• 한국정보시스템학회지:정보시스템연구
• /
• 제30권3호
• /
• pp.201-216
• /
• 2021

Purpose The purpose of this study is to analyze the trend of patent technology in textile materials using text mining methodology based on Dynamic Embedded Topic Model and Structural Topic Model. It is expected that this study will have positive impact on revitalizing and developing textile materials industry as finding out technology trends. Design/methodology/approach The data used in this study is 866 domestic patent text data in textile material from 1974 to 2020. In order to analyze technology trends from various aspect, Dynamic Embedded Topic Model and Structural Topic Model mechanism were used. The word embedding technique used in DETM is the GloVe technique. For Stable learning of topic modeling, amortized variational inference was performed based on the Recurrent Neural Network. Findings As a result of this analysis, it was found that 'manufacture' topics had the largest share among the six topics. Keyword trend analysis found the fact that natural and nanotechnology have recently been attracting attention. The metadata analysis results showed that manufacture technologies could have a high probability of patent registration in entire time series, but the analysis results in recent years showed that the trend of elasticity and safety technology is increasing.

• 지능정보연구
• /
• 제28권1호
• /
• pp.131-154
• /
• 2022

최근 방대한 양의 텍스트 데이터에 대한 분석을 통해 유용한 지식을 창출하는 시도가 꾸준히 증가하고 있으며, 특히 토픽 모델링(Topic Modeling)을 통해 다양한 분야의 여러 이슈를 발견하기 위한 연구가 활발히 이루어지고 있다. 초기의 토픽 모델링은 토픽의 발견 자체에 초점을 두었지만, 점차 시기의 변화에 따른 토픽의 변화를 고찰하는 방향으로 연구의 흐름이 진화하고 있다. 특히 토픽 자체의 내용, 즉 토픽을 구성하는 키워드의 변화를 수용한 다이내믹 토픽 모델링(Dynamic Topic Modeling)에 대한 관심이 높아지고 있지만, 다이내믹 토픽 모델링은 분석 결과의 직관적인 이해가 어렵고 키워드의 변화가 토픽의 의미에 미치는 영향을 나타내지 못한다는 한계를 갖는다. 본 논문에서는 이러한 한계를 극복하기 위해 다이내믹 토픽 모델링과 워드 임베딩(Word Embedding)을 활용하여 토픽의 변화 및 토픽 간 관계를 직관적으로 해석할 수 있는 방안을 제시한다. 구체적으로 본 연구에서는 다이내믹 토픽 모델링 결과로부터 각 시기별 토픽의 상위 키워드와 해당 키워드의 토픽 가중치를 도출하여 정규화하고, 사전 학습된 워드 임베딩 모델을 활용하여 각 토픽 키워드의 벡터를 추출한 후 각 토픽에 대해 키워드 벡터의 가중합을 산출하여 각 토픽의 의미를 벡터로 나타낸다. 또한 이렇게 도출된 각 토픽의 의미 벡터를 2차원 평면에 시각화하여 토픽의 변화 양상 및 토픽 간 관계를 표현하고 해석한다. 제안 방법론의 실무 적용 가능성을 평가하기 위해 DBpia에 2016년부터 2021년까지 공개된 논문 중 '인공지능' 관련 논문 1,847건에 대한 실험을 수행하였으며, 실험 결과 제안 방법론을 통해 다양한 토픽이 시간의 흐름에 따라 변화하는 양상을 직관적으로 파악할 수 있음을 확인하였다.

• 한국의류학회지
• /
• 제46권6호
• /
• pp.1004-1022
• /
• 2022

This study seeks to investigate K-fashion's external image by examining the trends in global media reporting. It applies Dynamic Topic Modeling (DTM), which captures the evolution of topics in a sequentially organized corpus of documents, and consists of text preprocessing, the determination of the number of topics, and a timeseries analysis of the probability distribution of words within topics. The data set comprised 551 online media articles on 'Korean fashion' or 'K-fashion' published on Google News between 2010 and 2021. The analysis identifies seven topics: 'brand look and style,' 'lifestyle,' 'traditional style,' 'Seoul Fashion Week (SFW) event,' 'model size,' 'K-pop,' and 'fashion market,' as well as annual topic proportion trends. It also explores annual word changes within the topic and indicates increasing and decreasing word patterns. In most topics, the probability distribution of the word 'brand' is confirmed to be on the increase, while 'digital,' 'platform,' and 'virtual' have been newly created in the 'SFW event' topic. Moreover, this study confirms the transition of each K-fashion topic over the past 12 years, along with various factors related to Hallyu content, traditional culture, government support, and digital technology innovation.

