• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.117-126
• /
• 2013

Recently, as Social Network Services(SNS), such as Twitter, Facebook, are becoming more popular, much research has been doing on opinion mining. However, current related researches are mostly focused on sentiment classification or feature selection, but there were few studies about opinion document retrieval. In this paper, we propose a new retrieval method of short opinion documents. Proposed method utilizes previous sentiment classification methodology, and applies several features of documents for evaluating the quality of the opinion documents. For generating the retrieval model, we adopt Learning-to-rank technique and integrate sentiment classification model to Learning-to-rank. Experimental results show that proposed method can be applied successfully in opinion search.

• Journal of IKEEE
• /
• v.20 no.3
• /
• pp.235-240
• /
• 2016

In this study, we use the data collected from Twitter, as an SNS(Social Networking Service), for service innovation. This data was collected and processed by Flume. The data set in May 2016 was 4,766 and 15,543 from company S and company X, respectively. We were able to figure out the emotional atmosphere of the two companies through the sentiment analysis(SA) and to find out about the vertical relationship through the bibliometric analysis(BA). Furthermore, we were able to grasp the horizontal relationship through the social network analysis(SNA). It was concluded that SNS was worth while to derive an innovative item.

• Korean journal of communication and information
• /
• v.61
• /
• pp.134-158
• /
• 2013

The public trades information through social media during crises. The use of social media during crises has been increased steadily. However, there are few studies done on the effects of social media use on crisis perception. The goal of this study is to examine how social media affect an organization's ability to manage crises. The study specifically tries to investigate how media types, organization-public relationships, and image restoration strategies affect the public's perception of crises. An experiment was conducted to test research questions by presenting crisis scenarios and observing how newspapers and the social media Twitter affected the crisis. According to a three-way ANOVA test, the type of media and image restoration strategies had an interaction effect on the public's perception of crises. Also, the type of media, organization-public relationship, and image restoration strategies had a three way effect toward the acceptance of crisis communication strategies. As a result, it can be said that the public's perception and acceptances of crisis communication were different depending on the type of media used. The effectiveness of social media was proved, and it was seen that to be able to effectively use social media, each organization must have different strategies depending on their needs.

• The Journal of the Korea Contents Association
• /
• v.14 no.8
• /
• pp.74-83
• /
• 2014

This study was conducted for the overall analysis for the interests, generally and uses of SNS (Social Network Service) of the overseas dance arts company. The subjects of this study were total 3,614 of countries, public, private and personal dance arts company in 100 countries on six continents. The selected 627 company which operate at least one SNS, and included them in this study. Then analyzed the SNS utilization six continental areas as per dance gener, types, and dance gener analyzed as per types. Also analyzed the SNS utilization six continental areas, dance gener as per types and obtained the following result First, It appeared that Ballet company of North America continent took advantage of SNS the most. Second, It appeared that Facebook, Twitter of North America was the most frequently used. Third, It appeared that Facebook wsa the most frequently used by traditional dance company. Fourth. Facebook, Twitter, Youtube were the most activity used by Ballet company of North America continent. In conclusion, this study recommends the policy alternatives related to the awareness of digital media, the establishment of the SNS marketing information system.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.28 no.2
• /
• pp.57-78
• /
• 2017

SNS is a useful tool to quickly deliver information in an emergency given their speed and expandability. Especially, SNS in the event of a disaster or an accident can offer on-site, accurate and detailed updates about essential information such as the safety of victims and the development of the situation, served as a valuable complement to the conventional media. This study aims to perform a comparative analysis on how social media are currently used by emergency management authorities in South Korea and other countries. Based on the results, this study proposed more effective ways to exploit SNS and improve efficiency of disaster management. To accomplish the goals, this study collected tweet information from various sources including the FEMA of the U. S., the FDMA and the Central Disaster Council of Japan, and the MPSS of Korea. The collected tweet information was analyzed by feedback, time series, and information types. The feedback analysis aims to quantify the number of monthly user feedback in order to assess user satisfaction about the tweet information. The time series analysis identifies the number of tweet information, feedback index and keywords by country for certain duration, examining why certain messages showed high feedback indices and what kind of contents should be offered by the authorities. Finally, the analysis of information type reviews the type of information contained in the tweet information that drew users' attention to identify the information type in which the authorities should deliver information to users. Based on these analyses, this study proposed improvement methods to use Tweeter in MPSS.

