• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.219-240
• /
• 2018

Sentiment analysis, which is one of the text mining techniques, is a method for extracting subjective content embedded in text documents. Recently, the sentiment analysis methods have been widely used in many fields. As good examples, data-driven surveys are based on analyzing the subjectivity of text data posted by users and market researches are conducted by analyzing users' review posts to quantify users' reputation on a target product. The basic method of sentiment analysis is to use sentiment dictionary (or lexicon), a list of sentiment vocabularies with positive, neutral, or negative semantics. In general, the meaning of many sentiment words is likely to be different across domains. For example, a sentiment word, 'sad' indicates negative meaning in many fields but a movie. In order to perform accurate sentiment analysis, we need to build the sentiment dictionary for a given domain. However, such a method of building the sentiment lexicon is time-consuming and various sentiment vocabularies are not included without the use of general-purpose sentiment lexicon. In order to address this problem, several studies have been carried out to construct the sentiment lexicon suitable for a specific domain based on 'OPEN HANGUL' and 'SentiWordNet', which are general-purpose sentiment lexicons. However, OPEN HANGUL is no longer being serviced and SentiWordNet does not work well because of language difference in the process of converting Korean word into English word. There are restrictions on the use of such general-purpose sentiment lexicons as seed data for building the sentiment lexicon for a specific domain. In this article, we construct 'KNU Korean Sentiment Lexicon (KNU-KSL)', a new general-purpose Korean sentiment dictionary that is more advanced than existing general-purpose lexicons. The proposed dictionary, which is a list of domain-independent sentiment words such as 'thank you', 'worthy', and 'impressed', is built to quickly construct the sentiment dictionary for a target domain. Especially, it constructs sentiment vocabularies by analyzing the glosses contained in Standard Korean Language Dictionary (SKLD) by the following procedures: First, we propose a sentiment classification model based on Bidirectional Long Short-Term Memory (Bi-LSTM). Second, the proposed deep learning model automatically classifies each of glosses to either positive or negative meaning. Third, positive words and phrases are extracted from the glosses classified as positive meaning, while negative words and phrases are extracted from the glosses classified as negative meaning. Our experimental results show that the average accuracy of the proposed sentiment classification model is up to 89.45%. In addition, the sentiment dictionary is more extended using various external sources including SentiWordNet, SenticNet, Emotional Verbs, and Sentiment Lexicon 0603. Furthermore, we add sentiment information about frequently used coined words and emoticons that are used mainly on the Web. The KNU-KSL contains a total of 14,843 sentiment vocabularies, each of which is one of 1-grams, 2-grams, phrases, and sentence patterns. Unlike existing sentiment dictionaries, it is composed of words that are not affected by particular domains. The recent trend on sentiment analysis is to use deep learning technique without sentiment dictionaries. The importance of developing sentiment dictionaries is declined gradually. However, one of recent studies shows that the words in the sentiment dictionary can be used as features of deep learning models, resulting in the sentiment analysis performed with higher accuracy (Teng, Z., 2016). This result indicates that the sentiment dictionary is used not only for sentiment analysis but also as features of deep learning models for improving accuracy. The proposed dictionary can be used as a basic data for constructing the sentiment lexicon of a particular domain and as features of deep learning models. It is also useful to automatically and quickly build large training sets for deep learning models.

• Asia pacific journal of information systems
• /
• v.24 no.2
• /
• pp.233-253
• /
• 2014

