• ETRI Journal
• /
• 제38권3호
• /
• pp.487-493
• /
• 2016

Two new methods are proposed for an unsupervised adaptation of a language model (LM) with a single sentence for automatic transcription tasks. At the training phase, training documents are clustered by a method known as Latent Dirichlet allocation (LDA), and then a domain-specific LM is trained for each cluster. At the test phase, an adapted LM is presented as a linear mixture of the now trained domain-specific LMs. Unlike previous adaptation methods, the proposed methods fully utilize a trained LDA model for the estimation of weight values, which are then to be assigned to the now trained domain-specific LMs; therefore, the clustering and weight-estimation algorithms of the trained LDA model are reliable. For the continuous speech recognition benchmark tests, the proposed methods outperform other unsupervised LM adaptation methods based on latent semantic analysis, non-negative matrix factorization, and LDA with n-gram counting.

• 방송공학회논문지
• /
• 제17권2호
• /
• pp.270-283
• /
• 2012

다채널 TV, IPTV 및 Smart TV 서비스의 등장으로 인해 수많은 방송 채널과 방대한 TV 프로그램 콘텐츠가 시청자 단말로 제공됨으로써 시청자들은 자신이 원하는 콘텐츠를 쉽게 찾고 소비하는 것이 어려운 TV 시청 환경을 맞게 되었다. 따라서 TV 사용자들에게 자신이 선호하는 콘텐츠를 자동 추천해 줌으로써 원하는 콘텐츠로의 접근성을 증대시키는 것은 미래의 지능형 TV 서비스에 있어서 주요한 이슈이다. 이에 본 논문에서는 사용자의 선호 취향과 대중의 선호취향을 모두 고려한 협업필터링 개념의 통계적 기계학습 기반 TV 프로그램 추천 모델을 제시한다. 이를 위해 시청한 TV 콘텐츠에 대한 선호 토픽을 사용자의 시청 선호도로 보고, 최근 널리 활용되고 있는 LDA(Latent Dirichlet Allocation)모델을 TV 프로그램 추천 모델에 적용하였다. LDA 기반 TV 프로그램 추천 성능을 개선하기 위해 본 논문에서는 TV시청 이용내역 데이터를 기반으로, TV 사용자들의 관심 토픽을 은닉 변수로 하고, TV 사용자들의 관심 토픽에 대한 다양성을 반영하기 위해 은닉 변수의 확률분포 특성을 비대칭 디리클레(Dirichlet) 분포로 모형화하여 실험에 적용하였다. 제안된 LDA 기반 TV 프로그램 자동 추천 방법의 성능을 검증하기 위해, 유사 시청 특성을 갖는 사용자 그룹에 대해 상위 5개의 TV 프로그램을 일주일 단위로 추천하였을 경우 평균 66.5%, 2개월 단위의 추천에 대해서는 평균 77.9%의 precision 추천 성능을 확인할 수 있었다.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제24권4호
• /
• pp.313-335
• /
• 2021

The purpose of this research is to identify topics discussed by Korean mathematics education studies and examine research trends for 15 years. I applied latent Dirichlet allocation (LDA) to the original text datasets including English abstracts of 3,157 articles published in eight journals indexed by the Korean Citation Index (KCI) from 1997 to 2019. I identified an LDA model with 60 topics, then research trends in 2,884 articles between 2002 and 2018 were as follows; mathematics educators have paid most attention to teacher education through 2010 to 2015 and curriculum analysis after 2016. The findings in this research can contribute to understand what have been discussed in Korean mathematics education society as well as what will and need to be emphasized more in the future compared to the global research trends. In addition, LDA has potentials to identify topics and keywords of manuscripts newly written and submitted to any journals in addition to information provided by authors.

• Asian Journal for Public Opinion Research
• /
• 제10권1호
• /
• pp.4-22
• /
• 2022

The purpose of this study is to explore the structure of social discourse on aging in Korea by analyzing newspaper articles on aging. The analysis is composed of three steps: first, data collection and preprocessing; second, identifying the latent topics; and third, observing yearly dynamics of topics. In total, 1,472 newspaper articles that included the word "aging" within the title were collected from 10 major newspapers between 2006 and 2019. The underlying topic structure was analyzed using Latent Dirichlet Allocation (LDA), a topic modeling method widely adopted by text mining academics and researchers. Seven latent topics were generated from the LDA model, defined as social issues, death, private insurance, economic growth, national debt, labor market innovation, and income security. The topic loadings demonstrated a clear increase in public interest on topics such as national debt and labor market innovation in recent years. This study concludes that media discourse on aging has shifted towards more productivity and efficiency related issues, requiring older people to be productive citizens. Such subjectivation connotes a decreased role of the government and society by shifting the responsibility to individuals not being able to adapt successfully as productive citizens within the labor market.

• 한국컴퓨터정보학회논문지
• /
• 제24권7호
• /
• pp.19-29
• /
• 2019

Requirements traceability is regarded as one of the important quality attributes in software requirements engineering field. If requirements traceability is guaranteed then we can trace the requirements' life throughout all the phases, from the customers' needs in the early stage of the project to requirements specification, deployment, and maintenance phase. This includes not only tracking the development artifacts that accompany the requirements, but also tracking backwards from the development artifacts to the initial customer requirements associated with them. In this paper, especially, we dealt with the traceability between functional requirements and non-functional requirements. Among many Information Retrieval (IR) techniques, we decided to utilize Latent Semantic Indexing (LSI) and Latent Dirichlet Allocation (LDA) in our research. Ultimately, we conducted an experiment on constructing traceability by using two techniques and analyzed the experiment results. And then we provided a comparative study between two IR techniques in constructing traceability between functional requirements and non-functional requirements.

