• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.123-138
• /
• 2017

Since the stock market is driven by the expectation of traders, studies have been conducted to predict stock price movements through analysis of various sources of text data. In order to predict stock price movements, research has been conducted not only on the relationship between text data and fluctuations in stock prices, but also on the trading stocks based on news articles and social media responses. Studies that predict the movements of stock prices have also applied classification algorithms with constructing term-document matrix in the same way as other text mining approaches. Because the document contains a lot of words, it is better to select words that contribute more for building a term-document matrix. Based on the frequency of words, words that show too little frequency or importance are removed. It also selects words according to their contribution by measuring the degree to which a word contributes to correctly classifying a document. The basic idea of constructing a term-document matrix was to collect all the documents to be analyzed and to select and use the words that have an influence on the classification. In this study, we analyze the documents for each individual item and select the words that are irrelevant for all categories as neutral words. We extract the words around the selected neutral word and use it to generate the term-document matrix. The neutral word itself starts with the idea that the stock movement is less related to the existence of the neutral words, and that the surrounding words of the neutral word are more likely to affect the stock price movements. And apply it to the algorithm that classifies the stock price fluctuations with the generated term-document matrix. In this study, we firstly removed stop words and selected neutral words for each stock. And we used a method to exclude words that are included in news articles for other stocks among the selected words. Through the online news portal, we collected four months of news articles on the top 10 market cap stocks. We split the news articles into 3 month news data as training data and apply the remaining one month news articles to the model to predict the stock price movements of the next day. We used SVM, Boosting and Random Forest for building models and predicting the movements of stock prices. The stock market opened for four months (2016/02/01 ~ 2016/05/31) for a total of 80 days, using the initial 60 days as a training set and the remaining 20 days as a test set. The proposed word - based algorithm in this study showed better classification performance than the word selection method based on sparsity. This study predicted stock price volatility by collecting and analyzing news articles of the top 10 stocks in market cap. We used the term - document matrix based classification model to estimate the stock price fluctuations and compared the performance of the existing sparse - based word extraction method and the suggested method of removing words from the term - document matrix. The suggested method differs from the word extraction method in that it uses not only the news articles for the corresponding stock but also other news items to determine the words to extract. In other words, it removed not only the words that appeared in all the increase and decrease but also the words that appeared common in the news for other stocks. When the prediction accuracy was compared, the suggested method showed higher accuracy. The limitation of this study is that the stock price prediction was set up to classify the rise and fall, and the experiment was conducted only for the top ten stocks. The 10 stocks used in the experiment do not represent the entire stock market. In addition, it is difficult to show the investment performance because stock price fluctuation and profit rate may be different. Therefore, it is necessary to study the research using more stocks and the yield prediction through trading simulation.

• The Journal of Korean Academy of Prosthodontics
• /
• v.46 no.5
• /
• pp.528-534
• /
• 2008

