• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.1-27
• /
• 2017

It is known that the economic sentiment index and macroeconomic indicators are closely related because economic agent's judgment and forecast of the business conditions affect economic fluctuations. For this reason, consumer sentiment or confidence provides steady fodder for business and is treated as an important piece of economic information. In Korea, private consumption accounts and consumer sentiment index highly relevant for both, which is a very important economic indicator for evaluating and forecasting the domestic economic situation. However, despite offering relevant insights into private consumption and GDP, the traditional approach to measuring the consumer confidence based on the survey has several limits. One possible weakness is that it takes considerable time to research, collect, and aggregate the data. If certain urgent issues arise, timely information will not be announced until the end of each month. In addition, the survey only contains information derived from questionnaire items, which means it can be difficult to catch up to the direct effects of newly arising issues. The survey also faces potential declines in response rates and erroneous responses. Therefore, it is necessary to find a way to complement it. For this purpose, we construct and assess an index designed to measure consumer economic sentiment index using sentiment analysis. Unlike the survey-based measures, our index relies on textual analysis to extract sentiment from economic and financial news articles. In particular, text data such as news articles and SNS are timely and cover a wide range of issues; because such sources can quickly capture the economic impact of specific economic issues, they have great potential as economic indicators. There exist two main approaches to the automatic extraction of sentiment from a text, we apply the lexicon-based approach, using sentiment lexicon dictionaries of words annotated with the semantic orientations. In creating the sentiment lexicon dictionaries, we enter the semantic orientation of individual words manually, though we do not attempt a full linguistic analysis (one that involves analysis of word senses or argument structure); this is the limitation of our research and further work in that direction remains possible. In this study, we generate a time series index of economic sentiment in the news. The construction of the index consists of three broad steps: (1) Collecting a large corpus of economic news articles on the web, (2) Applying lexicon-based methods for sentiment analysis of each article to score the article in terms of sentiment orientation (positive, negative and neutral), and (3) Constructing an economic sentiment index of consumers by aggregating monthly time series for each sentiment word. In line with existing scholarly assessments of the relationship between the consumer confidence index and macroeconomic indicators, any new index should be assessed for its usefulness. We examine the new index's usefulness by comparing other economic indicators to the CSI. To check the usefulness of the newly index based on sentiment analysis, trend and cross - correlation analysis are carried out to analyze the relations and lagged structure. Finally, we analyze the forecasting power using the one step ahead of out of sample prediction. As a result, the news sentiment index correlates strongly with related contemporaneous key indicators in almost all experiments. We also find that news sentiment shocks predict future economic activity in most cases. In almost all experiments, the news sentiment index strongly correlates with related contemporaneous key indicators. Furthermore, in most cases, news sentiment shocks predict future economic activity; in head-to-head comparisons, the news sentiment measures outperform survey-based sentiment index as CSI. Policy makers want to understand consumer or public opinions about existing or proposed policies. Such opinions enable relevant government decision-makers to respond quickly to monitor various web media, SNS, or news articles. Textual data, such as news articles and social networks (Twitter, Facebook and blogs) are generated at high-speeds and cover a wide range of issues; because such sources can quickly capture the economic impact of specific economic issues, they have great potential as economic indicators. Although research using unstructured data in economic analysis is in its early stages, but the utilization of data is expected to greatly increase once its usefulness is confirmed.

• Journal of Preventive Medicine and Public Health
• /
• v.7 no.1
• /
• pp.1-28
• /
• 1974

