• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.19-43
• /
• 2014

The Pareto principle, also known as the 80-20 rule, states that roughly 80% of the effects come from 20% of the causes for many events including natural phenomena. It has been recognized as a golden rule in business with a wide application of such discovery like 20 percent of customers resulting in 80 percent of total sales. On the other hand, the Long Tail theory, pointing out that "the trivial many" produces more value than "the vital few," has gained popularity in recent times with a tremendous reduction of distribution and inventory costs through the development of ICT(Information and Communication Technology). This study started with a view to illuminating how these two primary business paradigms-Pareto principle and Long Tail theory-relates to the success of virtual knowledge collaboration. The importance of virtual knowledge collaboration is soaring in this era of globalization and virtualization transcending geographical and temporal constraints. Many previous studies on knowledge sharing have focused on the factors to affect knowledge sharing, seeking to boost individual knowledge sharing and resolve the social dilemma caused from the fact that rational individuals are likely to rather consume than contribute knowledge. Knowledge collaboration can be defined as the creation of knowledge by not only sharing knowledge, but also by transforming and integrating such knowledge. In this perspective of knowledge collaboration, the relative distribution of knowledge sharing among participants can count as much as the absolute amounts of individual knowledge sharing. In particular, whether the more contribution of the upper 20 percent of participants in knowledge sharing will enhance the efficiency of overall knowledge collaboration is an issue of interest. This study deals with the effect of this sort of knowledge sharing distribution on the efficiency of knowledge collaboration and is extended to reflect the work characteristics. All analyses were conducted based on actual data instead of self-reported questionnaire surveys. More specifically, we analyzed the collaborative behaviors of editors of 2,978 English Wikipedia featured articles, which are the best quality grade of articles in English Wikipedia. We adopted Pareto ratio, the ratio of the number of knowledge contribution of the upper 20 percent of participants to the total number of knowledge contribution made by the total participants of an article group, to examine the effect of Pareto principle. In addition, Gini coefficient, which represents the inequality of income among a group of people, was applied to reveal the effect of inequality of knowledge contribution. Hypotheses were set up based on the assumption that the higher ratio of knowledge contribution by more highly motivated participants will lead to the higher collaboration efficiency, but if the ratio gets too high, the collaboration efficiency will be exacerbated because overall informational diversity is threatened and knowledge contribution of less motivated participants is intimidated. Cox regression models were formulated for each of the focal variables-Pareto ratio and Gini coefficient-with seven control variables such as the number of editors involved in an article, the average time length between successive edits of an article, the number of sections a featured article has, etc. The dependent variable of the Cox models is the time spent from article initiation to promotion to the featured article level, indicating the efficiency of knowledge collaboration. To examine whether the effects of the focal variables vary depending on the characteristics of a group task, we classified 2,978 featured articles into two categories: Academic and Non-academic. Academic articles refer to at least one paper published at an SCI, SSCI, A&HCI, or SCIE journal. We assumed that academic articles are more complex, entail more information processing and problem solving, and thus require more skill variety and expertise. The analysis results indicate the followings; First, Pareto ratio and inequality of knowledge sharing relates in a curvilinear fashion to the collaboration efficiency in an online community, promoting it to an optimal point and undermining it thereafter. Second, the curvilinear effect of Pareto ratio and inequality of knowledge sharing on the collaboration efficiency is more sensitive with a more academic task in an online community.