Purpose: Marginal fit is one of the important components for the successful prosthodontic restoration. Poor fitting margin of the restoration causes hypersensitivity, secondary caries, and plaque accumulation, which later result in prosthodontic failure. CAD/CAM zirconia all-ceramic restorations, such as $LAVA^{(R)}$ (3M ESPE, St.Paul, MN) and $EVEREST^{(R)}$ (KaVo Dental GmbH, Biberach, Germany) systems were recently introduced in Korea. It is clinically meaningful to evaluate the changes of the marginal fit of the CAD/CAM zirconia systems before and after build-up. The purposes of this study are to compare the marginal fit of the two CAD/CAM all-ceramic systems with that of the ceramometal restoration, before and after porcelain build-up Material and methods: A maxillary first premolar dentiform tooth was prepared with 2.0 mm occlusal reduction, 1.0 mm axial reduction, chamfer margin, and 6 degree taperness in the axial wall. The prepared dentiform die was duplicated into the metal abutment die. The metal die was placed in the dental study model, and the full arch impressions of the model were made. Twenty four copings of 3 groups which were $LAVA^{(R)}$, $EVEREST^{(R)}$, and ceramometal restorations were fabricated. Each coping was cemented on the metal die with color-mixed Fit-checker $II^{(R)}$ (GC Cor., Tokyo, Japan). The marginal opening of each coping was measured with $Microhiscope^{(R)}$ system (HIROX KH-1000 ING-Plus, Seoul, Korea. X300 magnification). After porcelain build-up, the marginal openings of $LAVA^{(R)}$, $EVEREST^{(R)}$,and ceramometal restorations were also evaluated in the same method. Statistical analysis was done with paired t-test and one-way ANOVA test. Results: In coping states, the mean marginal opening for $EVEREST^{(R)}$ restorations was $52.00{\pm}11.94\;{\mu}m$ for $LAVA^{(R)}$ restorations $56.97{\pm}10.00\;{\mu}m$, and for ceramometal restorations $97.38{\pm}18.54\;{\mu}m$. After porcelain build-up, the mean marginal opening for $EVEREST^{(R)}$ restorations was $61.69{\pm}19.33\;{\mu}m$, for $LAVA^{(R)}$ restorations $70.81{\pm}12.99\;{\mu}m$, and for ceramometal restorations $1115.25{\pm}23.86\;{\mu}m$. Conclusion: 1. $LAVA^{(R)}$ and $EVEREST^{(R)}$ restorations in comparison with ceramometal restorations showed better marginal fit, which had significant differences (P < 0.05) in coping state and also after porcelain build-up . 2. The mean marginal opening values between $LAVA^{(R)}$ and $EVEREST^{(R)}$ restorations did not showed significant differences after porcelain build-up as well as in coping state (P > .05). 3. $EVEREST^{(R)}$, $LAVA^{(R)}$ and ceramometal restorations showed a little increased marginal opening after porcelain build-up, but did not show any statistical significance (P > .05).

• Journal of Korean Society of Environmental Engineers
• /
• v.32 no.1
• /
• pp.33-46
• /
• 2010

We investigated and estimated at the characteristics of decomposition and by-products of N-Nitrosodimethylamine (NDMA) using a design of experiment (DOE) based on the Box-Behken design in an UV process, and also the main factors (variables) with UV intensity($X_2$) (range: $1.5{\sim}4.5\;mW/cm^2$), NDMA concentration ($X_2$) (range: 100~300 uM) and pH ($X_2$) (rang: 3~9) which consisted of 3 levels in each factor and 4 responses ($Y_1$ (% of NDMA removal), $Y_2$ (dimethylamine (DMA) reformation (uM)), $Y_3$ (dimethylformamide (DMF) reformation (uM), $Y_4$ ($NO_2$-N reformation (uM)) were set up to estimate the prediction model and the optimization conditions. The results of prediction model and optimization point using the canonical analysis in order to obtain the optimal operation conditions were $Y_1$ [% of NDMA removal] = $117+21X_1-0.3X_2-17.2X_3+{2.43X_1}^2+{0.001X_2}^2+{3.2X_3}^2-0.08X_1X_2-1.6X_1X_3-0.05X_2X_3$ ($R^2$= 96%, Adjusted $R^2$ = 88%) and 99.3% ($X_1:\;4.5\;mW/cm^2$, $X_2:\;190\;uM$, $X_3:\;3.2$), $Y_2$ [DMA conc] = $-101+18.5X_1+0.4X_2+21X_3-{3.3X_1}^2-{0.01X_2}^2-{1.5X_3}^2-0.01X_1X_2+0.07X_1X_3-0.01X_2X_3$ ($R^2$= 99.4%, 수정 $R^2$ = 95.7%) and 35.2 uM ($X_1$: 3 $mW/cm^2$, $X_2$: 220 uM, $X_3$: 6.3), $Y_3$ [DMF conc] = $-6.2+0.2X_1+0.02X_2+2X_3-0.26X_1^2-0.01X_2^2-0.2X_3^2-0.004X_1X_2+0.1X_1X_3-0.02X_2X_3$ ($R^2$= 98%, Adjusted $R^2$ = 94.4%) and 3.7 uM ($X_1:\;4.5\;$mW/cm^2$, $X_2:\;290\;uM$, $X_3:\;6.2$) and $Y_4$ [$NO_2$-N conc] = $-25+12.2X_1+0.15X_2+7.8X_3+{1.1X_1}^2+{0.001X_2}^2-{0.34X_3}^2+0.01X_1X_2+0.08X_1X_3-3.4X_2X_3$ ($R^2$= 98.5%, Adjusted $R^2$ = 95.7%) and 74.5 uM ($X_1:\;4.5\;mW/cm^2$, $X_2:\;220\;uM$, $X_3:\;3.1$). This study has demonstrated that the response surface methodology and the Box-Behnken statistical experiment design can provide statistically reliable results for decomposition and by-products of NDMA by the UV photolysis and also for determination of optimum conditions. Predictions obtained from the response functions were in good agreement with the experimental results indicating the reliability of the methodology used.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.57-71
• /
• 2013

