• 제목/요약/키워드: dynamic topic modeling

검색결과 50건 처리시간 0.023초

부동산 정책 관련 트위터 게시물 분석을 통한 대중 여론 이해 (Understanding Public Opinion by Analyzing Twitter Posts Related to Real Estate Policy)

  • 김규리;오찬희;주영준
    • 한국문헌정보학회지
    • /
    • 제56권3호
    • /
    • pp.47-72
    • /
    • 2022
  • 본 연구는 시간의 흐름에 따른 부동산 정책의 주제 동향과 부동산 정책에 대한 대중의 감성 여론을 파악하고자 하였다. 부동산 정책 관련 키워드('부동산정책', '부동산대책')를 이용하여 2008년 2월 25일부터 2021년 8월 31일까지 13년 6개월 동안 작성된 총 91,740개의 트위터 게시물을 수집하였다. 데이터를 전처리하고 공급, 부동산세, 금리, 인구 분산으로 범주화 하여 총 18,925개의 게시물에 대하여 감성 분석과 다이나믹 토픽 모델 분석을 진행하였다. 범주별 키워드는 공급 범주(임대주택, 그린벨트, 신혼부부, 무주택자, 공급, 재건축, 분양), 부동산세 범주(종부세, 취득세, 보유세, 다주택자, 투기), 금리 범주(금리), 인구 분산 범주(세종, 신도시)와 같다. 감성 분석 결과, 한 명이 평균 하나 또는 두 개의 긍정 의견을 게시한 걸로 확인되었고, 부정, 중립 의견의 경우, 한 명이 두 개 또는 세 개의 게시물을 게시한 걸로 확인되었다. 또한 일부 대중들은 부동산 정책에 일관된 감정을 가지고 있지 않고 긍정, 부정, 중립의 의견을 모두 표현하는 것을 유추할 수 있었다. 다이나믹 토픽 모델링 결과, 부동산 투기 세력, 불로소득 주제에 대한 부정적인 반응이 꾸준히 파악되었으며, 긍정적인 주제로는 주택 공급 확대와 무주택자들의 부동산 구입 혜택에 대한 기대감을 확인할 수 있었다. 본 연구는 기존 선행연구들이 특정 부동산 정책의 변화와 평가에 초점을 맞춰 분석한 것과는 달리, 소셜미디어 플랫폼 중 하나인 트위터에서 게시물을 수집하고 감성 분석, 다이나믹 토픽 모델링 분석을 활용하여 부동산 정책 평가자인 대중의 감성과 여론을 알아보고 시간의 흐름에 따른 부동산 정책에 관한 잠재적 주제와 동향을 파악했다는 것에 학술적 의의가 있다. 또한, 본 연구를 통해 부동산 정책에 대한 대중의 여론에 기반한 새로운 정책 제정에 도움을 주려고 한다.

Background Subtraction in Dynamic Environment based on Modified Adaptive GMM with TTD for Moving Object Detection

  • Niranjil, Kumar A.;Sureshkumar, C.
    • Journal of Electrical Engineering and Technology
    • /
    • 제10권1호
    • /
    • pp.372-378
    • /
    • 2015
  • Background subtraction is the first processing stage in video surveillance. It is a general term for a process which aims to separate foreground objects from a background. The goal is to construct and maintain a statistical representation of the scene that the camera sees. The output of background subtraction will be an input to a higher-level process. Background subtraction under dynamic environment in the video sequences is one such complex task. It is an important research topic in image analysis and computer vision domains. This work deals background modeling based on modified adaptive Gaussian mixture model (GMM) with three temporal differencing (TTD) method in dynamic environment. The results of background subtraction on several sequences in various testing environments show that the proposed method is efficient and robust for the dynamic environment and achieves good accuracy.

실시간 야지주행 시뮬레이션을 위한 3차원 가상노면의 구성 및 적용에 대한 연구 (Study on the 3D Virtual Ground Modeling and Application for Real-time Vehicle Driving Simulation on Off-road)

  • 이정한;유완석
    • 한국자동차공학회논문집
    • /
    • 제18권4호
    • /
    • pp.92-98
    • /
    • 2010
  • Virtual ground modeling is one of key topic for real-time vehicle dynamic simulation. This paper discusses about the virtual 3D road modeling process using parametric surface concept. General road data is a type of lumped position vector so interpolation process is required to compute contact of internal surface. The parametric surface has continuity and linearity within boundaries and functions are very simple to find out contact point. In this paper, the parametric surface formula is adopted to road modeling to calculate road hight. Position indexing method is proposed to reduce memory size and resource possession, and a simple mathematical method for contact patch searching is also proposed. The developed road process program is tested in dynamic driving simulation on off-road. Conclusively, the new virtual road program shows high performance of road hight computation in vast field of off-road simulation.