• Journal of Intelligence and Information Systems
• /
• v.16 no.2
• /
• pp.19-32
• /
• 2010

Volatility plays a central role in both academic and practical applications, especially in pricing financial derivative products and trading volatility strategies. This study presents a novel mechanism based on generalized autoregressive conditional heteroskedasticity (GARCH) models that is able to enhance the performance of intelligent volatility trading systems by predicting Korean stock market volatility more accurately. In particular, we embedded the concept of the volatility asymmetry documented widely in the literature into our model. The newly developed Korean stock market volatility index of KOSPI 200, VKOSPI, is used as a volatility proxy. It is the price of a linear portfolio of the KOSPI 200 index options and measures the effect of the expectations of dealers and option traders on stock market volatility for 30 calendar days. The KOSPI 200 index options market started in 1997 and has become the most actively traded market in the world. Its trading volume is more than 10 million contracts a day and records the highest of all the stock index option markets. Therefore, analyzing the VKOSPI has great importance in understanding volatility inherent in option prices and can afford some trading ideas for futures and option dealers. Use of the VKOSPI as volatility proxy avoids statistical estimation problems associated with other measures of volatility since the VKOSPI is model-free expected volatility of market participants calculated directly from the transacted option prices. This study estimates the symmetric and asymmetric GARCH models for the KOSPI 200 index from January 2003 to December 2006 by the maximum likelihood procedure. Asymmetric GARCH models include GJR-GARCH model of Glosten, Jagannathan and Runke, exponential GARCH model of Nelson and power autoregressive conditional heteroskedasticity (ARCH) of Ding, Granger and Engle. Symmetric GARCH model indicates basic GARCH (1, 1). Tomorrow's forecasted value and change direction of stock market volatility are obtained by recursive GARCH specifications from January 2007 to December 2009 and are compared with the VKOSPI. Empirical results indicate that negative unanticipated returns increase volatility more than positive return shocks of equal magnitude decrease volatility, indicating the existence of volatility asymmetry in the Korean stock market. The point value and change direction of tomorrow VKOSPI are estimated and forecasted by GARCH models. Volatility trading system is developed using the forecasted change direction of the VKOSPI, that is, if tomorrow VKOSPI is expected to rise, a long straddle or strangle position is established. A short straddle or strangle position is taken if VKOSPI is expected to fall tomorrow. Total profit is calculated as the cumulative sum of the VKOSPI percentage change. If forecasted direction is correct, the absolute value of the VKOSPI percentage changes is added to trading profit. It is subtracted from the trading profit if forecasted direction is not correct. For the in-sample period, the power ARCH model best fits in a statistical metric, Mean Squared Prediction Error (MSPE), and the exponential GARCH model shows the highest Mean Correct Prediction (MCP). The power ARCH model best fits also for the out-of-sample period and provides the highest probability for the VKOSPI change direction tomorrow. Generally, the power ARCH model shows the best fit for the VKOSPI. All the GARCH models provide trading profits for volatility trading system and the exponential GARCH model shows the best performance, annual profit of 197.56%, during the in-sample period. The GARCH models present trading profits during the out-of-sample period except for the exponential GARCH model. During the out-of-sample period, the power ARCH model shows the largest annual trading profit of 38%. The volatility clustering and asymmetry found in this research are the reflection of volatility non-linearity. This further suggests that combining the asymmetric GARCH models and artificial neural networks can significantly enhance the performance of the suggested volatility trading system, since artificial neural networks have been shown to effectively model nonlinear relationships.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.36 no.3
• /
• pp.115-127
• /
• 2018

This study was attempted to find out the value of cultural assets through the clear diagnosis and prescription of the dead and weakness factors of the Population of Retusa Fringe Trees in Pyeongji-ri, Jinan(Natural Monument No. 214), The results are as follows. First, Since the designation of 13 natural monuments in 1968, since 1973, many years have passed since then. In particular, despite the removal of some of the buried soil during the maintenance process, such as retreating from the fence of the primary school after 2010, Second, The first and third surviving tree of the designated trees also have many branches that are dead, the leaves are dull, and the amount of leaves is small. vitality of tree is 'extremely bad', and the first branch has already been faded by a large number of branches, and the amount of leaves is considerably low this year, so that only two flowers are bloomed. The second is also in a 'bad'state, with small leaves, low leaf density, and deformed water. The largest number 1 in the world is added to the concern that the s coverd oil is assumed to be paddy soils. Third, It is found that the composition ratio of silt is high because it is known as '[silty loam(SiL)]'. In addition, the pH of the northern soil at pH 1 was 6.6, which was significantly different from that of the other soil. In addition, the organic matter content was higher than the appropriate range, which is considered to reflect the result of continuous application for protection management. Fourth, It is considered that the root cause of failure and growth of Jinan pyeongji-ri Population of Retusa Fringe Trees group is chronic syndrome of