• 한국융합학회논문지
• /
• 제11권7호
• /
• pp.9-18
• /
• 2020

본 논문의 연구목표는 LDA(Latent Dirichlet Allocation) 모델을 적용하여 국가연구개발사업을 통해 수행되고 있는 ICT(Information and Communication Technology) 분야의 연구과제에 대한 주요 연구 토픽과 동향을 탐색하는데 있다. 연구방법에는 NTIS(National Science and Technology Information Service)로부터 최근 5년간 국가연구개발사업의 전체 연구과제 정보를 다운로드받고 이를 정보통신기획평가원(IITP)의 EZone 시스템과 매칭하여 ICT 분야 연구과제 5,200건을 확보하고, 토픽모델링 기법중 하나인 LDA 모델을 적용하여 연구토픽과 연구동향을 조사하였다. 실험결과로, ICT분야 연구과제에 대한 연구토픽은 인공지능, 빅데이터, 사물인터넷(Internet of Things)과 같은 지능정보기술로 확인되었고 연구동향에는 초실감미디어에 관한 연구가 활발히 진행되고 있음을 확인하였다. 끝으로 본 논문에서 진행된 국가연구개발사업에 대한 토픽모델링 결과는 향후 ICT분야 연구개발 계획 및 전략수립, 정책, 과제기획 등 중요한 정보로 활용될 수 있을 것이다.

• 한국과학교육학회지
• /
• 제42권2호
• /
• pp.185-200
• /
• 2022

이 연구에서는 LDA 기반의 토픽모델링 분석을 통해 한국과학교육학회지에 게재된 연구 논문들이 어떤 주제로 어떻게 변화했는지 탐색하였다. 이를 위해, 1978년부터 2021년 5월까지 한국과학교육학회지에 게재된 논문들의 영문초록 총 2,115개에 대한 LDA 기반 토픽모델링분석을 실시하였다. 분석 결과, 총 23개의 토픽을 추출하였으며 각 토픽들을 관련된 키워드 및 세부 연구주제들과 함께 제시하였다. 다음으로, 시간에 따른 토픽들의 변화 추이를 살펴보기 위해, 4년 주기에 대한 각 토픽들의 평균 비중값의 변화를 히트맵으로 시각화하였다. 이를 통해, 시간이 지남에 따라 상승해온 주제와 하락해온 주제들을 밝혔다. 이 연구의 결과들은 꾸준히 연구되어온 전통적인 연구 주제들, 교육 철학이나 연구방법의 변화, 사회나 정책적 요구에 따라 달라져온 연구 주제들을 드러냄으로써 한국의 과학교육연구에 새로운 통찰을 제공할 것으로 기대된다.

• Journal of Multimedia Information System
• /
• 제1권1호
• /
• pp.55-67
• /
• 2014

Image topic and emotion analysis is an important component of online image retrieval, which nowadays has become very popular in the widely growing social media community. However, due to the gaps between images and texts, there is very limited work in literature to detect one image's Topics and Emotions in a unified framework, although topics and emotions are two levels of semantics that often work together to comprehensively describe one image. In this work, a unified model, Joint Topic/Emotion Multi-Modal Hierarchical Latent Dirichlet Allocation (JTE-MMHLDA) model, which extends previous LDA, mmLDA, and JST model to capture topic and emotion information at the same time from heterogeneous data, is proposed. Specifically, a two level graphical structured model is built to realize sharing topics and emotions among the whole document collection. The experimental results on a Flickr dataset indicate that the proposed model efficiently discovers images' topics and emotions, and significantly outperform the text-only system by 4.4%, vision-only system by 18.1% in topic detection, and outperforms the text-only system by 7.1%, vision-only system by 39.7% in emotion detection.

• 대한예방한의학회지
• /
• 제26권1호
• /
• pp.43-57
• /
• 2022

Objective : This study aims to understand the consumer's needs for Korean medicine medical service using online review analysis of medical consumers. Methods : We analyzed the purpose and satisfaction factors of medical service use using LDA (Latent Dirichlet Allocation) topic modeling. The data used in the study was 120,727 screened reviews written by medical consumers registered on Naver. The analyzed results were compared with the "2020 Korean Medicine Utilization Survey". Results : From 2018 to 2021, the five most frequently used terms were "kindness", "treatment", "doctor", "Korean medicine", and "acupuncture". The main purpose of visiting Korean medicine medical clinic and hospital was to treat "traffic accidents" in 2018, "waist(back) pain" in 2019, "musculoskeletal pain" in 2020 & 2021. Based on the rating, reviewers were satisfied with "explanation of treatment" and "treatment attitude", and dissatisfied with "accessibility to the institution". Conclusion : We concluded that the main purpose of use of Korean medicine institution was to treat musculoskeletal disorders. Based on the results of this study, it is expected that it will be used to improve Korean medicine medical service in the future.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 봄 학술논문 발표대회
• /
• pp.31-32
• /
• 2022

The construction industry has more safety accidents than other industries. Although there have been more attempts to reduce safety hazards in the industry such as the enforcement of the "Serious Accidents Punishment Act (SAPA)", construction accident has not been reduced enough. In this study, analysis of safety risk factors has been made through Latent Dirichlet Allocation (LDA)-based topic modeling. Risk analysis in construction site would be improved with natural language processing and topic modeling.