• 한국융합학회논문지
• /
• 제11권9호
• /
• pp.21-29
• /
• 2020

최근 디지털 사회의 도래로 다양한 데이터가 폭발적으로 증가하고, 그중 문헌 내 주제어를 도출하는 토픽 모델링에 관한 연구가 활발히 진행되고 있다. 본 논문의 연구목표는 토픽 모델링 방법 중 하나인 DTM(Dynamic Topic Model) 모델을 적용해 D.N.A.(Data, Network, A.I) 분야에 대한 연구동향을 탐색하는데 있다. 실험 데이터는 최근 6년간(2015~2020) ICT(Information and Communication Technology) 분야 중 기술대분류가 SW·AI에 해당하는 연구과제 1,519개 사업에 대해 DTM 모델을 적용하였다. 실험결과로, D.N.A. 분야의 기술 키워드 Big data, Cloud, Artificial Intelligence와 확장된 의미의 기술 키워드 Unstructured, Edge Computing, Learning, Recognition 등이 매년 연구에 표출되었으며, 해당 키워드 들이 특정 연구과제에 종속되지 않고 다른 연구과제에서도 포괄적으로 연구되고 있음을 확인하였다. 끝으로 본 논문의 연구결과는 향후 D.N.A. 분야에 대한 정책기획·과제기획 등 연구개발 기획 과정과 기업의 기술 확보전략·마케팅 전략 등 다양한 곳에 활용될 수 있을 것으로 기대한다.

• ETRI Journal
• /
• 제45권6호
• /
• pp.982-995
• /
• 2023

Technological innovation generates products, services, and processes that can disrupt existing industries and lead to the emergence of new fields. Distributed ledger technology, or blockchain, offers novel transparency, security, and anonymity characteristics in transaction data that may disrupt existing industries. However, research attention has largely examined its application to finance. Less is known of any broader applications, particularly in Industry 4.0. This study investigates academic research publications on blockchain and predicts emerging industries using academia-industry dynamics. This study adopts latent Dirichlet allocation and dynamic topic models to analyze large text data with a high capacity for dimensionality reduction. Prior studies confirm that research contributes to technological innovation through spillover, including products, processes, and services. This study predicts emerging industries that will likely incorporate blockchain technology using insights from the knowledge structure of publications.

• 한국정보통신학회논문지
• /
• 제25권2호
• /
• pp.308-313
• /
• 2021

이 연구는 2019년 판문점 남북미 정상 회동 트윗을 타임 시퀀스와 함께 수집하여 시퀀셜 토픽모델링인 DTM으로 분석하였다. 트위터와 같은 마이크로 블로깅 서비스는 단일 이벤트에 뉴스와 오피니언이 혼재된 비정형 데이터가 대규모로 동시에 발생하고, 정보와 반응이 동일 메시지 형식으로 생산된다. 때문에 토픽 트렌드를 파악하려면 시퀀셜 데이터의 특성을 반영하여 패턴 분석을 해야 맥락적 의미를 알 수 있다. 토픽 일관성 점수를 구해 LDA를 평가한 후 DTM을 계산한 결과, 뉴스 보도와 오피니언 관련 토픽 30개가 도출되었고, 각 토픽과 키워드는 시간에 따라 발생 확률이 역동적으로 진화하고 있었다. 결론적으로 DTM은 특정 이벤트에 대한 사회 전반에 나타난 통합적 토픽 추이를 시간에 따라 분석하는데 적합한 모델임을 밝혔다.

