• Journal of Information Processing Systems
• /
• v.5 no.1
• /
• pp.5-10
• /
• 2009

Text data has always accounted for a major portion of the world's information. As the volume of information increases exponentially, the portion of text data also increases significantly. Text classification is therefore still an important area of research. LDA is an updated, probabilistic model which has been used in many applications in many other fields. As regards text data, LDA also has many applications, which has been applied various enhancements. However, it seems that no applications take care of the input for LDA. In this paper, we suggest a way to map the input space to a reduced space, which may avoid the unreliability, ambiguity and redundancy of individual terms as descriptors. The purpose of this paper is to show that LDA can be perfectly performed in a "clean and clear" space. Experiments are conducted on 20 News Groups data sets. The results show that the proposed method can boost the classification results when the appropriate choice of rank of the reduced space is determined.

• Journal of Digital Contents Society
• /
• v.16 no.3
• /
• pp.373-379
• /
• 2015

In this paper, we propose an online VQ Codebook generation method for updating an existing VQ Codebook in real-time and adding to an existing cluster with newly created text data which are news paper, web pages, blogs, tweets and IoT data like sensor, machine. Without degrading the performance of the batch VQ Codebook to the existing data, it was able to take advantage of the newly added data by using a triangle inequality which modifying the VQ Codebook progressively show a high degree of accuracy and speed. The result of applying to test data showed that the performance is similar to the batch method.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1347-1356
• /
• 2017

Artificial intelligence-based services are expanding into a new industrial revolution. There is artificial intelligence technology applied in real life due to the development of big data and deep learning related technology. And data analysis and intelligent assistant services that integrate information from various fields have also been commercialized. Chatbot with interactive artificial intelligence provide shopping, news or information. Chatbot service, which has begun to be adopted by some public institutions, is now just a first step in the steps. This study summarizes the services and technical analysis of chatbot. and the direction of public administration service chatbot was presented.

• Asian review of World Histories
• /
• v.4 no.1
• /
• pp.125-132
• /
• 2016

This paper, as a conlcusion to this special issue, presents the future work that is being carried out at NTU Singapore in collaboration with Microsoft Research and Microsoft Azure for Research. For our research team the real frontier research in world histories starts when we want to use computers to structure historical information, model historical narratives, simulate theoretical large scale hypotheses, and incent world historians to use virtual assistants and/or engage them in teamwork using social media and/or seduce them with immersive spaces to provide new learning and sharing environments, in which new things can emerge and happen: "You do not know which will be the next idea. Just repeating the same things is not enough" (Carlo Rubbia, 1984 Nobel Price in Physics, at Nanyang Technological University on January 19, 2016).

• Korean Management Science Review
• /
• v.26 no.2
• /
• pp.19-35
• /
• 2009

This paper investigated performance of the Markowitz's portfolio selection model with applications to Korean stock market. We chose Samsung-Group-Funds and KOSPI index for performance comparison with the Markowitz's portfolio selection model. For the most recent one and a half year period between March 2007 and September 2008, KOSPI index almost remained the same with only 0.1% change, Samsung-Group-Funds showed 20.54% return, and Markowitz's model, which is composed of the same 17 Samsung group stocks, achieved 52% return. We performed sensitivity analysis on the duration of financial data and the frequency of portfolio change in order to maximize the return of portfolio. In conclusion, according to our empirical research results with Samsung-Group-Funds, investment by Markowitz's model, which periodically changes portfolio by using nonlinear programming with only financial data, outperformed investment by the fund managers who possess rich experiences on stock trading and actively change portfolio by the minute-by-minute market news and business information.

• Journal of Distribution Science
• /
• v.13 no.7
• /
• pp.33-40
• /
• 2015

Purpose - This study aims to find out what impacts large retailers' behaviors appearing when they promote the strengthening of their market dominating power in the trade relations with small and medium suppliers or in the market can have on consumers. Research design, data, methodology - This study analyzed negative information (news) on large retailers (Lotte Mart, E-Mart and Homeplus) based on the monthly data over the past five years from 2008 to 2012 and also analyzed the correlation between dependent variables that are likely to affect sales through large retailer economic index, Results - This study conducted a correlation analysis on the time lag of the factors that have an impact on the negative information and sales of large retailers in order to analyze how consumers respond to the choice of large retailers' store (store sales) when they perceived negative information about the un- ethical behaviors of large retailers. Conclusions - Unfair and negative information on large retailers appeared significant for the hypothesis that sales will be affected by the image of large retailers and change of consumer attitudes.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.193-195
• /
• 2005

본 논문은 온톨로지를 이용하여 뉴스 비디오를 분야별로 자동으로 분류하는 효율적인 기법을 제안한다. 이를 위해서 뉴스 비디오를 파싱하여 키프레임(Key frame), 샷(Shot), 씬(Scene)으로 나누고 키프레임과 샷에서 특징 정보를 추출한다. 추출된 특징 정보를 이용하여 샷의 키워드 집합을 만들고 이를 이용하여 씬의 키워드 집합을 만든다. 그리고 씬의 키워드 집합을 어휘 온톨로지와 뉴스 온톨로지에 매칭(추론)하여, 씬의 분야를 결정한다. 또한 이렇게 결정된 분야를 기반으로 서로 유사한 씬들을 자동으로 그룹화하는 방법을 제안한다.

• Journal of information and communication convergence engineering
• /
• v.9 no.1
• /
• pp.69-73
• /
• 2011

Twitter is a microblogging service that allows its user to share short messages called tweets with each other. All the tweets are visible on a public timeline. These tweets have the valuable geospatial component and particularly time critical events. In this paper, our interest is in the rapid detection of disaster events such as tsunami, tornadoes, forest fires, and earthquakes. We describe the detection system of disaster events and show the way to detect a target event from Twitter data. This research examines the three disasters during the same time period and compares Twitter activity and Internet news on Google. A significant result from this research is that emergency detection could begin using microblogging service.

• Journal of Information Processing Systems
• /
• v.14 no.4
• /
• pp.904-915
• /
• 2018

We demonstrate how social media content can be used to predict the unemployment rate, a real-world indicator. We present a novel method for predicting the unemployment rate using social media analysis based on natural language processing and statistical modeling. The system collects social media contents including news articles, blogs, and tweets written in Korean, and then extracts data for modeling using part-of-speech tagging and sentiment analysis techniques. The autoregressive integrated moving average with exogenous variables (ARIMAX) and autoregressive with exogenous variables (ARX) models for unemployment rate prediction are fit using the analyzed data. The proposed method quantifies the social moods expressed in social media contents, whereas the existing methods simply present social tendencies. Our model derived a 27.9% improvement in error reduction compared to a Google Index-based model in the mean absolute percentage error metric.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.1
• /
• pp.9-15
• /
• 2018

Policy polls, which investigate the degree of support that the policy has for policy implementation, play an important role in making decisions. As the number of Internet users increases, the public is actively commenting on their policy news stories. Current policy polls tend to rely heavily on phone and offline surveys. Collecting and analyzing policy articles is useful in policy surveys. In this study, we propose a method of analyzing comments using deep learning technology showing outstanding performance in various fields. In particular, we designed various models based on the recurrent neural network (RNN) which is suitable for sequential data and compared the performance with the support vector machine (SVM), which is a traditional machine learning model. For all test sets, the SVM model show an accuracy of 0.73 and the RNN model have an accuracy of 0.83.