• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.71-88
• /
• 2017

Language models were originally developed for speech recognition and language processing. Using a set of example sentences, a language model predicts the next word or character based on sequential input data. N-gram models have been widely used but this model cannot model the correlation between the input units efficiently since it is a probabilistic model which are based on the frequency of each unit in the training set. Recently, as the deep learning algorithm has been developed, a recurrent neural network (RNN) model and a long short-term memory (LSTM) model have been widely used for the neural language model (Ahn, 2016; Kim et al., 2016; Lee et al., 2016). These models can reflect dependency between the objects that are entered sequentially into the model (Gers and Schmidhuber, 2001; Mikolov et al., 2010; Sundermeyer et al., 2012). In order to learning the neural language model, texts need to be decomposed into words or morphemes. Since, however, a training set of sentences includes a huge number of words or morphemes in general, the size of dictionary is very large and so it increases model complexity. In addition, word-level or morpheme-level models are able to generate vocabularies only which are contained in the training set. Furthermore, with highly morphological languages such as Turkish, Hungarian, Russian, Finnish or Korean, morpheme analyzers have more chance to cause errors in decomposition process (Lankinen et al., 2016). Therefore, this paper proposes a phoneme-level language model for Korean language based on LSTM models. A phoneme such as a vowel or a consonant is the smallest unit that comprises Korean texts. We construct the language model using three or four LSTM layers. Each model was trained using Stochastic Gradient Algorithm and more advanced optimization algorithms such as Adagrad, RMSprop, Adadelta, Adam, Adamax, and Nadam. Simulation study was done with Old Testament texts using a deep learning package Keras based the Theano. After pre-processing the texts, the dataset included 74 of unique characters including vowels, consonants, and punctuation marks. Then we constructed an input vector with 20 consecutive characters and an output with a following 21st character. Finally, total 1,023,411 sets of input-output vectors were included in the dataset and we divided them into training, validation, testsets with proportion 70:15:15. All the simulation were conducted on a system equipped with an Intel Xeon CPU (16 cores) and a NVIDIA GeForce GTX 1080 GPU. We compared the loss function evaluated for the validation set, the perplexity evaluated for the test set, and the time to be taken for training each model. As a result, all the optimization algorithms but the stochastic gradient algorithm showed similar validation loss and perplexity, which are clearly superior to those of the stochastic gradient algorithm. The stochastic gradient algorithm took the longest time to be trained for both 3- and 4-LSTM models. On average, the 4-LSTM layer model took 69% longer training time than the 3-LSTM layer model. However, the validation loss and perplexity were not improved significantly or became even worse for specific conditions. On the other hand, when comparing the automatically generated sentences, the 4-LSTM layer model tended to generate the sentences which are closer to the natural language than the 3-LSTM model. Although there were slight differences in the completeness of the generated sentences between the models, the sentence generation performance was quite satisfactory in any simulation conditions: they generated only legitimate Korean letters and the use of postposition and the conjugation of verbs were almost perfect in the sense of grammar. The results of this study are expected to be widely used for the processing of Korean language in the field of language processing and speech recognition, which are the basis of artificial intelligence systems.

• The Journal of Small Business Innovation
• /
• v.19 no.4
• /
• pp.19-39
• /
• 2016