Over a billion people in the world generate new news minute by minute. People forecasts some news but most news are from unexpected events such as natural disasters, accidents, crimes. People spend much time to watch a huge amount of news delivered from many media because they want to understand what is happening now, to predict what might happen in the near future, and to share and discuss on the news. People make better daily decisions through watching and obtaining useful information from news they saw. However, it is difficult that people choose news suitable to them and obtain useful information from the news because there are so many news media such as portal sites, broadcasters, and most news articles consist of gossipy news and breaking news. User interest changes over time and many people have no interest in outdated news. From this fact, applying users' recent interest to personalized news service is also required in news service. It means that personalized news service should dynamically manage user profiles. In this paper, a content-based news recommendation system is proposed to provide the personalized news service. For a personalized service, user's personal information is requisitely required. Social network service is used to extract user information for personalization service. The proposed system constructs dynamic user profile based on recent user information of Facebook, which is one of social network services. User information contains personal information, recent articles, and Facebook Page information. Facebook Pages are used for businesses, organizations and brands to share their contents and connect with people. Facebook users can add Facebook Page to specify their interest in the Page. The proposed system uses this Page information to create user profile, and to match user preferences to news topics. However, some Pages are not directly matched to news topic because Page deals with individual objects and do not provide topic information suitable to news. Freebase, which is a large collaborative database of well-known people, places, things, is used to match Page to news topic by using hierarchy information of its objects. By using recent Page information and articles of Facebook users, the proposed systems can own dynamic user profile. The generated user profile is used to measure user preferences on news. To generate news profile, news category predefined by news media is used and keywords of news articles are extracted after analysis of news contents including title, category, and scripts. TF-IDF technique, which reflects how important a word is to a document in a corpus, is used to identify keywords of each news article. For user profile and news profile, same format is used to efficiently measure similarity between user preferences and news. The proposed system calculates all similarity values between user profiles and news profiles. Existing methods of similarity calculation in vector space model do not cover synonym, hypernym and hyponym because they only handle given words in vector space model. The proposed system applies WordNet to similarity calculation to overcome the limitation. Top-N news articles, which have high similarity value for a target user, are recommended to the user. To evaluate the proposed news recommendation system, user profiles are generated using Facebook account with participants consent, and we implement a Web crawler to extract news information from PBS, which is non-profit public broadcasting television network in the United States, and construct news profiles. We compare the performance of the proposed method with that of benchmark algorithms. One is a traditional method based on TF-IDF. Another is 6Sub-Vectors method that divides the points to get keywords into six parts. Experimental results demonstrate that the proposed system provide useful news to users by applying user's social network information and WordNet functions, in terms of prediction error of recommended news.

