• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 2007년도 정기 학술대회 논문집
• /
• pp.188-192
• /
• 2007

This paper presents a current perspective on advanced fusion research trends in the construction industry as reflected in the proceedings of International Symposium on Automation and Robotics in Construction (ISARC) which has focused on advanced fusion technology in last decades. The paper reports the results of a 7-year analysis of papers between 2000 and 2006. The analysis focused on such data as research topics of the proceedings. The paper summarizes the data extracted from the paper and uses it to analyze advanced fusion research trends. The research result shows that the top research topics in advanced fusion research areas are construction robots and automation and intelligent construction management. The research also found that research related to advanced fusion technology is increasing throughout the world and topics are changing as current needs change.

• 정보관리학회지
• /
• 제36권1호
• /
• pp.53-71
• /
• 2019

최근 대학에서는 다양하게 변화하고 있는 실무현장과 학술연구분야를 반영하여 교과과정을 개편하자는 요구가 다양하게 나타나고 있다. 이에 이 연구에서는 교육과정 개편에 필요한 해외 문헌정보학 교육과정의 동향을 파악하고자 세 가지 측면에서 미국 문헌정보학 교과과정에 개설되어 있는 교과목을 분석하였다. 교과목 분석에 적용된 기준은 국가직무능력표준(NCS)의 문헌정보관리 직무단위, 한국연구재단의 국가과학기술표준분류와 학술연구분야 분류표에 나타난 문헌정보학 주제 분류이다. 세 가지 측면으로 분석한 결과 공통되게 나타난 현상은 시스템 구축설계 및 정보기술분야의 교과목 수가 많은 것이며 도서관 및 정보센터 경영과 이용자서비스도 교과목이 많은 주제 분야인 것으로 조사되었다.

• Journal of Information Science Theory and Practice
• /
• 제9권1호
• /
• pp.35-53
• /
• 2021

The study reported in this paper aimed to evaluate the topics and opinions of COVID-19 discussion found on Twitter. It performed topic modeling and sentiment analysis of tweets posted during the COVID-19 outbreak, and compared these results over space and time. In addition, by covering a more recent and a longer period of the pandemic timeline, several patterns not previously reported in the literature were revealed. Author-pooled Latent Dirichlet Allocation (LDA) was used to generate twenty topics that discuss different aspects related to the pandemic. Time-series analysis of the distribution of tweets over topics was performed to explore how the discussion on each topic changed over time, and the potential reasons behind the change. In addition, spatial analysis of topics was performed by comparing the percentage of tweets in each topic among top tweeting countries. Afterward, sentiment analysis of tweets was performed at both temporal and spatial levels. Our intention was to analyze how the sentiment differs between countries and in response to certain events. The performance of the topic model was assessed by being compared with other alternative topic modeling techniques. The topic coherence was measured for the different techniques while changing the number of topics. Results showed that the pooling by author before performing LDA significantly improved the produced topic models.

• 한국산업융합학회 논문집
• /
• 제27권2_2호
• /
• pp.445-456
• /
• 2024

This study aims to suggest service improvement opportunities by analyzing user review data of the top three OTT service apps(Netflix, Coupang Play, and TVING) on Google Play Store. To achieve this objective, we proposed a framework for uncovering service opportunities through the analysis of negative user reviews from OTT service providers. The framework involves automating the labeling of identified topics and generating service improvement opportunities using topic modeling and prompt engineering, leveraging GPT-4, a generative AI model. Consequently, we pinpointed five dissatisfaction topics for Netflix and TVING, and nine for Coupang Play. Common issues include "video playback errors", "app installation and update errors", "subscription and payment" problems, and concerns regarding "content quality". The commonly identified service enhancement opportunities include "enhancing and diversifying content quality". "optimizing video quality and data usage", "ensuring compatibility with external devices", and "streamlining payment and cancellation processes". In contrast to prior research, this study introduces a novel research framework leveraging generative AI to label topics and propose improvement strategies based on the derived topics. This is noteworthy as it identifies actionable service opportunities aimed at enhancing service competitiveness and satisfaction, instead of merely outlining topics.

• 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.