serious menstrual deterioration due to covered soil. This can also be attributed to the newly planted succession and to some of the deaths. Fifthly, It is urgent to gradually remove the subsoil part, which is estimated to be the cause of the initial damage. Above all, it is almost impossible to remove the coverd soil after grasping the details of the soil, such as clayey soil, which is buried in the rootstock. After removal of the coverd soil, a pestle is installed to improve the respiration of the roots and the ground with Masato. And the dead 4th dead wood and the 5th and 6th dead wood are the best, and the lower layer vegetation is mown. The viable neck should be removed from the upper surface, and the bark defect should undergo surgery and induce the development of blindness by vestibule below the growth point. Sixth, The underground roots should be identified to prepare a method to improve the decompression of the root and the respiration of the soil. It is induced by the shortening of rotten roots by tracing the first half of the rootstock to induce the generation of new roots. Seventh, We try mulching to suppress weed occurrence, trampling pressure, and soil moisturizing effect. In addition, consideration should be given to the fertilization of the foliar fertilizer, the injection of the nutrients, and the soil management of the inorganic fertilizer for the continuous nutrition supply. Future monitoring and forecasting plans should be developed to check for changes continuously.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.36 no.3
• /
• pp.58-74
• /
• 2018

This study aims to propose baseline data for designing restoration of Gaobyulup, researching space formation and characteristics of gardens of Gaobyulup, which located in the foot of Cheonmasan Mountain in Namyangju. Gaobyulup is a remain in retirement of Gyulsan Yu-Won Lee, a representative politician, administrator, and tea drinker in late Joseon Dynasty. The results of the research about the shape of Gaobyulup deducted through reference review, poetry and prose analysis, an on-the-spot survey and residents' interview are below: Lee, who used pseudonym as 'Gyulsan,' which menas Jongnamsan Mountain, yearned Mangcheonbyeoreop(輞川別業) by Yu Wang and retirement with a country house operation by Seogye Sedang Park. In the persuit of this ideal, he created and operated a country house in Gaogok of Yangju, which a family burial ground was located. Gaobyulup, which located in Gaogok in the lower part of Cheonmasan Mountain, was largely composed outer and inner gardens, and the area of house operation was started from a stone post of Gaobokji The inner garden of Gaobyulup was including major garden components like buildings, such as Sasihyanggwan, Obaekganjung, Imharyoe and Toesadam, and Chaewon near Haengrangchae, and Gwawon in an backyard. In addition, Younggwijung pavilion, which located 850m away from Gaobyulup, was the another country house inside the Byulup, thus Gaobyulup shows a duplex space formation. In the inner garden of Gaobyulup, there are Sasihyanggwan, which had functions of Sarangchae as library and depository of old paintings and calligraphic works, and Obaekganjung, a small Sarangchae which connected with Sasihyanggwan in the form of a transept. Yusanggoksuger located near Obaekganjung. Additionally, Imharyeo, a library with a tablet of Byeokryowon(??園), which located in the highest point in Byulup, has the functions of a reading room and a tea house. Many Taihu stones were located not only in Toesadam, a square-formed pond with lotus but also many places in the inner gardens. And rare garden plants were planted. These were closely related to the trend of horticulture for pleasure, wealth, and collecting old paintings and calligraphic works for pleasure of Lee. Meanwhile, the area of Younggwijung pavilion, located in Gaocheon stream fall from Byulup to Manhoiam, looks like Wooampok, a enjoying place of other personages, who use their pseudonym as "Oksan" or "Wooam" Lee identifies Wooampok as "Jesampok" and carved 'Gyulsan' s he declared this place is his operating area. Lee built Younggwijung pavilion and planted many peach trees for recreation of utopia. The stone letters of Byukpadongcheon, located in front of a bridge in the foreside of Younggwijung pavilion, seems another enchanted land created in Gaobokji inside. Lee carved Jeilsan in huge rock on the falls rear Manhoiam temple, which Lee did great role of foundation of the temple, so he identifies that this place was the end of the outer garden of Gaobyulup. This study tries to estimate traces of the country house in Gaogok through reference review and on-th-spot survey, and the results from this study are presumed based on site remains only conformed today. It needs to discover second scenary or stone carved letters between Jeilsan and Jesampok. Additionally, exact formation characteristics of Gaobyulup should be identified through excavation survey later. To do so, an interest and a major role of Namyangju-si must be equipped for future restoration of Gaobyulup.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.26 no.1
• /
• pp.69-89
• /
• 1981