With increasing adoption of smart products and complexity, companies have shifted their strategies from stand alone and competitive strategies to business ecosystem oriented and cooperative strategies. The win-win growth of business refers to corporate efforts undertaken by companies to pursue the healthiness of business between conglomerates and partnering companies such as suppliers for mutual prosperity and a long-term corporate soundness based on their business ecosystem and cooperative strategies. This study is designed to validate a theoretical proposition that the win-win growth strategy of Samsung Electronics and cooperative efforts among companies can create a healthy business ecosystem, based on results of case studies and surveys. In this study, a level of global market access of small and mid-sized companies is adopted as the key achievement index. The foreign market entry is considered as one of vulnerabilities in the ecosystem of small and mid-sized enterprises (SMEs). For SMEs, the global market access based on the research and development (R&D) has become the critical component in the process of transforming them into global small giants. The results of case studies and surveys are analyzed mainly based on a model of a virtuous cycle of Creativity, Opportunity, Productivity, and Proactivity (the COPP model) that features the characteristics of the healthiness of a business ecosystem. In the COPP model, a virtuous circle of profits made by the first three factors and Proactivity, which is the manifestation of entrepreneurship that proactively invests and reacts to the changing business environment of the future, enhances the healthiness of a given business ecosystem. With the application of the COPP model, this study finds major achievements of the win-win growth of Samsung Electronics as follows. First, Opportunity plays a role as a parameter in the relations of Creativity, Productivity, and creating profits. Namely, as companies export more (with more Opportunity), they are more likely to link their R&D efforts to Productivity and profitability. However, companies that do not export tend to fail to link their R&D investment to profitability. Second, this study finds that companies with huge investment on R&D for the future, which is the result of Proactivity, tend to hold a large number of patents (Creativity). And companies with significant numbers of patents tend to be large exporters as well (Opportunity), and companies with a large amount of exports tend to record high profitability (Productivity and profitability), and thus forms the virtuous cycle of the COPP model. In addition, to access global markets for sustainable growth, SMEs need to build and strengthen their competitiveness. This study concludes that companies with a high level of proactivity to invest for the future can create a virtuous circle of Creativity, Opportunity, Productivity, and Proactivity, thereby providing a strategic implication that SMEs should invest time and resources in forming such a virtuous cycle which is a sure way for the SMEs to grow into global small giants.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.109-125
• /
• 2020

The Ministry of National Defense is pushing for the Defense Acquisition Program to build strong defense capabilities, and it spends more than 10 trillion won annually on defense improvement. As the Defense Acquisition Program is directly related to the security of the nation as well as the lives and property of the people, it must be carried out very transparently and efficiently by experts. However, the excessive diversification of laws and regulations related to the Defense Acquisition Program has made it challenging for many working-level officials to carry out the Defense Acquisition Program smoothly. It is even known that many people realize that there are related regulations that they were unaware of until they push ahead with their work. In addition, the statutory statements related to the Defense Acquisition Program have the tendency to cause serious issues even if only a single expression is wrong within the sentence. Despite this, efforts to establish a sentence comparison system to correct this issue in real time have been minimal. Therefore, this paper tries to propose a "Comparison System between the Statement of Military Reports and Related Laws" implementation plan that uses the Siamese Network-based artificial neural network, a model in the field of natural language processing (NLP), to observe the similarity between sentences that are likely to appear in the Defense Acquisition Program related documents and those from related statutory provisions to determine and classify the risk of illegality and to make users aware of the consequences. Various artificial neural network models (Bi-LSTM, Self-Attention, D_Bi-LSTM) were studied using 3,442 pairs of "Original Sentence"(described in actual statutes) and "Edited Sentence"(edited sentences derived from "Original Sentence"). Among many Defense Acquisition Program related statutes, DEFENSE ACQUISITION PROGRAM ACT, ENFORCEMENT RULE OF THE DEFENSE ACQUISITION PROGRAM ACT, and ENFORCEMENT DECREE OF THE DEFENSE ACQUISITION PROGRAM ACT were selected. Furthermore, "Original Sentence" has the 83 provisions that actually appear in the Act. "Original Sentence" has the main 83 clauses most accessible to working-level officials in their work. "Edited Sentence" is comprised of 30 to 50 similar sentences that are likely to appear modified in the county report for each clause("Original Sentence"). During the creation of the edited sentences, the original sentences were modified using 12 certain rules, and these sentences were produced in proportion to the number of such rules, as it was the case for the original sentences. After conducting 1 : 1 sentence similarity performance evaluation experiments, it was possible to classify each "Edited Sentence" as legal or illegal with considerable accuracy. In addition, the "Edited Sentence" dataset used to train the neural network models contains a variety of actual statutory statements("Original Sentence"), which are characterized by the 12 rules. On the other hand, the models are not able to effectively classify other sentences, which appear in actual military reports, when only the "Original Sentence" and "Edited Sentence" dataset have been fed to them. The dataset is not ample enough for the model to recognize other incoming new sentences. Hence, the performance of the model was reassessed by writing an additional 120 new sentences that have better resemblance to those in the actual military report and still have association with the original sentences. Thereafter, we were able to check that the models' performances surpassed a certain level even when they were trained merely with "Original Sentence" and "Edited Sentence" data. If sufficient model learning is achieved through the improvement and expansion of the full set of learning data with the addition of the actual report appearance sentences, the models will be able to better classify other sentences coming from military reports as legal or illegal. Based on the experimental results, this study confirms the possibility and value of building "Real-Time Automated Comparison System Between Military Documents and Related Laws". The research conducted in this experiment can verify which specific clause, of several that appear in related law clause is most similar to the sentence that appears in the Defense Acquisition Program-related military reports. This helps determine whether the contents in the military report sentences are at the risk of illegality when they are compared with those in the law clauses.

