• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.169-170
• /
• 2017

In this paper, we analyze contents of formal and non - standardized data to understand what factors affect the ratings of drama. The formalized data collection collected 19 items from the four areas of drama information, person information, broadcasting information, and audience rating information of each broadcasting company. In order to collect unstructured data, crawling techniques were used to collect bulletin boards, pre - broadcast blogs and post - broadcast blogs for each drama. From the collected data, it was found that the differences according to broadcasting time, the start time, genre, and day of broadcasting were similar among broadcasting companies.

• The Journal of the Korea Contents Association
• /
• v.19 no.5
• /
• pp.147-162
• /
• 2019

This study investigates the relationship between the online WOMs(such as volume of blogs, articles, reviews, searches) and the number of audience of successful film.The results are as follow: Frist, using a curve-estimation method, the results show that the longitudinal trends of the online WOMs can be best described by a cubic indicating. Second, using panel analysis in model(t) the volume of blogs, reviews, and searches is positively associated with the number of audience. All of the variables' coefficient are significant. However the volume of articles is negatively related to the number of audience with a significant coefficient.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.389-392
• /
• 2020

The growth in social media, blogs and restaurant listing directories have led to increasing customer reviews about restaurants, their quality of food items and services available on the internet. These user reviews offer a massive amount of valuable information that can be used for various decision-making purposes. Currently, most food recommendation sites provide recommendation scores about restaurants rather than food items of the restaurant and the provided recommendation scores may be biased since they are calculated only from user reviews listed only in their sites. Usually, people wants a reliable recommendation about foods, not restaurant. In this paper, we present a reliable Korean food items rating method; we first extract food items by applying NER technique to restaurant reviews collected from many Korean restaurant recommendation web sites, blogs and web data. Then, we apply lexicon-based sentiment analysis on collected user reviews and predict people's opinions as sentiment polarity scores (+1 for positive; -1 for negative; 0 for neutral). Finally, by taking average of all calculated polarity scores about a food item, we obtain a rating to individual menu items of the restaurant. The proposed food item rating is more reliable since it does not depend on reviews of only one site.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.40 no.5
• /
• pp.830-843
• /
• 2016

The world wide increase of obesity and demands for various plus-size fashion are expanding the global plus-size fashion market. This study is to understand the market status of the US (the biggest plus-size fashion market) as well as analyze women's fashion shown in power blogs on the plus-size fashion trend. For research methods, photos from the top 10 globally ranked plus-size power blogs on Alexa.com were collected and divided into 5 plus-size body types based on: design factors, style, color, item, and texture. Pants with tops or completed outfits including pants, tops, and outer were the most common for casual styles; in addition, a tendency to pursue comfortable and naturally fitted clothes was also indicated. As for colors, the most common were blue colors and white or pastel toned colors; in addition, soft, hard, and transparent were all evenly used for materials. One-piece items were the most popular formal style that were mostly a one-tone color made with hard materials indicated by the pursuit of the fanciness and formality of a dress for a formal occasion. Black was the most common color, and the color variation was less diverse compared to that of casual styles. The most common for semi-formal styles were outfits with movability and more fanciness such as wearing a casual outer on top of a formal one-piece. When examining the fashion in plus-size blogs, there are differences in the frequency of design factors due to the diversity of body-types; in addition, different items were shown to be preferred in accordance with styles. The results of this study will help fashion companies who want to enter the global plus-size women's fashion market (including the US market); in addition, research on plus-size fashion that is changing the fashion and aesthetic paradigm is expected to contribute to academia.