잠재디리클레할당을 이용한 한국학술지인용색인의 풍력에너지 문헌검토 (Review of Wind Energy Publications in Korea Citation Index using Latent Dirichlet Allocation)

  • 김현구;이제현;오명찬
    • 신재생에너지
    • /
    • 제16권4호
    • /
    • pp.33-40
    • /
    • 2020
  • The research topics of more than 1,900 wind energy papers registered in the Korean Journal Citation Index (KCI) were modeled into 25 topics using latent directory allocation (LDA), and their consistency was cross-validated through principal component analysis (PCA) of the document word matrix. Key research topics in the wind energy field were identified as "offshore, wind farm," "blade, design," "generator, voltage, control," 'dynamic, load, noise," and "performance test." As a new method to determine the similarity between research topics in journals, a systematic evaluation method was proposed to analyze the correlation between topics by constructing a journal-topic matrix (JTM) and clustering them based on topic similarity between journals. By evaluating 24 journals that published more than 20 wind energy papers, it was confirmed that they were classified into meaningful clusters of mechanical engineering, electrical engineering, marine engineering, and renewable energy. It is expected that the proposed systematic method can be applied to the evaluation of the specificity of subsequent journals.

Text Mining in Online Social Networks: A Systematic Review

  • Alhazmi, Huda N
    • International Journal of Computer Science & Network Security
    • /
    • 제22권3호
    • /
    • pp.396-404
    • /
    • 2022
  • Online social networks contain a large amount of data that can be converted into valuable and insightful information. Text mining approaches allow exploring large-scale data efficiently. Therefore, this study reviews the recent literature on text mining in online social networks in a way that produces valid and valuable knowledge for further research. The review identifies text mining techniques used in social networking, the data used, tools, and the challenges. Research questions were formulated, then search strategy and selection criteria were defined, followed by the analysis of each paper to extract the data relevant to the research questions. The result shows that the most social media platforms used as a source of the data are Twitter and Facebook. The most common text mining technique were sentiment analysis and topic modeling. Classification and clustering were the most common approaches applied by the studies. The challenges include the need for processing with huge volumes of data, the noise, and the dynamic of the data. The study explores the recent development in text mining approaches in social networking by providing state and general view of work done in this research area.

유통업태 연구동향 분석: 백화점을 중심으로 (Research Trend Analysis of the Retail Industry: Focusing on the Department Store)

  • Hoe-Chang YANG
    • 융합경영연구
    • /
    • 제11권5호
    • /
    • pp.45-55
    • /
    • 2023
  • Purpose: As one of the continuous studies on the offline distribution industry, the purpose of this study is to find ways for offline stores to respond to the growth of online shopping by identifying research trends on department stores. Research design, data and methodology: To this end, this study conducted word frequency analysis, word co-occurrence frequency analysis, BERTopic, LDA, and dynamic topic modeling using Python 3.7 on a total of 551 English abstracts searched with the keyword 'department store' in scienceON as of October 10, 2022. Results: The results of word frequency analysis and co-occurrence frequency analysis revealed that research related to department stores frequently focuses on factors such as customers, consumers, products, satisfaction, services, and quality. BERTopic and LDA analyses identified five topics, including 'store image,' with 'shopping information' showing relatively high interest, while 'sales systems' were observed to have relatively lower interest. Conclusions: Based on the results of this study, it was concluded that research related to department stores has so far been conducted in a limited scope, and it is insufficient to provide clues for department stores to secure competitiveness against online platforms. Therefore, it is suggested that additional research be conducted on topics such as the true role of department stores in the retail industry, consumer reinterpretation, customer value and lifetime value, department stores as future retail spaces, ethical management, and transparent ESG management.