Can the stock market really be predicted? Stock market prediction has attracted much attention from many fields including business, economics, statistics, and mathematics. Early research on stock market prediction was based on random walk theory (RWT) and the efficient market hypothesis (EMH). According to the EMH, stock market are largely driven by new information rather than present and past prices. Since it is unpredictable, stock market will follow a random walk. Even though these theories, Schumaker [2010] asserted that people keep trying to predict the stock market by using artificial intelligence, statistical estimates, and mathematical models. Mathematical approaches include Percolation Methods, Log-Periodic Oscillations and Wavelet Transforms to model future prices. Examples of artificial intelligence approaches that deals with optimization and machine learning are Genetic Algorithms, Support Vector Machines (SVM) and Neural Networks. Statistical approaches typically predicts the future by using past stock market data. Recently, financial engineers have started to predict the stock prices movement pattern by using the SNS data. SNS is the place where peoples opinions and ideas are freely flow and affect others' beliefs on certain things. Through word-of-mouth in SNS, people share product usage experiences, subjective feelings, and commonly accompanying sentiment or mood with others. An increasing number of empirical analyses of sentiment and mood are based on textual collections of public user generated data on the web. The Opinion mining is one domain of the data mining fields extracting public opinions exposed in SNS by utilizing data mining. There have been many studies on the issues of opinion mining from Web sources such as product reviews, forum posts and blogs. In relation to this literatures, we are trying to understand the effects of SNS exposures of firms on stock prices in Korea. Similarly to Bollen et al. [2011], we empirically analyze the impact of SNS exposures on stock return rates. We use Social Metrics by Daum Soft, an SNS big data analysis company in Korea. Social Metrics provides trends and public opinions in Twitter and blogs by using natural language process and analysis tools. It collects the sentences circulated in the Twitter in real time, and breaks down these sentences into the word units and then extracts keywords. In this study, we classify firms' exposures in SNS into two groups: positive and negative. To test the correlation and causation relationship between SNS exposures and stock price returns, we first collect 252 firms' stock prices and KRX100 index in the Korea Stock Exchange (KRX) from May 25, 2012 to September 1, 2012. We also gather the public attitudes (positive, negative) about these firms from Social Metrics over the same period of time. We conduct regression analysis between stock prices and the number of SNS exposures. Having checked the correlation between the two variables, we perform Granger causality test to see the causation direction between the two variables. The research result is that the number of total SNS exposures is positively related with stock market returns. The number of positive mentions of has also positive relationship with stock market returns. Contrarily, the number of negative mentions has negative relationship with stock market returns, but this relationship is statistically not significant. This means that the impact of positive mentions is statistically bigger than the impact of negative mentions. We also investigate whether the impacts are moderated by industry type and firm's size. We find that the SNS exposures impacts are bigger for IT firms than for non-IT firms, and bigger for small sized firms than for large sized firms. The results of Granger causality test shows change of stock price return is caused by SNS exposures, while the causation of the other way round is not significant. Therefore the correlation relationship between SNS exposures and stock prices has uni-direction causality. The more a firm is exposed in SNS, the more is the stock price likely to increase, while stock price changes may not cause more SNS mentions.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.27 no.4
• /
• pp.413-433
• /
• 1994

Jinhae Bay once was a productive area of fisheries. It is, however, now notorious for its red tides; and oxygen deficient water-masses extensively develop at present in summer. Therefore the shellfish production of the bay has been decreasing and mass mortality often occurs. Under these circumstances, the three-dimensional numerical hydrodynamic and the material cycle models, which were developed by the Institute for Resources and Environment of Japan, were applied to analyze the processes affecting the oxygen depletion and also to evaluate the environment capacity for the reception of pollutant loads without dissolved oxygen depletion. In field surveys, oxygen deficient water-masses were formed with concentrations of below 2.0mg/l at the bottom layer in Masan Bay and the western part of Jinhae Bay during the summer. Current directions, computed by the $M_2$ constituent, were mainly toward the western part of Jinhae Bay during flood flows and in opposite directions during ebb flows. Tidal currents velocities during the ebb tide were stronger than that of the flood tide. The comparision between the simulated and observed tidal ellipses showed fairly good agreement. The residual currents, which were obtained by averaging the simulated tidal currents over 1 tidal cycle, showed the presence of counterclockwise eddies in the central part of Jinhae Bay. Density driven currents were generated southward at surface and northward at the bottom in Masan Bay and Jindong Bay, where the fresh water of rivers entered. The material cycle model was calibrated with the data surveyed in the field of the study area from June to July, 1992. The calibrated results are in fairly good agreement with measured values within relative error of $28\%$. The simulated dissolved oxygen distributions of bottom layer were relatively high with the concentration of $6.0{\sim}8.0mg/l$ at the boundaries, but an oxygen deficient water-masses were formed within the concentration of 2.0mg/l at the inner part of Masan Bay and the western part of Jinhae Bay. The results of sensitivity analyses showed that sediment oxygen demand(SOD) was one of the most important influence on the formation of oxygen depletion. Therefore, to control the oxygen deficient water-masses and to conserve the coastal environment, it is an effective method to reduce the SOD by improving the polluted sediment. As the results of simulations, in Masan Bay, oxygen deficient water-masses recovered to 5.0mg/l when the $50\%$ reduction in input COD loads from Masan basin and $70\%$ reduction in SOD was conducted. In the western part of Jinhae Bay, oxygen deficient water-masses recovered to 5.0mg/l when the $95\%$ reduction in SOD and $90\%$ reduction in culturing ground fecal loads was conducted.