• 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.

• Asia Marketing Journal
• /
• v.14 no.1
• /
• pp.131-157
• /
• 2012

Despite the voluminous research on switching barriers, the notion that they can generate negative responses has not been investigated. Further, a critical question is what determines the strength of such negative responses. To address this question, the classic theory of psychological reactance is briefly reviewed, and the idea of switching barrier is advanced. This study attempts to suggest a model on the negative effects of switching- frustrated situation, based on the studies on psychological reactance. According to psychological reactance theory(Brehm 1966), whenever a freedom is threatened or removed, individuals are motivated, at least temporarily, to restore their freedom. For example, if individuals think they are free to engage in behaviors .v, y, or z, then threatening their freedom to engage in x would cause psychological reactance. This reactance could be reduced by an increase in the perceived attractiveness of engaging in, the threatened behavior(Kivetz 2005). This investigation seeks to extend existing switching barrier research in three important ways. First, while the past research has emphasized only positive role of switching barrier, this study address negative role of it by applying psychological reactance theory. Second, to find negative results of switching barrier, I suggest negative psychological response including regret to the past choice, resentment to the present provider, and strong desire to the alternative provider. Third, I suggest the perceived severity of the switching barriers, the attractiveness of the alternative as switching-frustrated situation which can lead to negative results. And, in addition to these relationships, I added moderated effects of perceived justice for better explanation. So this study includes the following hypotheses. H1-1 ~ H1-3: The attractiveness of the alternative has a positive effect regret to the past choice (h1-1), resentment to the present provider (h1-2), and strong desire to the alternative provider (h1-3). H2-1 ~ H2-3 : The perceived severity of the switching barrier has a positive effect regret to the past choice (h2-1), resentment to the present provider (h2-2), and strong desire to the alternative provider (h2-3). H3-1 ~ H3-3 : The positive relationships between the attractiveness of the alternative and consumer' negative responses will be stronger at low level of perceived justice than at high level of perceived justice. H4-1 ~ H4-3 : The positive relationships between the perceived severity of the switching barrier and consumer' negative responses will be stronger at low level of perceived justice than at high level of perceived justice. Survey research is employed to test hypotheses involving perceived severity of the switching barrier(Hess 2008), attractiveness of the alternative(Anderson and Narus 1990; Ohanian 1990),regret(Glovich and Medvec 1995), resentment, strong desire(Alcohol Urge Questionaire: Bohn et al. 1995), perceived justice(Bies and Moag 1986; Clemmer 1993; Lind and Tyler 1998). Previous researches, such as reactance theory, emotion and service failure, have been referenced to measure constructs. All items were measured on a 7-point Likert scale ranging from "strongly disagree" to "strongly agree". We collected data involving various service field, and used 249 respondents to analyze these data using the moderated regression. The results of our analysis suggest, as expected, that the perceived severity of the switching barrier had positive effects on regret to the past choice(b = .197, p< .01), resentment to the present provider(b = .214, p< .01), and strong desire to the alternative provider(b = .254, p< .001). And the attractiveness of the alternative had positive effects on regret to the past choice(b = .353, p<.001), resentment to the present provider(b = .174, p< .01), and strong desire to the alternative provider(b = .265, p< .001). However, our findings indicate perceived justice partly moderates relationship between switching-frustrated situation and psychological negative response. The study has brought to light a number of insights between switching barriers and consumer' negative responses that have been subject to little prior research. In particular, this study adds to the existing understanding of the psychological responses to switching barriers in switching- frustrated situation. This research therefore has significance to marketers for strategic marketing programs, particularly in terms of customer retention and switching barrier strategies. Since consumers could exhibit negative responses to switching barrier, companies would be able to lose their customer when they thoughtlessly use switching barrier for remaining customer. Although the study has these contributions, there are several limitations including unsupported hypotheses and research method. So, we need to make up for these limitations in the future researches.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.227-252
• /
• 2018