축소형 회전익 항공기의 간략화된 동적 모델링 (Simplified Dynamic Modeling of Small-Scaled Rotorcraft)

  • 이환;이상기
    • 한국항공우주학회지
    • /
    • 제33권8호
    • /
    • pp.56-64
    • /
    • 2005
  • 모형헬리콥터를 이용한 무인항공기 설계를 위해 비선형 형태의 수학적 모델이 선행되어야 한다. 모형헬리콥터는 실기 헬리콥터에 비해 회전수가 훨씬 높으며 따라서 동특성도 실물기에 비해 훨씬 빠르다는 차이점이 있다. 본 논문에서는 축소형 헬리콥터의 수학적 모델링에 필요한 정식화과정으로서 복잡성을 최소화하면서도 실제의 동특성에 잘 부합하도록 각 구성요소별로 계산한 후 전체로 합산하는 방법을 제시하였다. 제자리 비행과 전진비행에서 수치계산을 통해 트림 값들을 계산하고 제자리 비행조건에서 선형 시스템을 해석하여 모형헬리콥터의 비행모드를 분석하였다. 계산결과 일반적인 경향은 몇 가지 작은 부분 이외에는 대체로 다른 연구결과와 비슷하였다. 이 과정을 검증하기 위해서 비행시험을 수행하여 시스템식별에 의한 결과와 비교하는 연구가 후속 수행될 예정이다.

신문기사 빅데이터를 활용한 친환경 섬유의 추이에 관한 연구 (The Trends of Eco-Friendly Textiles Using Big Data from Newspaper Articles)

  • 조남범;이충권
    • 스마트미디어저널
    • /
    • 제13권2호
    • /
    • pp.95-107
    • /
    • 2024
  • 환경에 친화적인 제품과 서비스의 개발은 시대적인 트렌드가 되었고, 경제적 가치를 가진 친환경 섬유의 개발과 활용은 새로운 비즈니스 모델로서 주목받고 있다. 친환경 섬유에 대한 동향을 분석하고 추이를 파악하는 것은 기업, 정부, 소비자 등 다양한 이해관계자들에게 중요한 정보와 인사이트를 제공하여 지속가능한 성장에 도움을 줄 수 있다. 이에 본 연구는 2000년부터 2023년 6월까지 섬유패션 분야를 주로 다루는 신문의 기사데이터를 수집하여 분석을 진행하였다. '친환경 섬유'라는 키워드가 포함된 기사 총 12,331건을 수집하였고, 추출된 데이터에서 형태소 분석을 진행 후 연도별 토픽을 알아보기 위해 잠재 디리클레 할당과 동적 토픽 모델링 분석을 수행하였다. 연구 결과는 섬유산업의 지속 가능한 발전을 위한 전략적 지침과 인사이트를 제공함으로써, 친환경 섬유의 연구와 개발, 그리고 상용화를 촉진함에 있어서 도움이 될 것으로 기대된다.

선삭가공에서 절삭력을 이용한 공구마멸의 감지 (Detection of Tool Wear using Cutting Force Measurement in Turning)

  • 윤재웅;이권용;이수철
    • 한국윤활학회:학술대회논문집
    • /
    • 한국윤활학회 2000년도 제31회 춘계학술대회
    • /
    • pp.68-75
    • /
    • 2000
  • The development of flexible automation in the manufacturing industry is concerned with production activities performed by unmanned machining system. A major topic relevant to metal-cutting operations is monitoring tool wear, which affects process efficiency and product quality, and implementing automatic tool replacements. In this paper, the measurement of the cutting force components has been found to provide a method for an in-process detection of tool wear. Cutting force components are divided into static and dynamic components in this paper, and the static components of cutting force have been used to detect flank wear. To eliminate the influence of variations in cutting conditions, tools, and workpiece materials, the force modeling is performed for various cutting conditions. The normalized force disparities are defined in this paper, and the relationships between normalized disparity and flank wear are established. Finally, Artificial neural network is used to learn these relationships and detect tool wear. According to the proposed method, the static force components could provide the effective means to detect flank wear for varying cutting conditions in turning operation.

  • PDF

Relation Between News Topics and Variations in Pharmaceutical Indices During COVID-19 Using a Generalized Dirichlet-Multinomial Regression (g-DMR) Model

  • Kim, Jang Hyun;Park, Min Hyung;Kim, Yerin;Nan, Dongyan;Travieso, Fernando
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제15권5호
    • /
    • pp.1630-1648
    • /
    • 2021
  • Owing to the unprecedented COVID-19 pandemic, the pharmaceutical industry has attracted considerable attention, spurred by the widespread expectation of vaccine development. In this study, we collect relevant topics from news articles related to COVID-19 and explore their links with two South Korean pharmaceutical indices, the Drug and Medicine index of the Korea Composite Stock Price Index (KOSPI) and the Korean Securities Dealers Automated Quotations (KOSDAQ) Pharmaceutical index. We use generalized Dirichlet-multinomial regression (g-DMR) to reveal the dynamic topic distributions over metadata of index values. The results of our analysis, obtained using g-DMR, reveal that a greater focus on specific news topics has a significant relationship with fluctuations in the indices. We also provide practical and theoretical implications based on this analysis.