• Journal of Korean Academy of Nursing
• /
• v.28 no.4
• /
• pp.1047-1059
• /
• 1998

Senile Dementia is one of the dispositional mental disorder which has been known to the world since Hippocratic age. It has become a wide-spread social problem all over the world because of chronic disease processes and the demands of dependent care for several years as well as improbability of treatment of it at the causal level. Essentially, life styles of the older generation differ from those of the younger generation. While the fomer is used to the patriarchal system and the spirit of filial piet and respect, the latter is pragmatized and individualized under the effects of the Western material civilization. These differences between the two generations cause conflict between family members. In particular, the pain and conflict of care-givers who take care of a totally dependent dementia patient not only is inciting to the collapse of the family union, but is expanding into a serious social problem. According to this practical difficulty, this study has tried to compare dementia care-givers' experiences inter-culturally and to help set up more proper nursing interventions, describing and explaining them through ethnographies by participant observation and in-depth interviews that enable seeing them in a more close, honest and certain way. It also tries to provide a theoetical model of nusing care for dementia patients which is proper to Korean culture. This study is composed of 12 participants (4 males, 8 females) whose ages range from 37-71 years. The relations of patients are 5 spouses(3 husbands, 2 wives), 4 daughters-in-law, 2 daughters, and 1 son-in-law. The following are the care-givers' meaning of experiences that results of the study shows. The first is "psychological conflict". It contains the minds of getting angry, reproaching, being driven to dispair, blaming oneself, giving up lives, and being afraid, hopeless, and resigned. The second is "physical, social and psychological pressure" . At this stage, care-givers are shown to be under stress of both body and soul for the lack of freedom and tiredness. They also feel constraint because they hardly cope with the care and live through others' eyes. The third is "isolation". It makes the relationship of patient care-giver to be estranged, without understanding each other. They, also, experience indifference such as being upset and left alone. The forth is "acceptance" They gradually have compassion, bear up and then adapt themselves to the circumstances they are in. The fifth is "love". Now they learn to reward the other with love. It is also shown that this stage contains the process of winning others' recognition. The final is "hope". In this stage they really want situations to go smoothly and hope everything will be O.K. These consequences enable us to summarize the principles of cue experience such as, in the early stage, negative response such as physical·psychological confusion, pain and conflict are primary. Then the stage of acceptance emerges. It is an initial positive response phase when care-givers may admit their situations. As time passes by a positive response stage emerges. At last they have love and hope. Three stages we noted above : however, there are never consistent situations. Rather it gradually comes into the stage of acceptance, repeating continuous conflict, pressure and isolation. If any interest and understanding of families or the support of surrounding society lack, it will again be converted to negative responses sooner or later. Otherwise, positive responses like hope and love can be encouraged if the family and the surroundings give active aids and understanding. After all, the principles of dementia care experiences neither stay at any stage, nor develop from negative stages to positive stages steadily. They are cycling systems in which negative responses and positive responses are constantly being converted. I would like to suggest the following based on the above conclusions : First, the systematic and planned education of dementia should be performed in order to enhance public relations. Second, a special medical treatment center which deals with dementia, under government's charge, should be managed. Third, the various studies approaching dementia care experiences result in the development of more reasonable and useful nursing guidelines.

