• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.195-198
• /
• 2015

최근 TV 서비스의 가입자 및 TV 프로그램 콘텐츠의 급격한 증가에 따라 빅데이터 처리에 적합한 추천 시스템의 필요성이 증가하고 있다. 본 논문은 사용자들의 간접 평가 데이터 기반의 추천 시스템 디자인 시, 누적된 사용자의 과거 이용내역 데이터를 저장하지 않고 새로 생성된 사용자 이용내역 데이터를 학습하는 효율적인 알고리즘이면서, 시간 흐름에 따라 사용자들의 선호도 변화 및 TV 프로그램 스케줄 변화의 추적이 가능한 토픽 모델링 기반의 알고리즘을 제안한다. 빅데이터 처리를 위해서는 분산처리 형태의 알고리즘을 피할 수 없는데, 기존의 연구들 중 토픽 모델링 기반의 추론 알고리즘의 병렬분산처리 과정 중에 핵심이 되는 부분은 많은 데이터를 여러 대의 기계에 나누어 병렬분산 학습하면서 전역변수 데이터를 동기화하는 부분이다. 그런데, 이러한 전역데이터 동기화 기술에 있어, 여러 대의 컴퓨터를 병렬분산처리하기위한 하둡 기반의 시스템 및 서버-클라이언트간의 중재, 고장 감내 시스템 등을 모두 고려한 알고리즘들이 제안되어 왔으나, 네트워크 대역폭 한계로 인해 데이터 증가에 따른 동기화 시간 지연은 피할 수 없는 부분이다. 이에, 본 논문에서는 빅데이터 처리를 위해 사용자들을 클러스터링하고, 클러스터별 제안 알고리즘으로 전역데이터 동기화를 수행한 것과 지역 데이터를 활용하여 추론 연산한 결과, 클러스터별 지역별 TV프로그램 시청 토큰 별 은닉토픽 할당 테이블을 유지할 때 추천 성능이 더욱 향상되어 나오는 결과를 확인하여, 제안된 구조의 추천 시스템 디자인의 효율성과 합리성을 확인할 수 있었다.

• Journal of the Korea Convergence Society
• /
• v.12 no.4
• /
• pp.31-42
• /
• 2021

The purpose of this study was to explore research topics and examine the trend in COVID19 related research papers. We identified eight topics using latent Dirichlet allocation and found acceptable validity in comparison with the structural topic model. The subtopics have been extracted using k-means clustering and plotted in PCA space. Additionally, we discovered the topics bearing negative tones and warning signs by sentiment analysis. The results flagged up the issues of the topics, Biomedical Related, International Dynamics and Psychological Impact. The findings could serve as a guideline for researchers who explore new research directions and policymakers who need to make decisions about which research projects to support.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.640-645
• /
• 2014

Many people use social network services as to communicate, to share an information and to build social relationships between others on the Internet. Twitter is such a representative service, where millions of tweets are posted a day and a huge amount of data collection has been being accumulated. Social mining that extracts the meaningful information from the massive data has been intensively studied. Typically, Twitter easily can deliver and retweet the contents using the following-follower relationships. Topic modeling in tweet data is a good tool for issue tracking in social media. To overcome the restrictions of short contents in tweets, we introduce a notion of reply graph which is constructed as a graph structure of which nodes correspond to users and of which edges correspond to existence of reply and retweet messages between the users. The LDA topic model, which is a typical method of topic modeling, is ineffective for short textual data. This paper introduces a topic modeling method that uses reply graph to reduce the number of short documents and to improve the quality of mining results. The proposed model uses the LDA model as the topic modeling framework for tweet issue tracking. Some experimental results of the proposed method are presented for a collection of Twitter data of 7 days.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.23-28
• /
• 2023

This study aims to examine the characteristics of YouTube space, focusing on YouTube contents related to conflict. From 2012 to 2022, conflict-related contents posted on YouTube was collected and the major topics and characteristics were identified through topic modeling analysis. The results reveal that YouTube contents related to conflict consisted mainly of news reports on social structural conflicts and broadcast programs dealing with family conflicts. These results make us worry that YouTube space will function as a means of generating profits for existing broadcasting contents rather than expecting that it can be used as the public sphere for conflict-related issues. It is time for in-depth discussions on how our society will use YouTube in the future.

• The Journal of Society for e-Business Studies
• /
• v.8 no.4
• /
• pp.151-166
• /
• 2003

The Topic Maps paradigm allows people and organizations to integrate and merge heterogeneous products classification systems such as UNSPSC and HS. Merging their product ontologies could combine information about classification scheme for products. We analyzed two product classification schemes for UML modeling and developed an integrated TM for watches . Examples in XTM syntax show how UNSPSC and HS can be integrated by merging their ontology.