The writers have conducted the investigation to assess the nutritional status of young rural Korean children aged from 0 to 4 years old in August 1971. The survey areas were Kaejong-myon. Daeya-myon, Okku-gun, Jeonra-bukdo, Korea. These survey areas were typical agricultural plain areas. The total numbers of children examined were 2,706 comprising 1,394 male and 1,312 female. The weight, height, and chest circumference of children were measured and means and standard deviations. were calculated for each measurement. In addition, the nutritional status of each child was classified by the four levels of malnutrition and the Gomez classification, The examination of red blood cell count, haematocrit value, and intestinal parasite infection were carried out at the same time. In general, recent work tend to suggest that environmental influences, especially nutrition, are of great importance than genetic background or other biological factors for physical growth and development. Certainly the physical dimensions of the body are much influenced by nutrition, particularly in the rapidly growing period of early childhood. Selected body measurements can therefore give valuable information concerning protein-calory malnutrition. Growth can also be affected by bacterial, viral, and parasitic infection. For the field workers in a developing country, therefore, nutritional anthropometry appears to be of greatest value in the assessment of growth failure and undernutrition, principally from lack of protein and calories. In order to compare and evaluate the data obtained, the optimal data of growth from the off-spring of the true well-fed, medically and socially protected are needed. So-called 'Standards' that have been compiled for preschool children in Korea, however, are based on measurement of children from middle or lower socio-economic groups, who are, in fact, usually undernourished from six months of age onwards and continuously exposed to a succession of infective and parasitic diseases. So that, the Harvard Standards which is one of the international reference standards was used as the reference standards in this study. Findings of the survey were as follows: A. Anthropometric data: 1) Comparing the mean values for body weight obtained with the Korean standard weight of the same age, the rural Korean children were slightly haevier than the Korean standard values in both sexes. Comparing with the Japanese children values, the rural Korean children were slightly haevier in male and in the infant period of female but lighter in female of the period of 1 to 4 years old than Japanese children. 2) Comparing the mean values for height obtained with the Korean standard height of the same age, the rural Korean children were taller than the Korean standard values except the second half of infatn period in both sexes. Comparing with the Japanese children, the rural Korean children were slightly smaller than Japanese children except the first half of infant peroid in both sexes. 3) Mear values of chest circumference of rural Korean children obtained were less than the Korean standard values of the same ages in both sexes. B. Prevalence of Protein-Calory Malnutrition: Children examined were devided into two groups, i. e., infant(up to the first birthday) and toddler (1 to 4 fears old). 1) Percentages of four levels of malnutrition: a) When the nutrtional status of each child was classified (1) by body weight value, the percentages for male and female of children attained standard growth were 52.8%(infant 83.3%, toddler 44.4%) and 39.7% (infant 74.5%. toddler 30.5%), the first level of malnutrition were 31.9%(infant 13.7%, toddler 36.9%) and 31.7%(infant 15.3%, toddler 36,0%), the second level of malnutrition were 12.3%(infant 1.7%, toddler 15.3%) and 23.3% (infant 7.7%, fodder 27.5%), the third level of malnutrition were 2.7%(infant 0.7%, toddler 3.2%) and 4.6%(infant 1.8%, toddler 5.3%) the fourth level of malnutrition were 0.3% (infant 0.7%, toddler 0.2%) and 0.7% (0.7% for infant and toddler) respectively. (2) by height value, the percentages for male and female of children attained standard growth were 80.3% (infant 97.3%, toddler 75.6%) and 75.1% (infant 96.4%, toddler 69.5), the first level of malnutrition were 17.9% (infant 2.0%, toddler 22.3%) and 23.6% (infants 3.6%, toddler 28.8%), the second level of malnutrition were 1.2% (infant 0.3%, toddler 1.5%) and 1.1% (infant 0%, toddler 1.4%), the third level of malnutrition were 0.4%(infant 0.3%, toddler 0.5%) and 0.2%(infant 0%, toddler 0.3%), the fourth level of malnutrition were 0.1%(infant 0%, toddler 0.1%) and 0% respectively. (3) by body weight in relation to height, the percentages for male and female of children attained standard growth were 87.9% (infant 77.6%, toddler 87.9%) and 78.2% (infant 77.4%, toddler 78.2%), the first level of malnutrition were 12.2% (infant 18.4%, toddler 10.6%) and 18.2% (infant 17.9%, toddler 18.3%), the second level of malnutrition were 1.9%(infant 3.3%, toddler 1.5%) and 3.0%(infant 3.3%, toddler 2.9%), the third level of malnutrition were 0.1%(infant 0%. toddler 0.1%) and 0.5% (infant 0%, toddler 0.6%), the fourth level of malnutrition were 0.1%(infant 0.7%, toddler 0%) and 0.3% (infant 1.5%, toddler 0%) respectively. b) When the nutritional status of each child according to the mother's age at perturition, i. e., young aged mother (up to 30 years old), middle aged mother (31 to 40 years old) and old aged mother (41 years or above) was classified (1) by body weight, among infants and toddlers, at each year of age, with increasing the mother's age, there was an increase in percentage of subjects underweight. This tendency of increasing percentage of underweight was more significant in the infant period than the toddler period. (2) by height value, no significant differences between each mother's age group were found. c) When the nutritional status of each child according to the birth rank, i. e., lower birth rank (first to third) and higher birth rank (fourth or above) was classified (1) by weight value, children of higher birth rank were slightly more often underweight than those of lower birth rank, but not significant. (2) by height value, no differences were found between children of lower and higher birth rank. 2) Gomez Classification: When the nutritional status of each child was classified a) by body weight value, the percentages for male and female of children. attained standard growth were 53.1% (infant 82.6%, toddler 44.9%) and 39.2% (infant 73.4%, toddler 30.1%), the first degree of malnutrition were 39.4% (infant 14.7%, toddler 46.2%) and 47.1% (infant 21.9%, toddler 53.8%), the second degree of malnutrition were 7.3%(infant 2.3%, toddler 8.6%) and 12.9% (infant 4.0%, toddler 15.2%). and the third degree of malnutrition were 0.2%. (infant 0.3%, toddler 0.2%) and 0.8% (infant 0.7%, toddler 0.9%) respectively. b) by height value, the percentages for male and female of children attained standard growth were 80.8% (infant 97.0%, toddler 76.3%) and 73.8%(infant 95.6%, toddler 68.0%), the first degree of malnutrition were 18.5% (infant 2.7%, toddler 22.9%) and 24.6% (infant 4.4%, toddler 30.0%), the second degree of malnutrition were 0.6%(infant 0.3%, toddler 0.7%) and 0.5% (infant 0.1%, toddler 0.7%), and the third degree of malnutrition were 0.1%(infant 0%, toddler 0.1%) and 1.1% (infant 0%, toddler 1.3%) respectively. C. Results of clinical laboratory examination: 1) Red blood cells: The ranges of mean red blood cell counts for male and female were $3,538,000/mm^3\;to\;4,403,000/mm^3\;and\;3,576,000/mm^3\;to\;4,483,000/mm^3$ respectively. The lowest red cell counts were seen at the age of 0-3 months for male and 1-2 months for female. 2) Haematocrit value : The ranges of haematocrit value of male and female were 35.1% to 38.8% and 34.7% to 38.8% respectively. The lowest haematocrit values were seen at the age of 2-3 months for male and 1-2, months for female. 3) The prevalence rates of intestinal parasites for male and female children with Ascaris lumbricoides were 34.1% (infant 18.8%, toddler 38.1%) and 36.0%(infant 18.4%, toddler 40.7%), with Trichocephalus trichiuris were 6.8% (infant 2.9%, toddler 7.9%) and 9.0% (infant 3.0%, toddler 10.6%), with Hookworm were 0.3% (infant 0.5%, toddler 0.2%) and 0.3% (infant 0.5%, toddler 0.3%), with Clonorchis sinensis were 0.4%(infant 0%, toddler 0.5%) and 0.1%(infant 0%, toddler 0.1%) respectively.