• Geophysics and Geophysical Exploration
• /
• v.9 no.1
• /
• pp.67-72
• /
• 2006

Injection of $CO_2$ into underground saline formations, due to their large storage capacity, is probably the most promising approach for the reduction of $CO_2$ emissions into the atmosphere. $CO_2$ storage must be carefully planned and monitored to ensure that the $CO_2$ is safely retained in the formation for periods of at least thousands of years. Seismic methods, particularly for offshore reservoirs, are the primary tool for monitoring the injection process and distribution of $CO_2$ in the reservoir over time provided that reservoir properties are favourable. Seismic methods are equally essential for the characterisation of a potential trap, determining the reservoir properties, and estimating its capacity. Hence, an assessment of the change in seismic response to $CO_2$ storage needs to be carried out at a very early stage. This must be revisited at later stages, to assess potential changes in seismic response arising from changes in fluid properties or mineral composition that may arise from chemical interactions between the host rock and the $CO_2$. Thus, carefully structured modelling of the seismic response changes caused by injection of $CO_2$ into a reservoir over time helps in the design of a long-term monitoring program. For that purpose we have developed a Graphical User Interface (GUI) driven rock physics simulator, designed to model both short and long-term 4D seismic responses to injected $CO_2$. The application incorporates $CO_2$ phase changes, local pressure and temperature changes. chemical reactions and mineral precipitation. By incorporating anisotropic Gassmann equations into the simulator, the seismic response of faults and fractures reactivated by $CO_2$ can also be predicted. We show field examples (potential $CO_2$ sequestration sites offshore and onshore) where we have tested our rock physics simulator. 4D seismic responses are modelled to help design the monitoring program.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.43-65
• /
• 2010

Facing a complex environment driven by a decade, many companies are adopting new strategic frameworks such as Customer Relationship Management system to achieve sustainable profitability as well as overcome serious competition for survival. In many business areas, CRM system advanced a great deal in a matter of continuous compensating the defect and overall integration. However, pharmaceutical companies in Korea were slow to accept them for usesince they still have a tendency of holding fast to traditional way of sales and marketing based on individual networks of sales representatives. In the circumstance, this article tried to empirically address current status of CRM system as well as the effects of the system on the performance of pharmaceutical companies by applying BSC method's four perspectives, from financial, customer, learning and growth and internal process. Survey by e-mail and post to employers and employees who were working in pharma firms were undergone for the purpose. Total 113 cases among collected 140 ones were used for the statistical analysis by SPSS ver. 15 package. Reliability, Factor analysis, regression were done. This study revealed that CRM system had a significant effect on improving financial and non-financial performance of pharmaceutical companies as expected. Proposed regression model fits well and among them, CRM marketing information system shed the light on substantial impact on companies' outcome given profitability, growth and investment. Useful analytical information by CRM marketing information system appears to enable pharmaceutical firms to set up effective marketing and sales strategies, these result in favorable financial performance by enhancing values for stakeholderseventually, not to mention short-term profit and/or mid-term potential to growth. CRM system depicted its influence on not only financial performance, but also non-financial fruit of pharmaceutical companies. Further analysis for each component showed that CRM marketing information system were able to demonstrate statistically significant effect on the performance like the result of financial outcome. CRM system is believed to provide the companies with efficient way of customers managing by valuable standardized business process prompt coping with specific customers' needs. It consequently induces customer satisfaction and retentionto improve performance for long period. That is, there is a virtuous circle for creating value as the cornerstone for sustainable growth. However, the research failed to put forward to evidence to support hypothesis regarding favorable influence of CRM sales representative's records assessment system and CRM customer analysis system on the management performance. The analysis is regarded to reflect the lack of understanding of sales people and respondents between actual work duties and far-sighted goal in strategic analysis framework. Ordinary salesmen seem to dedicate short-term goal for the purpose of meeting sales target, receiving incentive bonus in a manner-of-fact style, as such, they tend to avail themselves of personal network and sales and promotional expense rather than CRM system. The study finding proposed a link between CRM information system and performance. It empirically indicated that pharmaceutical companies had been implementing CRM system as an effective strategic business framework in order for more balanced achievements based on the grounded understanding of both CRM system and integrated performance. It suggests a positive impact of supportive CRM system on firm performance, especially for pharmaceutical industry through the initial empirical evidence. Also, it brings out unmet needs for more practical system design, improvement of employees' awareness, increase of system utilization in the field. On the basis of the insight from this exploratory study, confirmatory research by more appropriate measurement tool and increased sample size should be further examined.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.8 no.3
• /
• pp.113-124
• /
• 2013