• The Journal of the Korea Contents Association
• /
• v.15 no.3
• /
• pp.252-264
• /
• 2015

The purpose of this study was to identify pregnant women's needs for information on prenatal genetic diagnosis and screening. This study is consisted of two phases. In the first phase in December 2011, six blogs featuring questions and answers on prenatal genetic diagnosis and screening were selected from four major search engines in Korea by using the keywords "prenatal genetic diagnosis," "prenatal genetic screening", and "amniocentesis." An analyzing framework was constructed on the basis of 389 posts on six blogs between November 2006 and October 2011. In the second phase, the contents of the "MomsHolicbaby" blog posted from November 2010 to October 2011 were reviewed. Then, pregnant women's questions on prenatal genetic diagnosis and screening (100 questions) and amniocentesis (200 questions with 1,665 answers) were analyzed using descriptive statistics. Among posters who had ever been recommended to undergo amniocentesis, 56.5% described feelings of anxiety, 25.5% did not know the purpose of the test, and 33.9% refused to undergo the test. Among 295 posters answering questions about amniocentesis, 61.4% disagreed with undergoing the test. The results show that there is a need for healthcare professionals to provide more educational and emotional support to pregnant women considering prenatal genetic diagnosis and screening. Providing online health information can be integrated into prenatal genetic education for pregnant women as well as nurses. In addition, prenatal women's preferences about undergoing amniocentesis should be reflected in the current legal discussion on criteria for termination of pregnancy.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.122-124
• /
• 2018

While the investment on virtual currency is becoming a way of individual financial-tech, this research is to analysis big-data on virtual currency. The analysis is to focus on big-data in the SNS such as blogs and twitter.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2008.06a
• /
• pp.85-89
• /
• 2008

웹상에서 자동 데이터 추출과 분석기법은 최근 검색분야의 주요이슈이다. 본 논문은 웹상의 자동 설문조사 시스템에 관한 연구이다. 그리고 기존의 Corpus의 성향을 분석하고 검색 및 분석 시스템의 항목들을 정의하였다. 또한 Corpus를 이용한 웹 검색 및 분석 시스템의 활용 분야를 기술하고 향후 개발 방향을 기술하였다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.5
• /
• pp.360-364
• /
• 2009

Analyzing information diffusion in a blog world is a very useful research issue, which can be used for predicting information diffusion, abnormally detection, marketing, and revitalizing the blog world. Existing studies on information diffusion in blog networks establish explicit relationship between blogs, and analyze only the word-of-mouth effect through such explicit relationships. However, we observed that more than 85% of all information diffusion in a blog world occurs through non-explicit relationships. In this paper, we propose a new model that considers both explicit and non-explicit relationships between blogs in order to explain all information diffusion phenomena in a blog world. We verify the superiority of our proposed models through extensive experiments of information diffusions at a real blog net-work.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.11
• /
• pp.21-29
• /
• 2010

Opinion retrieval which searches the opinions expressed in documents by users cannot outperform significantly yet traditional topical retrieval which searches the facts. Therefore, the focus of this paper is to identify the statistical characteristics which can be applied to opinion retrieval by comparing and analyzing the term statistics of opinion and non-opinion documents in the blog domain. The TREC Blogs06 collection and 150 TREC topics are used in the experiments. The difference between term probability distributions in opinion documents is measured by JS divergence, and the difference according to the topic types and topic domains is also investigated. Moreover, the term probabilities of opinion terms are analyzed comparatively. The main findings of this study include the following: it is necessary to consider the topic-specific characteristics for the opinion detection; it is effective to extract positive and negative opinion terms according to the topics; the topic types are complementary to the topic domains; and special attention has to be given to the usage of the positive opinion terms.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.3
• /
• pp.292-297
• /
• 2014

As a Social Network Service (SNS) has become an integral part of our everyday lives, millions of users can express their opinion and share information regardless of time and place. Hence sentiment analysis using micro-blogs has been studied in various field to know people's opinion on particular topics. Most of previous researches on movie reviews consider only positive and negative sentiment and use it to predict movie rating. As people feel not only positive and negative but also various emotion, the sentiment that people feel while watching a movie need to be classified in more detail to extract more information than personal preference. We measure sentiment distributions of each movie from tweets according to the Thayer's model. Then, we find similar movies by calculating similarity between each sentiment distributions. Through the experiments, we verify that our method using micro-blogs performs better than using only genre information of movies.