Stevia (Stevia rebaudiana Bertoni) is a perennial herb widely distributed in the mountainous area of Paraguay. It belongs to the family Compositae and contains 6 to 12 percent stevioside in the leaves. Stevioside is a glucoside having similar sweetening character to surgar and the degree of sweetness is approximately 300 times of sugar. Since Korea does not produce any sugar crops, and the synthetic sweetenings are potentially hazardous for health, it is rather urgent to develop an economical new sweetener. Consequently, the current experiments are conducted to establish cultural practices of stevia, a new sweetening herbs, introduced into Korea in 1973 and the results are summarized as followings: 1. Days from transplanting of cuttings to the flower bud formation of 6 stevia lines were similar among daylengths of 8, 10 and 12 hours, but it was much greater at daylengths of 14 or 24 hour and varietal differences were noticable. All lines were photosensitive, but a line, 77013, was the most sensitive and 77067 and Suweon 2 were less sensitive to daylength. 2. Critical daylength of all lines seemed to be approximately 12 hours. Growth of plants was severely retarded at daylengths less than 12 hours. 3. Cutting were responded to short daylength before rooting. Number of days from transplanting to flower bud formation of 40-day old cuttings in the nursery bed was 20 days and it was delayed as duration of nursery were shorter. 4. Number of days from emergence to flower bud formation was shortest at short day treatment from 20 days after emergence. It was became longer as initiation of short day treatment was earlier or later than 20 days. 5. Plant height, number of branches, and top dry weight of stevia were reduced as cutting date was delayed from March 20 to May 20. The highest yield of dry leaf was obtained at nursery duration of 40-50 days in march 20 cutting, 30-40 days in April 20 cutting, and 30 days in May 20 cutting. 6. An asymptotic relationship was observed between plant population and leaf dry weight. Yield of dry leaf increased rapidly as plant population increased from 5,000 to 10,000 plants/10a with a reduced increasing rate from 10,000 to 20,000 plants/l0a, and levelled off at the plant population higher than 20,000 plants/l0a. 7. Stevia was adaptable in Suweon, Chengju, Mokpo and Jeju and drought was one of the main factors reducing yield of dry leaf. Yield of dry leaf was reduced significantly (approximately 30%) at June 20 transplanting compared to optimum transplanting. 8. Yield of dry leaf was higher in a vinyl house compared to unprotected control at long daylength or natural daylength except at short day treatment at March 20. Higher temperature ill a vinyl house does not have benefital effects at April 20 transplanting. 9. The highest content of stevioside was noted at the upper leaves of the plant but the lowest was measured at the plant parts of 20cm above ground. Leaf dry weight and stevioside yield was mainly contributed by the plant parts of 60 to 120cm above ground but the varietal differences were also significant. 10. Delayed harvest by the time of flower bud formation increased leaf dry weight remarkably. However, there were insignificant changes of yield as harvests were made at any time after flower bud formation. Content of stevioside was highest at the time of flower bud formation and earlier or later harvest than this time was low in its content. The optimum harvesting time determined by leaf dry weight and stevioside content was the periods from flower bud formation to right before flowering that would be the period from September 10 to September 15 in Suweon area. 11. Stevioside and rebaudioside content in the leaves of Stevia varieties were ranged from 5.4% to 14.3% and 1.5% to 8.3% respectively. However, no definit relationships between stevioside and rebaudioside were observed in these particular experiments.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.1-21
• /
• 2012

In recent years, mobile phone has experienced an extremely fast evolution. It is equipped with high-quality color displays, high resolution cameras, and real-time accelerated 3D graphics. In addition, some other features are includes GPS sensor and Digital Compass, etc. This evolution advent significantly helps the application developers to use the power of smart-phones, to create a rich environment that offers a wide range of services and exciting possibilities. To date mobile AR in outdoor research there are many popular location-based AR services, such Layar and Wikitude. These systems have big limitation the AR contents hardly overlaid on the real target. Another research is context-based AR services using image recognition and tracking. The AR contents are precisely overlaid on the real target. But the real-time performance is restricted by the retrieval time and hardly implement in large scale area. In our work, we exploit to combine advantages of location-based AR with context-based AR. The system can easily find out surrounding landmarks first and then do the recognition and tracking with them. The proposed system mainly consists of two major parts-landmark browsing module and annotation module. In landmark browsing module, user can view an augmented virtual information (information media), such as text, picture and video on their smart-phone viewfinder, when they pointing out their smart-phone to a certain building or landmark. For this, landmark recognition technique is applied in this work. SURF point-based features are used in the matching process due to their robustness. To ensure the image retrieval and matching processes is fast enough for real time tracking, we exploit the contextual device (GPS and digital compass) information. This is necessary to select the nearest and pointed orientation landmarks from the database. The queried image is only matched with this selected data. Therefore, the speed for matching will be significantly increased. Secondly is the annotation module. Instead of viewing only the augmented information media, user can create virtual annotation based on linked data. Having to know a full knowledge about the landmark, are not necessary required. They can simply look for the appropriate topic by searching it with a keyword in linked data. With this, it helps the system to find out target URI in order to generate correct AR contents. On the other hand, in order to recognize target landmarks, images of selected building or landmark are captured from different angle and distance. This procedure looks like a similar processing of building a connection between the real building and the virtual information existed in the Linked Open Data. In our experiments, search range in the database is reduced by clustering images into groups according to their coordinates. A Grid-base clustering method and user location information are used to restrict the retrieval range. Comparing the existed research using cluster and GPS information the retrieval time is around 70~80ms. Experiment results show our approach the retrieval time reduces to around 18~20ms in average. Therefore the totally processing time is reduced from 490~540ms to 438~480ms. The performance improvement will be more obvious when the database growing. It demonstrates the proposed system is efficient and robust in many cases.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.73-85