The evolution of instant communication has mirrored the development of the Internet and messenger applications are among the most representative manifestations of instant communication technologies. In messenger applications, senders use emoticons to supplement the emotions conveyed in the text of their messages. The fact that communication via messenger applications is not face-to-face makes it difficult for senders to communicate their emotions to message recipients. Emoticons have long been used as symbols that indicate the moods of speakers. However, at present, emoticon-use is evolving into a means of conveying the psychological states of consumers who want to express individual characteristics and personality quirks while communicating their emotions to others. The fact that companies like KakaoTalk, Line, Apple, etc. have begun conducting emoticon business and sales of related content are expected to gradually increase testifies to the significance of this phenomenon. Nevertheless, despite the development of emoticons themselves and the growth of the emoticon market, no suitable emoticon recommendation system has yet been developed. Even KakaoTalk, a messenger application that commands more than 90% of domestic market share in South Korea, just grouped in to popularity, most recent, or brief category. This means consumers face the inconvenience of constantly scrolling around to locate the emoticons they want. The creation of an emoticon recommendation system would improve consumer convenience and satisfaction and increase the sales revenue of companies the sell emoticons. To recommend appropriate emoticons, it is necessary to quantify the emotions that the consumer sees and emotions. Such quantification will enable us to analyze the characteristics and emotions felt by consumers who used similar emoticons, which, in turn, will facilitate our emoticon recommendations for consumers. One way to quantify emoticons use is metadata-ization. Metadata-ization is a means of structuring or organizing unstructured and semi-structured data to extract meaning. By structuring unstructured emoticon data through metadata-ization, we can easily classify emoticons based on the emotions consumers want to express. To determine emoticons' precise emotions, we had to consider sub-detail expressions-not only the seven common emotional adjectives but also the metaphorical expressions that appear only in South Korean proved by previous studies related to emotion focusing on the emoticon's characteristics. We therefore collected the sub-detail expressions of emotion based on the "Shape", "Color" and "Adumbration". Moreover, to design a highly accurate recommendation system, we considered both emotion-technical indexes and emoticon-emotional indexes. We then identified 14 features of emoticon-technical indexes and selected 36 emotional adjectives. The 36 emotional adjectives consisted of contrasting adjectives, which we reduced to 18, and we measured the 18 emotional adjectives using 40 emoticon sets randomly selected from the top-ranked emoticons in the KakaoTalk shop. We surveyed 277 consumers in their mid-twenties who had experience purchasing emoticons; we recruited them online and asked them to evaluate five different emoticon sets. After data acquisition, we conducted a factor analysis of emoticon-emotional factors. We extracted four factors that we named "Comic", Softness", "Modernity" and "Transparency". We analyzed both the relationship between indexes and consumer attitude and the relationship between emoticon-technical indexes and emoticon-emotional factors. Through this process, we confirmed that the emoticon-technical indexes did not directly affect consumer attitudes but had a mediating effect on consumer attitudes through emoticon-emotional factors. The results of the analysis revealed the mechanism consumers use to evaluate emoticons; the results also showed that consumers' emoticon-technical indexes affected emoticon-emotional factors and that the emoticon-emotional factors affected consumer satisfaction. We therefore designed the emoticon recommendation system using only four emoticon-emotional factors; we created a recommendation method to calculate the Euclidean distance from each factors' emotion. In an attempt to increase the accuracy of the emoticon recommendation system, we compared the emotional patterns of selected emoticons with the recommended emoticons. The emotional patterns corresponded in principle. We verified the emoticon recommendation system by testing prediction accuracy; the predictions were 81.02% accurate in the first result, 76.64% accurate in the second, and 81.63% accurate in the third. This study developed a methodology that can be used in various fields academically and practically. We expect that the novel emoticon recommendation system we designed will increase emoticon sales for companies who conduct business in this domain and make consumer experiences more convenient. In addition, this study served as an important first step in the development of an intelligent emoticon recommendation system. The emotional factors proposed in this study could be collected in an emotional library that could serve as an emotion index for evaluation when new emoticons are released. Moreover, by combining the accumulated emotional library with company sales data, sales information, and consumer data, companies could develop hybrid recommendation systems that would bolster convenience for consumers and serve as intellectual assets that companies could strategically deploy.