• Asia Marketing Journal
• /
• v.14 no.2
• /
• pp.65-96
• /
• 2012

Brand has received much attention from considerable marketing research. When consumers consume product or services, they are exposed to a lot of brand related stimuli. These contain brand personality, brand experience, brand identity, brand communications and so on. A special kind of new crisis occasionally confronting companies' brand management today is the brand related rumor. An important influence on consumers' purchase decision making is the word-of-mouth spread by other consumers and most decisions are influenced by other's recommendations. In light of this influence, firms have reasonable reason to study and understand consumer-to-consumer communication such as brand rumor. The importance of brand rumor to marketers is increasing as the number of internet user and SNS(social network service) site grows. Due to the development of internet technology, people can spread rumors without the limitation of time, space and place. However relatively few studies have been published in marketing journals and little is known about brand rumors in the marketplace. The study of rumor has a long history in all major social science. But very few studies have dealt with the antecedents and consequences of any kind of brand rumor. Rumor has been generally described as a story or statement in general circulation without proper confirmation or certainty as to fact. And it also can be defined as an unconfirmed proposition, passed along from people to people. Rosnow(1991) claimed that rumors were transmitted because people needed to explain ambiguous and uncertain events and talking about them reduced associated anxiety. Especially negative rumors are believed to have the potential to devastate a company's reputation and relations with customers. From the perspective of marketer, negative rumors are considered harmful and extremely difficult to control in general. It is becoming a threat to a company's sustainability and sometimes leads to negative brand image and loss of customers. Thus there is a growing concern that these negative rumors can damage brands' reputations and lead them to financial disaster too. In this study we aimed to distinguish antecedents of brand rumor transmission and investigate the effects of brand rumor characteristics on rumor spread intention. We also found key components in personal acceptance of brand rumor. In contextualist perspective, we tried to unify the traditional psychological and sociological views. In this unified research approach we defined brand rumor's characteristics based on five major variables that had been found to influence the process of rumor spread intention. The five factors of usefulness, source credibility, message credibility, worry, and vividness, encompass multi level elements of brand rumor. We also selected product involvement as a control variable. To perform the empirical research, imaginary Korean 'Kimch' brand and related contamination rumor was created and proposed. Questionnaires were collected from 178 Korean samples. Data were collected from college students who have been experienced the focal product. College students were regarded as good subjects because they have a tendency to express their opinions in detail. PLS(partial least square) method was adopted to analyze the relations between variables in the equation model. The most widely adopted causal modeling method is LISREL. However it is poorly suited to deal with relatively small data samples and can yield not proper solutions in some cases. PLS has been developed to avoid some of these limitations and provide more reliable results. To test the reliability using SPSS 16 s/w, Cronbach alpha was examined and all the values were appropriate showing alpha values between .802 and .953. Subsequently, confirmatory factor analysis was conducted successfully. And structural equation modeling has been used to analyze the research model using smartPLS(ver. 2.0) s/w. Overall, R² of adoption of rumor is .476 and R² of intention of rumor transmission is .218. The overall model showed a satisfactory fit. The empirical results can be summarized as follows. According to the results, the variables of brand rumor characteristic such as source credibility, message credibility, worry, and vividness affect argument strength of rumor. And argument strength of rumor also affects rumor intention. On the other hand, the relationship between perceived usefulness and argument strength of rumor is not significant. The moderating effect of product involvement on the relations between argument strength of rumor and rumor W.O.M intention is not supported neither. Consequently this study suggests some managerial and academic implications. We consider some implications for corporate crisis management planning, PR and brand management. This results show marketers that rumor is a critical factor for managing strong brand assets. Also for researchers, brand rumor should become an important thesis of their interests to understand the relationship between consumer and brand. Recently many brand managers and marketers have focused on the short-term view. They just focused on strengthen the positive brand image. According to this study we suggested that effective brand management requires managing negative brand rumors with a long-term view of marketing decisions.

• Journal of Food Hygiene and Safety
• /
• v.13 no.4
• /
• pp.441-447
• /
• 1998

This study was performed to investigate the changes of amount of S. typhimurium during cooking processes using pork and japchae (a Korean food which is made from meat, vegetables and noodles), and to support a practical application to develop a hazard analysis critical control point (HACCP) model. The pork was purchased in a retail shop, cut ($0.5\;cm\;{\times}\;10\;cm\;{\times}\;10\;cm$, 25 g), tested for Salmonella contamination (results: negative), inoculated with S. typhimurium ($10^{7}\;CFU/g$), then treated in various conditions related to cooking. Mter thawing for 24 hours in various conditions, the number of S. typhimurium was increased to $10^{10}\;CFU/g$ at a refrigerated temperature ($4~10^{\circ}C$), and to $10^{21}\;CFU/g$ at room temperature ($22~29^{\circ}C$). Mter thawing in a microwave oven for 40 seconds, the number of S. typhimurium increased to $10^{8}\;CFU/g$. During the thawing period, the number of S. typhimurium increased over time. At the refrigerated temperature, the number of the bacteria was $10^{10}\;CFU/g$ after 24 hours, $10^{13}\;CFU/g$ after 48 hours, and $10^{20}\;CFU/g$ after 72 hours. At room temperature the number of bacteria reached $10^{11}\;CFU/g$ in 2 hours, $10^{15}\;CFU/g$ in 4 hours, $10^{16}\;CFU/g$ in 8 hours, $10^{18}\;CFU/g$ in 12 hours, and $10^{21}\;CFU/g$ in 24 hours. Mter cooking in a frying pan (150{\pm}7^{\circ}C$) for 3 minutes, the bacterial count was $10^{16}\;CFU/g$. After cooking in hot water for 20 minutes, the bacterial count was $10^{7}\;CFU/g\;at\;60^{\circ}C,\;10^{6}\;CFU/g\;at\;63^{\circ}C,\;and\;10^{4}\;CFU/g\;at\;65^{\circ}C$. The fried pork was mixed with cooked vegetables, noodles, sesame oil, sesame seeds, and seasonings to make Korean japchae. This process took $10{\pm}2$ minutes. The bacterial count in the japchae increased to $10^{7}\;CFU/g$ from the count of $10^{6}\;CFU/g$ of the fried pork before it was mixed with the other ingredients. These results indicate that the amount of S. typhimurium is effected by various different cooking processes. This study can suggest that pork should be cooked in water at over $65^{\circ}C$ for 20 minutes in order to prevent food poisoning, if the pork is contaminated with S. typhimurium. The presence of S. typhimurium in the raw pork is identified in an HA for japchae, and the primary CCP for japchae is inadequate cooking (cooking method and time/temperature). We need to standardize time-temperature-size and amount of pork in cooking japchae, because pork is usually cooked in ordinary frying pans when we make this food.

