• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.5
• /
• pp.482-488
• /
• 2014

This paper aims to analyze user's emotion automatically by analyzing Twitter, a representative social network service (SNS). In order to create sentiment analysis models by using machine learning techniques, sentiment labels that represent positive/negative emotions are required. However it is very expensive to obtain sentiment labels of tweets. So, in this paper, we propose a sentiment analysis model by using self-training technique in order to utilize "data without sentiment labels" as well as "data with sentiment labels". Self-training technique is that labels of "data without sentiment labels" is determined by utilizing "data with sentiment labels", and then updates models using together with "data with sentiment labels" and newly labeled data. This technique improves the sentiment analysis performance gradually. However, it has a problem that misclassifications of unlabeled data in an early stage affect the model updating through the whole learning process because labels of unlabeled data never changes once those are determined. Thus, labels of "data without sentiment labels" needs to be carefully determined. In this paper, in order to get high performance using self-training technique, we propose 3 policies for updating "data with sentiment labels" and conduct a comparative analysis. The first policy is to select data of which confidence is higher than a given threshold among newly labeled data. The second policy is to choose the same number of the positive and negative data in the newly labeled data in order to avoid the imbalanced class learning problem. The third policy is to choose newly labeled data less than a given maximum number in order to avoid the updates of large amount of data at a time for gradual model updates. Experiments are conducted using Stanford data set and the data set is classified into positive and negative. As a result, the learned model has a high performance than the learned models by using "data with sentiment labels" only and the self-training with a regular model update policy.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.22 no.3
• /
• pp.182-191
• /
• 2011

Objectives: The aim of this study was to investigate the sleep patterns of South Korean elementary school children and whether the differences in sleep patterns were related to behavior, emotional problems, attention and academic performance. Method: This study included a community sample of 268 boys and girls from fourth-, fifth- and sixth-grade classes in a South Korean metropolitan city from November to December 2010. The primary caregivers completed a questionnaire that included information on demographic characteristics, as well as the Child's Sleep Habit Questionnaire (CSHQ), the Korean version of Child Behavior Checklist (K-CBCL), the Korean version of the Learning Disability Evaluation Scale (K-LDES), the Korean version of ADHD Rating Scale (K-ARS) and the Disruptive Behavior Disorder Scale (DBDS). We conducted analyses on the CSHQ individual items, between the subscales, on the total scores and on the K-CBCL, the K-LEDS, the K-ARS and the DBDS. Results: Based on the findings from the CHSQ, the subjects had significantly higher scores for bedtime resistance ($9.18{\pm}2.17$), delayed sleep onset ($1.32{\pm}0.62$), the sleep duration ($4.19{\pm}1.52$) and daytime sleepiness ($14.10{\pm}3.55$) than the scores from the previous reports on children from western countries. The total CHSQ score showed positive correlations to all subscales of the K-CBCL : withdrawn (r=0.24, p<.005), somatic complaint (r=0.24, p<.005) and anxious/depressive (r=0.38, p<.005). Bedtime resistance was associated with oppositional defiant disorder (r=0.15, p<.05) and a positive correlation was demonstrated between sleep anxiety and the oppositional defiant disorder score (r=0.13, p<.05), night waking and the conduct disorder score (r=0.16, p<.05). Delayed sleep onset was related with low performance on the K-LDES with respect to thinking (r=-0.17, p<.05) and mathematical calculation (r=-0.17, p<.05). Conclusion: The results of this study reconfirm Korean children's problematic sleep patterns. Taken together the results provide that the reduced sleep duration and disruption of sleep pattern can have a significant impact on emotion, behavior, performance of learning in children. Further studies concerning more diverse psychosocial factors affecting sleep pattern will be helpful to understanding of the sleep health in Korean children.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.199-219
• /
• 2018

With the everyday use of the Internet and the spread of various smart devices, users have been able to communicate in real time and the existing communication style has changed. Due to the change of the information subject by the Internet, data became more massive and caused the very large information called big data. These Big Data are seen as a new opportunity to understand social issues. In particular, text mining explores patterns using unstructured text data to find meaningful information. Since text data exists in various places such as newspaper, book, and web, the amount of data is very diverse and large, so it is suitable for understanding social reality. In recent years, there has been an increasing number of attempts to analyze texts from web such as SNS and blogs where the public can communicate freely. It is recognized as a useful method to grasp public opinion immediately so it can be used for political, social and cultural issue research. Text mining has received much attention in order to investigate the public's reputation for candidates, and to predict the voting rate instead of the polling. This is because many people question the credibility of the survey. Also, People tend to refuse or reveal their real intention when they are asked to respond to the poll. This study collected comments from the largest Internet portal site in Korea and conducted research on the 19th Korean presidential election in 2017. We collected 226,447 comments from April 29, 2017 to May 7, 2017, which includes the prohibition period of public opinion polls just prior to the presidential election day. We analyzed frequencies, associative emotional words, topic emotions, and candidate voting rates. By frequency analysis, we identified the words that are the most important issues per day. Particularly, according to the result of the presidential debate, it was seen that the candidate who became an issue was located at the top of the frequency analysis. By the analysis of associative emotional words, we were able to identify issues most relevant to each candidate. The topic emotion analysis was used to identify each candidate's topic and to express the emotions of the public on the topics. Finally, we estimated the voting rate by combining the volume of comments and sentiment score. By doing above, we explored the issues for each candidate and predicted the voting rate. The analysis showed that news comments is an effective tool for tracking the issue of presidential candidates and for predicting the voting rate. Particularly, this study showed issues per day and quantitative index for sentiment. Also it predicted voting rate for each candidate and precisely matched the ranking of the top five candidates. Each candidate will be able to objectively grasp public opinion and reflect it to the election strategy. Candidates can use positive issues more actively on election strategies, and try to correct negative issues. Particularly, candidates should be aware that they can get severe damage to their reputation if they face a moral problem. Voters can objectively look at issues and public opinion about each candidate and make more informed decisions when voting. If they refer to the results of this study before voting, they will be able to see the opinions of the public from the Big Data, and vote for a candidate with a more objective perspective. If the candidates have a campaign with reference to Big Data Analysis, the public will be more active on the web, recognizing that their wants are being reflected. The way of expressing their political views can be done in various web places. This can contribute to the act of political participation by the people.