• Journal of Food Hygiene and Safety
• /
• v.27 no.1
• /
• pp.42-49
• /
• 2012

This study was carried out to investigate the toxicity of food Red No.2 in the Sprague-Dawley (SD) female rat for 4 weeks. SD rats were orally administered for 28 days, with dosage of 500, 1,000, 2,000 mg/kg/day. Animals treated with food Red No.2 did not cause any death and show any clinical signs. They did not show any significant changes of body weight, feed uptake and water consumption. There were not significantly different from the control group in urinalysis, hematological, serum biochemical value and histopathological examination. In conclusion, 4 weeks of the repetitive oral medication of food Red No.2 has resulted no alteration of toxicity according to the test materials in the group of female rats with injection of 2,000 mg/kg. Therefore, food Red No.2 was not indicated to have any toxic effect in the SD rats, when it was orally administered below the dosage 2,000 mg/kg/day for 4 weeks.

• Korean Journal of Agricultural Science
• /
• v.4 no.2
• /
• pp.344-390
• /
• 1977

The purpose of this paper was to schedule optimum cutting strategy which could maximize the total yield under certain restrictions on periodic timber removals and harvest areas from an industrial forest, based on a linear programming technique. Sensitivity of the regulation model to variations in restrictions has also been analyzed to get information on the changes of total yield in the planning period. The regulation procedure has been made on the experimental forest of the Agricultural College of Seoul National University. The forest is composed of 219 cutting units, and characterized by younger age group which is very common in Korea. The planning period is devided into 10 cutting periods of five years each, and cutting is permissible only on the stands of age groups 5-9. It is also assumed in the study that the subsequent forests are established immediately after cutting existing forests, non-stocked forest lands are planted in first cutting period, and established forests are fully stocked until next harvest. All feasible cutting regimes have been defined to each unit depending on their age groups. Total yield (Vi, k) of each regime expected in the planning period has been projected using stand yield tables and forest inventory data, and the regime which gives highest Vi, k has been selected as a optimum cutting regime. After calculating periodic yields and cutting areas, and total yield from the optimum regimes selected without any restrictions, the upper and lower limits of periodic yields(Vj-max, Vj-min) and those of periodic cutting areas (Aj-max, Aj-min) have been decided. The optimum regimes under such restrictions have been selected by linear programming. The results of the study may be summarized as follows:- 1. The fluctuations of periodic harvest yields and areas under cutting regimes selected without restrictions were very great, because of irregular composition of age classes and growing stocks of existing stands. About 68.8 percent of total yield is expected in period 10, while none of yield in periods 6 and 7. 2. After inspection of the above solution, restricted optimum cutting regimes were obtained under the restrictions of Amin=150 ha, Amax=400ha, $Vmin=5,000m^3$ and $Vmax=50,000m^3$, using LP regulation model. As a result, about $50,000m^3$ of stable harvest yield per period and a relatively balanced age group distribution is expected from period 5. In this case, the loss in total yield was about 29 percent of that of unrestricted regimes. 3. Thinning schedule could be easily treated by the model presented in the study, and the thinnings made it possible to select optimum regimes which might be effective for smoothing the wood flows, not to speak of increasing total yield in the planning period. 4. It was known that the stronger the restrictions becomes in the optimum solution the earlier the period comes in which balanced harvest yields and age group distribution can be formed. There was also a tendency in this particular case that the periodic yields were strongly affected by constraints, and the fluctuations of harvest areas depended upon the amount of periodic yields. 5. Because the total yield was decreased at the increasing rate with imposing stronger restrictions, the Joss would be very great where strict sustained yield and normal age group distribution are required in the earlier periods. 6. Total yield under the same restrictions in a period was increased by lowering the felling age and extending the range of cutting age groups. Therefore, it seemed to be advantageous for producing maximum timber yield to adopt wider range of cutting age groups with the lower limit at which the smallest utilization size of timber could be produced. 7. The LP regulation model presented in the study seemed to be useful in the Korean situation from the following point of view: (1) The model can provide forest managers with the solution of where, when, and how much to cut in order to best fulfill the owners objective. (2) Planning is visualized as a continuous process where new strateges are automatically evolved as changes in the forest environment are recognized. (3) The cost (measured as decrease in total yield) of imposing restrictions can be easily evaluated. (4) Thinning schedule can be treated without difficulty. (5) The model can be applied to irregular forests. (6) Traditional regulation methods can be rainforced by the model.