• /
• 2013

Nowadays, in today's information society, the importance of the knowledge service using the information to creative value is getting higher day by day. In addition, depending on the development of IT technology, it is ease to collect and use information. Also, many companies actively use customer information to marketing in a variety of industries. Into the 21st century, companies have been actively using the culture arts to manage corporate image and marketing closely linked to their commercial interests. But, it is difficult that companies attract or maintain consumer's interest through their technology. For that reason, it is trend to perform cultural activities for tool of differentiation over many firms. Many firms used the customer's experience to new marketing strategy in order to effectively respond to competitive market. Accordingly, it is emerging rapidly that the necessity of personalized service to provide a new experience for people based on the personal profile information that contains the characteristics of the individual. Like this, personalized service using customer's individual profile information such as language, symbols, behavior, and emotions is very important today. Through this, we will be able to judge interaction between people and content and to maximize customer's experience and satisfaction. There are various relative works provide customer-centered service. Specially, emotion recognition research is emerging recently. Existing researches experienced emotion recognition using mostly bio-signal. Most of researches are voice and face studies that have great emotional changes. However, there are several difficulties to predict people's emotion caused by limitation of equipment and service environments. So, in this paper, we develop emotion prediction model based on vision-based interface to overcome existing limitations. Emotion recognition research based on people's gesture and posture has been processed by several researchers. This paper developed a model that recognizes people's emotional states through body gesture and posture using difference image method. And we found optimization validation model for four kinds of emotions' prediction. A proposed model purposed to automatically determine and predict 4 human emotions (Sadness, Surprise, Joy, and Disgust). To build up the model, event booth was installed in the KOCCA's lobby and we provided some proper stimulative movie to collect their body gesture and posture as the change of emotions. And then, we extracted body movements using difference image method. And we revised people data to build proposed model through neural network. The proposed model for emotion prediction used 3 type time-frame sets (20 frames, 30 frames, and 40 frames). And then, we adopted the model which has best performance compared with other models.' Before build three kinds of models, the entire 97 data set were divided into three data sets of learning, test, and validation set. The proposed model for emotion prediction was constructed using artificial neural network. In this paper, we used the back-propagation algorithm as a learning method, and set learning rate to 10%, momentum rate to 10%. The sigmoid function was used as the transform function. And we designed a three-layer perceptron neural network with one hidden layer and four output nodes. Based on the test data set, the learning for this research model was stopped when it reaches 50000 after reaching the minimum error in order to explore the point of learning. We finally processed each model's accuracy and found best model to predict each emotions. The result showed prediction accuracy 100% from sadness, and 96% from joy prediction in 20 frames set model. And 88% from surprise, and 98% from disgust in 30 frames set model. The findings of our research are expected to be useful to provide effective algorithm for personalized service in various industries such as advertisement, exhibition, performance, etc.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.123-139
• /
• 2019

The job classification system of major job sites differs from site to site and is different from the job classification system of the 'SQF(Sectoral Qualifications Framework)' proposed by the SW field. Therefore, a new job classification system is needed for SW companies, SW job seekers, and job sites to understand. The purpose of this study is to establish a standard job classification system that reflects market demand by analyzing SQF based on job offer information of major job sites and the NCS(National Competency Standards). For this purpose, the association analysis between occupations of major job sites is conducted and the association rule between SQF and occupation is conducted to derive the association rule between occupations. Using this association rule, we proposed an intelligent job classification system based on data mapping the job classification system of major job sites and SQF and job classification system. First, major job sites are selected to obtain information on the job classification system of the SW market. Then We identify ways to collect job information from each site and collect data through open API. Focusing on the relationship between the data, filtering only the job information posted on each job site at the same time, other job information is deleted. Next, we will map the job classification system between job sites using the association rules derived from the association analysis. We will complete the mapping between these market segments, discuss