• Journal of the Korean Society for Library and Information Science
• /
• v.56 no.3
• /
• pp.47-72
• /
• 2022

This study aims to understand the trends of subjects related to real estate policies and public's emotional opinion on the policies. Two keywords related to real estate policies such as "real estate policy" and "real estate measure" were used to collect tweets created from February 25, 2008 to August 31, 2021. A total of 91,740 tweets were collected and we applied sentiment analysis and dynamic topic modeling to the final preprocessed and categorized data of 18,925 tweets. Sentiment analysis and dynamic topic model analysis were conducted for a total of 18,925 posts after preprocessing data and categorizing them into supply, real estate tax, interest rate, and population variance. Keywords of each category are as follows: the supply categories (rental housing, greenbelt, newlyweds, homeless, supply, reconstruction, sale), real estate tax categories (comprehensive real estate tax, acquisition tax, holding tax, multiple homeowners, speculation), interest rate categories (interest rate), and population variance categories (Sejong, new city). The results of the sentiment analysis showed that one person posted on average one or two positive tweets whereas in the case of negative and neutral tweets, one person posted two or three. In addition, we found that part of people have both positive as well as negative and neutral opinions towards real estate policies. As the results of dynamic topic modeling analysis, negative reactions to real estate speculative forces and unearned income were identified as major negative topics and as for positive topics, expectation on increasing supply of housing and benefits for homeless people who purchase houses were identified. Unlike previous studies, which focused on changes and evaluations of specific real estate policies, this study has academic significance in that it collected posts from Twitter, one of the social media platforms, used emotional analysis, dynamic topic modeling analysis, and identified potential topics and trends of real estate policy over time. The results of the study can help create new policies that take public opinion on real estate policies into consideration.

• Journal of the Korea Convergence Society
• /
• v.9 no.11
• /
• pp.179-192
• /
• 2018

The purpose of this study is to research the design solutions that should be taken into consideration when developing mobile applications of Mindfulness Training. We aim to provide basic UI / UX design guidances for being effectiveness of mobile application of Mindfulness Training. For this purpose, We research in various aspects. Base on this, We select an approach and apply the application screen prototypes. We suggest some points for to be considered in the development of UI / IX design for mobile applications for Mindfulness Training based on obtained knowledge through this research process.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.5
• /
• pp.37-48
• /
• 2022

With development of Digital Technology, social issues are communicated through digital-based platform such as SNS and form public opinion. This study attempted to analyze big data from Twitter, a world-renowned social network service, and find out the public opinion. After collecting Twitter data based on 14 keywords for 1 year in 2021, analyzed the term-frequency and relationship among keyword documents with pearson correlation coefficient using Data-mining Technology. Furthermore, the 6 main topics that on the center of information security field in 2021 were derived through topic modeling using the LDA(Latent Dirichlet Allocation) technique. These results are expected to be used as basic data especially finding key agenda when establishing strategies for the next step related industries or establishing government policies.

• 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.

• Spatial Information Research
• /
• v.22 no.4
• /
• pp.21-38
• /
• 2014

Since users who search maps conduct their searching using the name they already know or is commonly called rather than formal name of a specific place, they tend to fail to find their destination. In addition, in typical web map service in terms of spatial searching of map. Location information of unintended place can be provided because when spatial searching is conducted with the vocabulary 'nearby' and 'in the vicinity', location exceeding 2 km from the current location is searched altogether as well. In this research, spatial range that human can perceive is calculated by extracting POI date with the usage of twitter data of SNS, constructing spatial relations with existing POI, which is already constructed. As a result, various place names acquired could be utilized as different names of existing POI data and it is expected that new POI data would contribute to select places for constructing POI data by utilizing to recognize places having lots of POI variation. Besides, we also expect efficient spatial searching be conducted using diverse spatial vocabulary which can be used in spatial searching and spatial range that human can perceive.