The government strives to create venture ecosystem for realizing creative economy, at the same time, the Mistry of Education is spending huge resources and efforts to spread entrepreneurship education to universities in Korea. Since entrepreneurship education gives motivation to individuals and creates market innovation and these connect to the growth of national economy through increased efficiency, entrepreneurship education is becoming increasingly more important for realizing creative economy. Based on the importance, entrepreneurship education in the universities is now spreading rapidly. However, college students' entrepreneurial intention has still not been improved comparing to spreading entrepreneurship education. To overcome the poor improvement, entrepreneurship education needs to be driven more systematic direction through the study on the effect of students' motivation and environment. In this study, entrepreneurship as a part of careers perspectives, is analyzed on students' career reasons with entrepreneurial intention. For this study, 918 surveys was collected from 7 universities having entrepreneurship courses in Seoul and Gyeonggi regions in 2012 and analyzed 858 surveys in order to prove the hypothesis. The results disclosed the relationship between students' career reasons and entrepreneurial self-efficacy and intention. Motivation factors of self-realization, innovation and role model have positive effect on entrepreneurial self-efficacy following by increased entrepreneurial intention, unlike the common notion financial success and independence factors are not significant with entrepreneurial intention of students. Based on these results having meaningful implication to Korea entrepreneurship education, this study is expected to have contribution to the successful promoting the creative economy realization of our government.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.11
• /
• pp.509-520
• /
• 2015

College Scholastic Ability Test(CSAT) is a primary test to evaluate the study achievement of high-school students and used by most universities for admission decision in South Korea. Because its level of difficulty is a significant issue to both students and universities, the government makes a huge effort to have a consistent difficulty level every year. However, the actual levels of difficulty have significantly fluctuated, which causes many problems with university admission. In this paper, we build two types of data-driven prediction models to predict correct answer rate and to identify significant factors for CSAT English test through accumulated test data of CSAT, unlike traditional methods depending on experts' judgments. Initially, we derive candidate question-specific factors that can influence the correct answer rate, such as the position, EBS-relation, readability, from the annual CSAT practices and CSAT for 10 years. In addition, we drive context-specific factors by employing topic modeling which identify the underlying topics over the text. Then, the correct answer rate is predicted by multiple linear regression and level of difficulty is predicted by classification tree. The experimental results show that 90% of accuracy can be achieved by the level of difficulty (difficult/easy) classification model, whereas the error rate for correct answer rate is below 16%. Points and problem category are found to be critical to predict the correct answer rate. In addition, the correct answer rate is also influenced by some of the topics discovered by topic modeling. Based on our study, it will be possible to predict the range of expected correct answer rate for both question-level and entire test-level, which will help CSAT examiners to control the level of difficulties.

• Journal of Korea Technology Innovation Society
• /
• v.12 no.4
• /
• pp.788-818
• /
• 2009

Renewable energy refers to solar energy, biomass energy, hydrogen energy, wind power, fuel cell, coal liquefaction and vaporization, marine energy, waste energy, and liquidity fuel made out of byproduct of geothermal heat, hydrogen and coal; it excludes energy based on coal, oil, nuclear energy and natural gas. Developed countries have recognized the importance of these energies and thus have set the mid to long term plans to develop and commercialize the technology and supported them with drastic political and financial measures. Considering the growing recognition to the field, it is necessary to analysis up-to-now achievement of the government's related projects, in the standards of type of renewable energy, management of sectional goals, and its commercialization. Korean government is chiefly following suit the USA and British policies of developing and distributing renewable energy. However, unlike Japan which is in the lead role in solar rays industry, it still lacks in state-directed support, participation of enterprises and social recognition. The research regarding renewable energy has mainly examinedthe state of supply of each technology and suitability of specific region for applying the technology. The evaluation shows that the research has been focused on supply and demand of renewable as well as general energy and solution for the enhancement of supply capacity in certain area. However, in-depth study for commercialization and the increase of capacity in industry followed by development of the technology is still inadequate. 'Cost-benefit model for each energy source' is used in analysis of technology development of renewable energy and quantitative and macro economical effects of its commercialization in order to foresee following expand in related industries and increase in added value. First, Investment on the renewable energy technology development is in direct proportion both to the product and growth, but product shows slightly higher index under the same amount of R&D investment than growth. It indicates that advance in technology greatly influences the final product, the energy growth. Moreover, while R&D investment on renewable energy product as well as the government funds included in the investment have proportionate influence on the renewable energy growth, private investment in the total amount invested has reciprocal influence. This statistic shows that research and development is mainly driven by government funds rather than private investment. Finally, while R&D investment on renewable energy growth affects proportionately, government funds and private investment shows no direct relations, which indicates that the effects of research and development on renewable energy do not affect government funds or private investment. All of the results signify that although it is important to have government policy in technology development and commercialization, private investment and active participation of enterprises are the key to the success in the industry.

