing loss. In other words, when learning, the auxiliary loss, computed through CNN layers, allowed the local context to be captured more fitted. After learning, the model is designed to do aspect-sentiment analysis through the existing method. To evaluate the performance of this model, two datasets, SemEval-2015 task 12 and SemEval-2016 task 5, were used and the f1-score increased compared to the existing models. When the batch was 8 and epoch was 5, the difference was largest between the F1-score of existing models and this study with 29 and 45, respectively. Even when batch and epoch were adjusted, the F1-scores were higher than the existing models. It can be said that even when the batch and epoch numbers were small, they can be learned effectively compared to the existing models. Therefore, it can be useful in situations where resources are limited. Through this study, aspect-based sentiments can be more accurately analyzed. Through various uses in business, such as development or establishing marketing strategies, both consumers and sellers will be able to make efficient decisions. In addition, it is believed that the model can be fully learned and utilized by small businesses, those that do not have much data, given that they use a pre-training model and recorded a relatively high F1-score even with limited resources.