• 대한산업공학회지
• /
• 제42권6호
• /
• pp.421-431
• /
• 2016

Over the last four decades, industrial engineering (IE) research in Korea has continued to evolve and expand to respond to social needs. This paper aims to identify research topics in IE research and explore their dynamic changes over time. The topic modeling approach, which automatically discovers topics that pervade a large and unstructured collection of documents, is adopted to identify research topics in domestic IE research. 1,242 articles published from 2001 to 2015 in two IE journals issued by the Korean Institute of Industrial Engineers were collected and their English abstracts were analyzed. Applying the Latent Dirichlet Allocation model led us to uncover 50 topics of domestic IE research. The top 10 most popular topics are revealed, and topic trends are explored by examining the dynamic changes over time. The four topics, technology management, financial engineering, data mining (supervised learning), efficiency analysis, are selected as hot topics while several traditional topics related with manufacturing are revealed as cold topics. The findings are expected to provide fruitful implications for IE researchers.

• Coupled systems mechanics
• /
• 제12권1호
• /
• pp.83-102
• /
• 2023

First introduced in 2016, the dynamic foundation model is an interesting topic in which the foundation is described close to reality by taking into account the influence of the foundation mass in the calculation of oscillation and is an important parameter that should be considered. In this paper, a follow-up investigation is conducted with the object of the Mindlin plate on a nonlinear dynamic foundation under moving loads. The base model includes nonlinear elastic springs, linear Pasternak parameters, viscous damping, and foundation mass. The problem is formulated by the finite element analysis and solved by the Newmark-β method. The displacement results at the center of the plate are analyzed and discussed with the change of various parameters including the nonlinear stiffness, the foundation mass, and the load velocity. The dynamic response of the plate sufficiently depends on the foundation mass.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권8호
• /
• pp.3168-3186
• /
• 2020

Automatic topic essay generation (TEG) is a controllable text generation task that aims to generate informative, diverse, and topic-consistent essays based on multiple topics. To make the generated essays of high quality, a reasonable method should consider both diversity and topic-consistency. Another essential issue is the intrinsic link of the topics, which contributes to making the essays closely surround the semantics of provided topics. However, it remains challenging for TEG to fill the semantic gap between source topic words and target output, and a more powerful model is needed to capture the semantics of given topics. To this end, we propose a pretraining-based contextual self-attention (PC-SAN) model that is built upon the seq2seq framework. For the encoder of our model, we employ a dynamic weight sum of layers from BERT to fully utilize the semantics of topics, which is of great help to fill the gap and improve the quality of the generated essays. In the decoding phase, we also transform the target-side contextual history information into the query layers to alleviate the lack of context in typical self-attention networks (SANs). Experimental results on large-scale paragraph-level Chinese corpora verify that our model is capable of generating diverse, topic-consistent text and essentially makes improvements as compare to strong baselines. Furthermore, extensive analysis validates the effectiveness of contextual embeddings from BERT and contextual history information in SANs.

• Journal of Information Processing Systems
• /
• 제19권1호
• /
• pp.55-66
• /
• 2023

Community portraits can deeply explore the characteristics of community structures and describe the personalized knowledge needs of community users, which is of great practical significance for improving community recommendation services, as well as the accuracy of resource push. The current community portraits generally have the problems of weak perception of interest characteristics and low degree of integration of topic information. To resolve this problem, the reader community portrait method based on the thematic and timeliness characteristics of interest labels (UIT) is proposed. First, community opinion leaders are identified based on multi-feature calculations, and then the topic features of their texts are identified based on the LDA topic model. On this basis, a semantic mapping including "reader community-opinion leader-text content" was established. Second, the readers' interest similarity of the labels was dynamically updated, and two kinds of tag parameters were integrated, namely, the intensity of interest labels and the stability of interest labels. Finally, the similarity distance between the opinion leader and the topic of interest was calculated to obtain the dynamic interest set of the opinion leaders. Experimental analysis was conducted on real data from the Douban reading community. The experimental results show that the UIT has the highest average F value (0.551) compared to the state-of-the-art approaches, which indicates that the UIT has better performance in the smooth time dimension.