• Korean Journal of Poultry Science
• /
• v.13 no.1
• /
• pp.1-14
• /
• 1986

The subject of this study was to obtain some genetic information for developing superior layer chickens. Heterosis and combining ability effects were estimated with 5,759 progenies of full diallel crosses of 6 strains in White Leghorn. Fertility, hatchability, brooder-house viability, rearing- house viability, laying-house viability, age at 1st egg laying, body weight at 1st egg laying, average egg weight, hen-day egg production, hen-housed egg production, and feed conversion were investigated and analyzed into heterosis effect, general combining ability, specific combining ability and reciprocal effect by Grilling's model I. The results obtained were summarized as follows; 1. The general performance of each traits was 94.76% in fertility, 74.05% in hatchability, 97.47% in brooder-house viability, 99.72% in rearing-house viability, 93.81% in laying-house viability, 150 day in the age at 1st egg laying, 1,505g in the body weight at 1st egg laying, 60.08g in average egg weight, 77.11% in hen-day egg production, 269.8 eggs in hen-housed egg Production, and 2.44 in feed conversion. 2. The heterosis effects were estimated to -0.66%, 9.58%, 0.26%, 1.83%, -3.87%, 3.63%, 0.96%, 4.23%, 6.4%, and -0.8%, in fertility, hatchability, brooder-house viability, laying-house viability, the age at 1st egg laying, the body weight at 1st egg laying, average egg weight, hen-day egg Production, hen-housed egg production and feed conversion, respectively. 3. The results obtained from analysis of combining ability were as follows ; 1) Estimates of general combining ability, specific combining ability and reciprocal effects were not high in fertility. It was considered that fertility was mainly affected by environmental factors. In the hatchability, the general combining ability was more important than specific combining ability and reciprocal effects, and the superior strains were K and V which the additive genetic effects were very high. 2) In the brooder-house viability and laying-house viability, specific combining ability and reciprocal effects appeared to be important and the combinations of K${\times}$A and A${\times}$K were very superior. 3) In the feed conversion and average egg weight, general combining ability was more important compared with specific combining ability and reciprocal effects. On the basis of combining ability the superior strains were F, K and B in feed conversion, F and B in the average egg weight. 4) General combining ability, specific combining ability and reciprocal effects were important in the age at 1st egg laying and the combination of V ${\times}$F, F${\times}$K and B${\times}$F were very useful on the basis of these effects. In the body weight at 1st egg laying, general combining ability was more important than specific combining ability and reciprocal effects, relatively. The K, F and E strains were recommended to develop the light strain in the body weight at 1st egg laying. 5) General combining ability, specific combining ability and reciprocal effects were important in the hen-day egg production and hen-housed egg production. The combinations of F${\times}$K, A${\times}$K, and K${\times}$A were proper for developing these traits. 4. In general, high general combining ability effects were estimated for hatchability, body weight at 1st egg laying, average egg weight, hen-day egg production, hen-housed egg production, and feed conversion and high specific combining ability effects for brooder-house viability, laying house viability, age at 1st egg laying, hen-day egg production and hen-housed egg production, and high reciprocal effects for the age at 1st egg laying.