• Journal of Information Technology Services
• /
• v.17 no.1
• /
• pp.79-89
• /
• 2018

Sentiment analysis is a technique of text mining that extracts feelings of the person who wrote the sentence like movie review. The preliminary researches of sentiment analysis identify sentiments by using the dictionary which contains negative and positive words collected in advance. As researches on deep learning are actively carried out, sentiment analysis using deep learning model with morpheme or word unit has been done. However, this model has disadvantages in that the word dictionary varies according to the domain and the number of morphemes or words gets relatively larger than that of phonemes. Therefore, the size of the dictionary becomes large and the complexity of the model increases accordingly. We construct a sentiment analysis model using recurrent neural network by dividing input data into phoneme-level which is smaller than morpheme-level. To verify the performance, we use 30,000 movie reviews from the Korean biggest portal, Naver. Morpheme-level sentiment analysis model is also implemented and compared. As a result, the phoneme-level sentiment analysis model is superior to that of the morpheme-level, and in particular, the phoneme-level model using LSTM performs better than that of using GRU model. It is expected that Korean text processing based on a phoneme-level model can be applied to various text mining and language models.

• The Mathematical Education
• /
• v.53 no.3
• /
• pp.329-355
• /
• 2014

The purpose of this study is to understand the difference of cognitive structure depending on the level of the 6th graders' problem-solving abilities about the division of fraction and to propose a method for improving the 6th graders' understanding about the division of fraction through the word association test. The following is the findings from this study. 1)The lower level students' is, the lower the step that the chunk appeared in cognitive structure is. 2)The basic level students' association frequency between any two concepts was less than the excellent level students and the ordinary level students' it. 3)The basic level students' connection number between concepts was far less than the excellent level students and the ordinary level students' it. 4)The connection between natural number and unit fractions, subtraction of fraction and division of fraction, division of fraction and reduction to common denominator, and division of fraction and common multiple that expected in this study did not appear in the three groups.

• International Journal of Human Ecology
• /
• v.16 no.2
• /
• pp.11-20
• /
• 2015

The purpose of this study was to examine the effects of the construal level and temporal distance of a message and consumer's Social Network Service (SNS) self-efficacy on consumers' attitudes toward SNS fashion advertising. This study employed a 2 (message configuration: high construal level/low construal level) ${\times}$ 2 (temporal distance: distant future/near future) ${\times}$ 2 (SNS self-efficacy: high/low) between-subject factorial design. The survey was conducted on Facebook users in their twenties (N=216). The results are as follows: First, attitude toward SNS fashion advertising and purchase intention was higher when the message construal level was lower and when the temporal distance was closer. Second, no interactions between temporal distance and message construal level for attitude toward SNS advertising and purchase intention were found in this study. However, interactions between temporal distance and SNS self-efficacy for attitude toward SNS advertising and purchase intention were found. When the SNS self-efficacy was high, message with the low construal level reacted significantly positive in terms of attitude toward the ad as well as purchase intention. It is expected that this study will provide insight for apparel makers or retailers to use SNS as a new advertising media for fashion marketing. Practical implications and limitations are discussed.

• Journal of Korea Planning Association
• /
• v.53 no.6
• /
• pp.19-38
• /
• 2018

The purpose of this study is to examine the impacts of neighborhood sports activity facilities on the exercise time and subjective health level using the National Sport Participation Survey data(2013-2015) in Seoul, Korea. We conducted path analysis including exercise time, subjective health level and various environmental factors. From the survey data, we extracted individual's characteristics including subjective health and exercise time. In addition, we calculated physical environment variables of neighborhood units. The results of this study are as follow. First, most of moderating variables such as gender, age, income and job showed expected relationships with exercise time or subjective health level. Second, the perceived level regarding neighborhood sports facilities such as public sports facilities had a strong positive association with exercise time and subjective health level. Third, the area of public sports facility, neighborhood park and the number of schools had positive effects on the exercise time and subjective health level. Lastly, land use mix and the number of intersections showed a positive effects on exercise time. To sum up, the results indicated that public sports facility, neighborhood park and perceived environment on neighborhood sports facility are critical factors of residents' exercise time and subjective health level.

• Journal of the Korean School Mathematics Society
• /
• v.23 no.3
• /
• pp.397-425
• /
• 2020

Statistical literacy is a key ability expected of citizens in information-laden societies, and is often revealed as an expected outcome of schooling and as a necessary component of adults' numeracy and literacy. Knowing how important statistical literacy is, the purpose of this research was to measure statistical literacy of adults and secondary mathematics teachers. This study explored the statistical literacy based on the level of understanding in poll results and analyzed the data obtained through semi-structured interviews with 20 secondary mathematics teachers and 20 adults. As a result, the following conclusions were obtained: First, few secondary mathematics teachers and adults correctly recognized the meaning of statistical terms and expressions included in the poll results. Second, 70% of research participants did not reach levels 3 or 4 of statistical literacy levels. Third, the statistical literacy level of secondary mathematical teachers was higher than that of adults.