• Journal of The Korean Association of Information Education
• /
• v.26 no.5
• /
• pp.467-480
• /
• 2022

This paper aimed to explore research trends for the conceptualization of IT humanities. Reflecting domestic and international references which focused on the possibility of the integration of digital technology and humanities, the authors examined the beginning, background, and relevant concepts of IT humanities to figure out the meaning and the research trends. In addition, using the search word "IT humanities," the authors analyzed network topics of the keywords retrieved from 1,566 KCI and 64 SCI journal articles published since 2001. The concept of IT humanities in the previous studies has tended to associate with competencies that allow considering various fields of IT based on the lens of humanities perspectives. The result of the topic modeling revealed four groups as fields to be integrated with IT humanities, methods of implementation, connections of literature or culture, and creations of IT humanities. Instead of instrumentalization or merger by one stance of IT or humanities, it is imperative to collaboratively work for the generation of a new viewpoint through mutual respect of disciplines.

• Knowledge Management Research
• /
• v.22 no.3
• /
• pp.55-73
• /
• 2021

The sharing economy is considered as a collaborative consumption which enables customers to share unused resources. This study investigated the key factors affecting consumer loyalty in the context of sharing accommodation. Emotions, perceived value and self-image consistency were posited as key antecedents of enhancing customer loyalty. Authentic experience, home amenities, and price fairness were also considered as Airbnb's selection attributes. Airbnb was selected a survey target because it is the largest company in the domain of shared accommodation market. The research model was analyzed for 294 Airbnb customer through structural equation models. Additionally, this paper examine Airbnb customers' experiences by topic modelling method posted on the Naver blog. Based on the understanding of the key factors affecting customer loyalty to sharing accommodation, the analysis results contribute to establish effective marketing and operation strategies by enhancing customer experience.

• Journal of Digital Convergence
• /
• v.20 no.2
• /
• pp.203-215
• /
• 2022

The study is to investigate research trends and knowledge structures in the Smart Farm field. To achieve the research purpose, keywords and the relationship among keywords were analyzed targeting 104 Korean academic journals related to the Smart Farm in KCI(Korea Citation Index), and topics were analyzed using the LDA Topic Modeling technique. As a result of the analysis, the main keywords in the Korean Smart Farm-related research field were 'environment', 'system', 'use', 'technology', 'cultivation', etc. The results of Degree, Betweenness, and Eigenvector Centrality were presented. There were 7 topics, such as 'Introduction analysis of Smart Farm', 'Eco-friendly Smart Farm and economic efficiency of Smart Farm', 'Smart Farm platform design', 'Smart Farm production optimization', 'Smart Farm ecosystem', 'Smart Farm system implementation', and 'Government policy for Smart Farm' in the results of Topic Modeling. This study will be expected to serve as basic data for policy development necessary to advance Korean Smart Farm research in the future by examining research trends related to Korean Smart Farm.

• The Journal of the Korea Contents Association
• /
• v.19 no.7
• /
• pp.427-435
• /
• 2019

Soundscape provides important resources to understand social and cultural aspects of our society, however, it is still its infancy to study on the research framework to record, conserve, categorize, and analyze soundscapes. Topic modeling is an automatic approach to discover hidden themes that are disperse in unstructured documents, thus topic modeling is robust enough to find latent topics such as research trends behind a collection of documents. The purpose of this paper is to discover topics on current soundscape research based on topic modeling, furthermore, to discuss the possibilities to design a metadata system for sound archives and to improve Soundscape Ontology which is currently developing.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.33-55
• /
• 2022

This study analyzed the comments and the replies on internet news related to the presidential election in order to verify whether online discussions are properly conducted. According to Habermas' public sphere theory, discussions is an effort among participants to reach a social consensus through the deliberations that are based on open communications. We propose that if such discussions properly take place through the act of writing in the Internet space, the comments and the replies will show a certain difference in terms of the structure and the content. To validate, this study analyzed more than 40,000 comments collected from Daum News portal site in Korea. The topic of the related news was the presidential election, because it is a topic of which people are highly interested in and that comments are actively running. The result of the t-test and topic modeling result show that all the hypotheses were supported thus we conclude that online discussions properly took places. This study also showed that online comments are not chaotic remarks that relieve people's stresses, but rather an outcome of the deliberation processes moving towards a social consensus.