with the experts, further map the SQF, and finally propose a new job classification system. As a result, more than 30,000 job listings were collected in XML format using open API in 'WORKNET,' 'JOBKOREA,' and 'saramin', which are the main job sites in Korea. After filtering out about 900 job postings simultaneously posted on multiple job sites, 800 association rules were derived by applying the Apriori algorithm, which is a frequent pattern mining. Based on 800 related rules, the job classification system of WORKNET, JOBKOREA, and saramin and the SQF job classification system were mapped and classified into 1st and 4th stages. In the new job taxonomy, the first primary class, IT consulting, computer system, network, and security related job system, consisted of three secondary classifications, five tertiary classifications, and five fourth classifications. The second primary classification, the database and the job system related to system operation, consisted of three secondary classifications, three tertiary classifications, and four fourth classifications. The third primary category, Web Planning, Web Programming, Web Design, and Game, was composed of four secondary classifications, nine tertiary classifications, and two fourth classifications. The last primary classification, job systems related to ICT management, computer and communication engineering technology, consisted of three secondary classifications and six tertiary classifications. In particular, the new job classification system has a relatively flexible stage of classification, unlike other existing classification systems. WORKNET divides jobs into third categories, JOBKOREA divides jobs into second categories, and the subdivided jobs into keywords. saramin divided the job into the second classification, and the subdivided the job into keyword form. The newly proposed standard job classification system accepts some keyword-based jobs, and treats some product names as jobs. In the classification system, not only are jobs suspended in the second classification, but there are also jobs that are subdivided into the fourth classification. This reflected the idea that not all jobs could be broken down into the same steps. We also proposed a combination of rules and experts' opinions from market data collected and conducted associative analysis. Therefore, the newly proposed job classification system can be regarded as a data-based intelligent job classification system that reflects the market demand, unlike the existing job classification system. This study is meaningful in that it suggests a new job classification system that reflects market demand by attempting mapping between occupations based on data through the association analysis between occupations rather than intuition of some experts. However, this study has a limitation in that it cannot fully reflect the market demand that changes over time because the data collection point is temporary. As market demands change over time, including seasonal factors and major corporate public recruitment timings, continuous data monitoring and repeated experiments are needed to achieve more accurate matching. The results of this study can be used to suggest the direction of improvement of SQF in the SW industry in the future, and it is expected to be transferred to other industries with the experience of success in the SW industry.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.57-78
• /
• 2020

With the development of the Internet, consumers have had an opportunity to check product information easily through E-Commerce. Product reviews used in the process of purchasing goods are based on user experience, allowing consumers to engage as producers of information as well as refer to information. This can be a way to increase the efficiency of purchasing decisions from the perspective of consumers, and from the seller's point of view, it can help develop products and strengthen their competitiveness. However, it takes a lot of time and effort to understand the overall assessment and assessment dimensions of the products that I think are important in reading the vast amount of product reviews offered by E-Commerce for the products consumers want to compare. This is because product reviews are unstructured information and it is difficult to read sentiment of reviews and assessment dimension immediately. For example, consumers who want to purchase a laptop would like to check the assessment of comparative products at each dimension, such as performance, weight, delivery, speed, and design. Therefore, in this paper, we would like to propose a method to automatically generate multi-dimensional product assessment scores in product reviews that we would like to compare. The methods presented in this study consist largely of two phases. One is the pre-preparation phase and the second is the individual product scoring phase. In the pre-preparation phase, a dimensioned classification model and a sentiment analysis model are created based on a review of the large category product group review. By combining word embedding and association analysis, the dimensioned classification model complements the limitation that word embedding methods for finding relevance between dimensions and words in existing studies see only the distance of words in sentences. Sentiment analysis models generate CNN models by organizing learning data tagged with positives and negatives on a phrase unit for accurate polarity detection. Through this, the individual product scoring phase applies the models pre-prepared for the phrase unit review. Multi-dimensional assessment scores can be obtained by aggregating them by assessment dimension according to the proportion of reviews organized like this, which are grouped among those that are judged to describe a specific dimension for each phrase. In the experiment of this paper, approximately 260,000 reviews of the large category product group are collected to form a dimensioned classification model and a sentiment analysis