• Journal of Elementary Mathematics Education in Korea
• /
• v.11 no.1
• /
• pp.81-98
• /
• 2007

In order to help students learn geometric concepts in mathematics in an easy and interesting way, the present study restructured the textbook so that it utilizes GSP based on van Hiele's theory. In addition, we purposed to examine how effective the restructured textbook is in enhancing students' van Hiele level and to lay a base for the active use of GSP in learning figures in elementary school. In conclusion, the results of this study is expected to solve problems in the structure of the current textbook such as the violation of continuity in van Hiele's theory and inconsistency between the level of textbook contents and students' level through the restructuring of the textbook using GSP and provide helps for effective figure learning. In addition, this research is expected to be an opportunity for the active use of GSP in teaching figures in elementary school.

• Journal of the Korean Society for Railway
• /
• v.11 no.4
• /
• pp.378-383
• /
• 2008

In December 2006, the Ministry of Environment Republic of Korea established the guideline which is "Indoor Air Quality Management Guidelines in Public Transportation." as control items, $CO_2$ (carbon dioxide) and PM10 (particle matter) are classified two categories, that is, Level 1 (non-rush hour), Level 2 (rush hour). Therefore, the quality of air in train and subway should be controlled in accordance with the guideline. We took a measure the air freshness inside train twice at Line 4 (Tangogae-Oido), in Sep. 2007 and at Line 1 (Dongincheon-Yongsan) in Nov. 2007, respectively and, also expected the emitted $CO_2$ concentration by using a property of matter such as EMU (Electric Multiple Unit) design reviewing specification and air. According to the measured values, the concentration of PM10 was 44, 57, 45% and the concentration of $CO_2$ was 39, 36, 44% respectively, all measured values are within the guideline and also, as a result we found the expected value and measured value are similar.

• Industrial Engineering and Management Systems
• /
• v.8 no.2
• /
• pp.80-92
• /
• 2009

This paper addresses the inventory rationing issue embedded in the regional supply chain inventory replenishment problem (RSIRP). The concerned supply chain, which was fed by the national supply chain, consisted of a single warehouse distributing a single product to multiple stores (M-stores) with independent and normally distributed customer demand. It was assumed that the supply chain operated under the order-up-to level inventory replenishment system and had only one truck at the regional warehouse. The truck could make one replenishment trip to one store per period (a round trip per period). Based on current inventories and the vehicle constraint, the warehouse must make two decisions in each period: which store in the region to replenish and what was the replenishment quantity? The objective was to position inventories so as to minimize lost sales in the region. The warehouse inventory was replenished in every fixed-interval from a source outside the region, but the store inventory could be replenished daily. The truck destination (store) in each period was selected based on its maximum expected shortage. The replenishment quantity was then determined based on the predetermined order-up-to level system. In case of insufficient warehouse inventories to fulfill all projected store demands, an inventory rationing rule must be applied. In this paper, a new inventory rationing rule named Expected Cost Minimization (ECM) was proposed based on the practical purpose. The numerical results based on real data from a selective industry show that its performance was better and more robust than the current practice and other sharing rules in the existing literature.

• Journal of the Korean Society of Safety
• /
• v.28 no.3
• /
• pp.107-113
• /
• 2013

Problem solving and/or decision making process usually encountered in human living consists of a sequence of human behaviors based upon his/her knowledge. Thus, Rasmussen introduced Skill-Rule-Knowledge paradigm to countermeasure human errors that can occur in Nuclear Power Plants. Unfortunately however, it was not so easy as expected since objective evidence have not been obtainable with conventional research techniques. With the help of EEG band pawer ratio techniques, this study tried to get psycho-physiological symptoms of human errors, if any, while human beings perform knowledge-based behaviors such as simple arithmetic computations with different difficulty level. A set of simulated works was carried out with a computer station. Four kinds of arithmetic computation tasks were given to 10 health male under-graduate students on different day individually, and during the experiment, EEG and ECG was measured continuously for objective psycho-physiological analysis. According to the results, ${\alpha}$/(${\alpha}+{\beta}$) as well as ${\alpha}/{\beta}$ band power ratio were sensitive to task difficulty level which consistently decreased both. However, any one of them failed to reveal the influence of tasks with different difficulty level in the aspect of task duration time. On the contrary, Heart Rate Variability was more suggestive than expected. To make a conclusion, it can be said that band power of EEG waves will be helpful in not only assessment of work difficulty level but also assessment of workers' skill development if supported by cardiac function such as HRV.

• Journal of Soil and Groundwater Environment
• /
• v.19 no.3
• /
• pp.123-133
• /
• 2014

It is important to predict the groundwater level fluctuation for effective management of groundwater monitoring system and groundwater resources. In the present study, three different time series models for the prediction of groundwater level in response to rainfall were built, those are transfer function noise model (TFNM), artificial neural network (ANN), and adaptive neuro fuzzy interference system (ANFIS). The models were applied to time series data of Boen, Cheolsan, and Hongcheon stations in National Groundwater Monitoring Network. The result shows that the model performance of ANN and ANFIS was higher than that of TFNM for the present case study. As lead time increased, prediction accuracy decreased with underestimation of peak values. The performance of the three models at Boen station was worst especially for TFNM, where the correlation between rainfall and groundwater data was lowest and the groundwater extraction is expected on account of agricultural activities. The sensitivity analysis for the input structure showed that ANFIS was most sensitive to input data combinations. It is expected that the time series model approach and results of the present study are meaningful and useful for the effective management of monitoring stations and groundwater resources.