• 한국인공지능학회지
• /
• 제12권3호
• /
• pp.17-24
• /
• 2024

This study aims to derive a technology development roadmap in related fields by utilizing patent documents of financial technology. To this end, patent documents are extracted by dragging technical keywords from prior research and related reports on financial technology. By applying the TF-IDF (Term Frequency-Inverse Document Frequency) technique in the extracted patent document, which is a text mining technique, to the extracted patent documents, the Latent Dirichlet Allocation (LDA) algorithm was applied to identify the keywords and identify the topics of the core technologies of financial technology. Based on the proportion of topics by year, which is the result of LDA, promising technology fields and convergence fields were identified through trend analysis and similarity analysis between topics. A first-stage technology development roadmap for technology field development and a second-stage technology development roadmap for convergence were derived through network analysis about the technology data-based integrated management system of the high-dimensional payment system using RF and intelligent cards, as well as the security processing methodology for data information and network payment, which are identified financial technology fields. The proposed method can serve as a sufficient reason basis for developing financial technology R&D strategies and technology roadmaps.

• Journal of Information Science Theory and Practice
• /
• 제9권2호
• /
• pp.47-65
• /
• 2021

This study aims to identify specific topics, trends, and structural characteristics of scholarly communication research, based on 1,435 articles published from 1970 to 2018 in the Scopus database through Latent Dirichlet Allocation topic modeling, serial analysis, and network analysis. Topic modeling, time series analysis, and network analysis were used to analyze specific topics, trends, and structures, respectively. The results were summarized into three sets as follows. First, the specific topics of scholarly communication research were nineteen in number, including research resource management and research data, and their research proportion is even. Second, as a result of the time series analysis, there are three upward trending topics: Topic 6: Open Access Publishing, Topic 7: Green Open Access, Topic 19: Informal Communication, and two downward trending topics: Topic 11: Researcher Network and Topic 12: Electronic Journal. Third, the network analysis results indicated that high mean profile association topics were related to the institution, and topics with high triangle betweenness centrality, such as Topic 14: Research Resource Management, shared the citation context. Also, through cluster analysis using parallel nearest neighbor clustering, six clusters connected with different concepts were identified.

• 대한산업공학회지
• /
• 제43권3호
• /
• pp.213-228
• /
• 2017

Augmented reality (AR), which is a live direct or indirect view of a real-world environment combined with virtual objects, has grown rapidly owing to its wide application potential. Despite the growth of AR technology and its increased attraction, however, little attention has been paid to identifying sub-technologies of this technology and their evolving trends based on the data encompassing industrial competition. In the present study, therefore we collect AR-related patents granted until 2015 and then identify technology topics constituting AR technology by applying topic modeling to the patents' textual data. Subsequently, this study determines dynamic evolving trends with respect to those identified technology topics using indicators and maps based on the technology topics' patents and citations. The contributions of this study are twofold; it provides an overall understanding of AR technology's evolving trends based on text mining of AR patents and will assist technology experts in academia and industry in determining further R&D in the near future.

• 한국정밀공학회지
• /
• 제32권2호
• /
• pp.199-208
• /
• 2015

The aim of this paper is to review recent developments and commercialized products in the field of wearable wellness sensors and devices (WWSD). Although there are several dedicated researches, the completed theories and systematic techniques have not been well established. Therefore, we divided the WWSD into four different topics (healthcare, safety & prevention, gaming & lifestyle, and sports & fitness), and review the state of the arts and challenges on the applications on the sensor and device technologies with particular focus on WWSD. We also review the limitations of the current technologies on the developments and commercialized products. Finally, we suggest and discuss new research topics related on the four topics of the WWSD.

• 정보과학회 논문지
• /
• 제44권11호
• /
• pp.1138-1148
• /
• 2017

토픽 추출은 문서 집합으로부터 그 문서 집합을 대표하는 토픽을 자동 추출하는 기술이며 자연어 처리의 중요한 연구 분야이다. 대표적인 토픽 추출 방법으로는 잠재 디리클레 할당과 단어 군집화 기반 토픽 추출방법이 있다. 그러나 이러한 방법의 문제점으로는 토픽 중복 문제와 토픽 혼재 문제가 있다. 토픽 중복 문제는 특정 토픽이 여러 개의 토픽으로 추출되는 문제이며, 토픽 혼재 문제는 추출된 하나의 토픽 내에 여러 토픽이 혼재되어 있는 문제이다. 이러한 문제를 해결하기 위하여 본 연구에서는 토픽 중복 문제에 대해 강건한 잠재 디리클레 할당으로 토픽을 추출하고 단어 간 유사도를 이용하여 토픽 분리 및 토픽 병합의 단계를 거쳐 최종적으로 토픽을 보정하는 방법을 제안한다. 실험 결과 제안 방법이 잠재 디리클레 할당 방법에 비해 좋은 성능을 보였다.