model. In addition, reviews of the laptops of S and L companies selling at E-Commerce are collected and used as experimental data, respectively. The dimensioned classification model classified individual product reviews broken down into phrases into six assessment dimensions and combined the existing word embedding method with an association analysis indicating frequency between words and dimensions. As a result of combining word embedding and association analysis, the accuracy of the model increased by 13.7%. The sentiment analysis models could be seen to closely analyze the assessment when they were taught in a phrase unit rather than in sentences. As a result, it was confirmed that the accuracy was 29.4% higher than the sentence-based model. Through this study, both sellers and consumers can expect efficient decision making in purchasing and product development, given that they can make multi-dimensional comparisons of products. In addition, text reviews, which are unstructured data, were transformed into objective values such as frequency and morpheme, and they were analysed together using word embedding and association analysis to improve the objectivity aspects of more precise multi-dimensional analysis and research. This will be an attractive analysis model in terms of not only enabling more effective service deployment during the evolving E-Commerce market and fierce competition, but also satisfying both customers.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.79-104
• /
• 2020

Recently, as deep learning has attracted attention, the use of deep learning is being considered as a method for solving problems in various fields. In particular, deep learning is known to have excellent performance when applied to applying unstructured data such as text, sound and images, and many studies have proven its effectiveness. Owing to the remarkable development of text and image deep learning technology, interests in image captioning technology and its application is rapidly increasing. Image captioning is a technique that automatically generates relevant captions for a given image by handling both image comprehension and text generation simultaneously. In spite of the high entry barrier of image captioning that analysts should be able to process both image and text data, image captioning has established itself as one of the key fields in the A.I. research owing to its various applicability. In addition, many researches have been conducted to improve the performance of image captioning in various aspects. Recent researches attempt to create advanced captions that can not only describe an image accurately, but also convey the information contained in the image more sophisticatedly. Despite many recent efforts to improve the performance of image captioning, it is difficult to find any researches to interpret images from the perspective of domain experts in each field not from the perspective of the general public. Even for the same image, the part of interests may differ according to the professional field of the person who has encountered the image. Moreover, the way of interpreting and expressing the image also differs according to the level of expertise. The public tends to recognize the image from a holistic and general perspective, that is, from the perspective of identifying the image's constituent objects and their relationships. On the contrary, the domain experts tend to recognize the image by focusing on some specific elements necessary to interpret the given image based on their expertise. It implies that meaningful parts of an image are mutually different depending on viewers' perspective even for the same image. So, image captioning needs to implement this phenomenon. Therefore, in this study, we propose a method to generate captions specialized in each domain for the image by utilizing the expertise of experts in the corresponding domain. Specifically, after performing pre-training on a large amount of general data, the expertise in the field is transplanted through transfer-learning with a small amount of expertise data. However, simple adaption of transfer learning using expertise data may invoke another type of problems. Simultaneous learning with captions of various characteristics may invoke so-called 'inter-observation interference' problem, which make it difficult to perform pure learning of each characteristic point of view. For learning with vast amount of data, most of this interference is self-purified and has little impact on learning results. On the contrary, in the case of fine-tuning where learning is performed on a small amount of data, the impact of such interference on learning can be relatively large. To solve this problem, therefore, we propose a novel 'Character-Independent Transfer-learning' that performs transfer learning independently for each character. In order to confirm the feasibility of the proposed methodology, we performed experiments utilizing the results of pre-training on MSCOCO dataset which is comprised of 120,000 images and about 600,000 general captions. Additionally, according to the advice of an art therapist, about 300 pairs of 'image / expertise captions' were created, and the data was used for the experiments of expertise transplantation. As a result of the experiment, it was confirmed that the caption generated according to the proposed methodology generates captions from the perspective of implanted expertise whereas the caption generated through learning on general data contains a number of contents irrelevant to expertise interpretation. In this paper, we propose a novel approach of specialized image interpretation. To achieve this goal, we present a method to use transfer learning and generate captions specialized in the specific domain. In the future, by applying the proposed methodology to expertise transplant in various fields, we expected that many researches will be actively conducted to solve the problem of lack of expertise data and to improve performance of image captioning.