• Journal of Intelligence and Information Systems
• /
• v.27 no.2
• /
• pp.1-15
• /
• 2021

If it is difficult for us to make decisions, we ask for advice from friends or people around us. When we decide to buy products online, we read anonymous reviews and buy them. With the advent of the Data-driven era, IT technology's development is spilling out many data from individuals to objects. Companies or individuals have accumulated, processed, and analyzed such a large amount of data that they can now make decisions or execute directly using data that used to depend on experts. Nowadays, the recommender system plays a vital role in determining the user's preferences to purchase goods and uses a recommender system to induce clicks on web services (Facebook, Amazon, Netflix, Youtube). For example, Youtube's recommender system, which is used by 1 billion people worldwide every month, includes videos that users like, "like" and videos they watched. Recommended system research is deeply linked to practical business. Therefore, many researchers are interested in building better solutions. Recommender systems use the information obtained from their users to generate recommendations because the development of the provided recommender systems requires information on items that are likely to be preferred by the user. We began to trust patterns and rules derived from data rather than empirical intuition through the recommender systems. The capacity and development of data have led machine learning to develop deep learning. However, such recommender systems are not all solutions. Proceeding with the recommender systems, there should be no scarcity in all data and a sufficient amount. Also, it requires detailed information about the individual. The recommender systems work correctly when these conditions operate. The recommender systems become a complex problem for both consumers and sellers when the interaction log is insufficient. Because the seller's perspective needs to make recommendations at a personal level to the consumer and receive appropriate recommendations with reliable data from the consumer's perspective. In this paper, to improve the accuracy problem for "appropriate recommendation" to consumers, the recommender systems are proposed in combination with context-based deep learning. This research is to combine user-based data to create hybrid Recommender Systems. The hybrid approach developed is not a collaborative type of Recommender Systems, but a collaborative extension that integrates user data with deep learning. Customer review data were used for the data set. Consumers buy products in online shopping malls and then evaluate product reviews. Rating reviews are based on reviews from buyers who have already purchased, giving users confidence before purchasing the product. However, the recommendation system mainly uses scores or ratings rather than reviews to suggest items purchased by many users. In fact, consumer reviews include product opinions and user sentiment that will be spent on evaluation. By incorporating these parts into the study, this paper aims to improve the recommendation system. This study is an algorithm used when individuals have difficulty in selecting an item. Consumer reviews and record patterns made it possible to rely on recommendations appropriately. The algorithm implements a recommendation system through collaborative filtering. This study's predictive accuracy is measured by Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). Netflix is strategically using the referral system in its programs through competitions that reduce RMSE every year, making fair use of predictive accuracy. Research on hybrid recommender systems combining the NLP approach for personalization recommender systems, deep learning base, etc. has been increasing. Among NLP studies, sentiment analysis began to take shape in the mid-2000s as user review data increased. Sentiment analysis is a text classification task based on machine learning. The machine learning-based sentiment analysis has a disadvantage in that it is difficult to identify the review's information expression because it is challenging to consider the text's characteristics. In this study, we propose a deep learning recommender system that utilizes BERT's sentiment analysis by minimizing the disadvantages of machine learning. This study offers a deep learning recommender system that uses BERT's sentiment analysis by reducing the disadvantages of machine learning. The comparison model was performed through a recommender system based on Naive-CF(collaborative filtering), SVD(singular value decomposition)-CF, MF(matrix factorization)-CF, BPR-MF(Bayesian personalized ranking matrix factorization)-CF, LSTM, CNN-LSTM, GRU(Gated Recurrent Units). As a result of the experiment, the recommender system based on BERT was the best.