• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.409-410
• /
• 2019

본 논문에서는 국내 갑상선암의 연구 동향을 파악하기 위해 텍스트 중심의 접근법을 제안한다. 국내 갑상선암은 2000년대에 들어서며 발생이 급증하여 과잉진단의 논란을 불러일으켰으나, 다양한 분야의 자정 노력으로 수술 환자수가 크게 줄었다. 본 연구에서는 텍스트 마이닝 기술을 사용하여 디비피아에 등록되어 있는 갑상선암 관련 논문의 키워드와 초록을 수집하여 분석하였다. 1980년대는 대부분의 사례보고가 있었고 1990년대에 들어서면서 검진을 통한 조기 진단의 내용이 자주 나타났다. 2000년대에는 여러 장비들을 활용한 검사방법과 미세한 암의 발견에 대한 논의가 증가하였음을 확인 할 수 있었다. 2010년대에 들어서는 환자의 삶의 질에 대한 연구가 많이 이루어졌다. 지난 수십 년 동안 갑상선 암 연구 주제에 대해 뚜렷한 변화가 나타났으며, 향후 연구의 기초자료로 활용될 수 있으리라 기대된다.

• Journal of Digital Convergence
• /
• v.17 no.4
• /
• pp.49-55
• /
• 2019

This study is on the trend of real estate market using text mining and big data. The data were collected through internet news posted on Naver from August 2016 to August 2017. As a result of TF-IDF analysis, the frequency was high in the order of housing, sale, household, real estate market, and region. Many words related to policies such as loan, government, countermeasures, and regulations were extracted, and the region - related words appeared the most frequently in Seoul. The combination of the words related to the region showed that the frequencies of 'Seoul - Gangnam', 'Seoul - Metropolitan area', 'Gangnam - reconstruction' and 'Seoul - reconstruction' appeared frequently. It can be seen that the people's interest and expectation about the reconstruction of Gangnam area is high.

• Journal of Korea Game Society
• /
• v.22 no.1
• /
• pp.87-98
• /
• 2022

With the development of fourth industrial revolution-related technology and increased demands for non-face-to-face services, VR games attract attention. This study collected VR game review data from an online game platform STEAM and analyzed chronical trends using text mining and word cloud analysis. According to the results, experience and perceived cost were major trends from 2016 to 2017, increased demands for FPS and rhythm games were from 2018 to 2019, and story and immersion were from 2020 to 2021. It aims to contribute to expanding the base of VR games by identifying the keywords VR users take interest in by period.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.729-734
• /
• 2022

Various studies using accident cases are being conducted to identify the causes of accidents in the construction industry, but studies on the differences between public and private construction are insignificant. In this study, web scraping and text mining technologies were applied to analyze the causes of accidents by order type. Through statistical analysis and word cloud analysis of more than 10,000 structured and unstructured data collected, it was confirmed that there was a difference in the types and causes of accidents in public and private construction. In addition, it can contribute to the establishment of safety management measures in the future by identifying the correlation between major accident causes.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.475-476
• /
• 2022

본 논문에서는 청각장애인의 사회참여성 증진 및 사회적 차별감소를 목적으로 딥러닝 영상인식 기반으로 MediaPipe 기술을 활용한 수화-텍스트 번역시스템을 설계한다. 제시하는 시스템은 실시간으로 수집된 수화 사용자의 영상정보를 통해 동작과 표정을 인식하여 텍스트로 번역함으로써 장애인과 비장애인의 원활한 의사소통 서비스를 제공하는 것을 주 목적으로한다. 향후 개선된 수화 인식 및 문장 조합을 통해 일상에서 청각장애인과 일반인의 자유로운 커뮤니케이션을 제공하는 서비스로 확장하고자한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.714-715
• /
• 2023

최근들어 청원 시스템은 사람들의 다양한 의견을 반영하고 대응하기 위한 중요한 수단으로 부상하고 있다. 그러나 많은 양의 청원 글들을 수작업으로 분류하는 것은 매우 시간이 많이 소요되며, 인적 오류가 발생할 수 있는 문제점이 존재한다. 이를 해결하기 위해 자연어처리(NLP) 기술을 활용한 청원 분류 시스템을 개발하는 것이 필요하다. 본 연구에서는 BERT(Bidirectional Encoder Representations from Transformers)[1]를 기반으로 한 텍스트 필터링 시스템을 제안한다. BERT 는 최근 자연어 분류 분야에서 상위 성능을 보이는 모델로, 이를 활용하여 청원 글을 분류하고 분류된 결과를 이용해 해당 글의 노출여부를 결정한다. 본 논문에서는 BERT 모델의 이론적 배경과 구조, 그리고 미세 조정 학습 방법을 소개하고, 이를 활용하여 청원 분류 시스템을 구현하는 방법을 제시한다. 우리가 제안하는 BERT 기반의 텍스트 필터링 시스템은 청원 글 분류를 자동화하고, 이에 따른 대응 속도와 정확도를 향상시킬 것으로 기대된다. 또한, 이 시스템은 다양한 분야에서 응용 가능하며, 대용량 데이터 처리에도 적합하다. 이를 통해 대학 청원 시스템에서 혐오성 발언 등 부적절한 내용을 사전에 방지하고 학생들의 의견을 효율적으로 수집할 수 있는 기능을 제공할 수 있다는 장점을 가지고 있다.

• Journal of KIISE
• /
• v.44 no.6
• /
• pp.581-586
• /
• 2017

For automatic web scraping, unnecessary components such as menus and advertisements need to be removed from web pages and main contents should be extracted automatically. A content block tends to be located in the middle of a web page. In particular, Korean web documents rarely include metadata and have a complex design; a suitable method of content extraction is therefore needed. Existing content extraction algorithms use the textual and structural features of content blocks because processing visual features requires heavy computation for rendering and image processing. In this paper, we propose a new content extraction method using the tag positions in HTML as a quasi-visual feature. In addition, we develop a tag rank position, a type of tag position not affected by text length, and show that gradient boosting with the tag rank position is a very accurate content extraction method. The result of this paper shows that the content extraction method can be used to collect high-quality text data automatically from various web pages.

• Journal of KIISE:Databases
• /
• v.28 no.3
• /
• pp.406-417
• /
• 2001

With the advances in multimedia databases on the World Wide Web, it becomes more important to provide users with the search capability of distributed multimedia data. While there have been many studies about the database selection and the collection fusion for text databases. The multimedia databases on the Web have autonomous and heterogeneous properties and they use mainly the content based retrieval. The collection fusion problem of multimedia databases is concerned with the merging of results retrieved by content based retrieval from heterogeneous multimedia databases on the Web. This problem is crucial for the search in distributed multimedia databases, however, it has not been studied yet. This paper provides novel algorithms for processing the collection fusion of heterogeneous multimedia databases on the Web. We propose two heuristic algorithms for estimating the number of objects to be retrieved from local databases and an algorithm using the linear regression. Extensive experiments show the effectiveness and efficiency of these algorithms. These algorithms can provide the basis for the distributed content based retrieval algorithms for multimedia databases on the Web.

• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.47-53
• /
• 2021

With increasing interest in the 4th industrial revolution, data-driven scientific methodologies have developed. However, there are limitations of data collection in the real estate field of research. In addition, as the public becomes more knowledgeable about the real estate market, the qualitative sentiment comes to play a bigger role in the real estate market. Therefore, we propose a method to collect quantitative data that reflects sentiment using text mining and k-means algorithms, rather than the existing source data, and to predict the direction of housing index through artificial neural network learning based on the collected data. Data from 2012 to 2019 is set as the training period and 2020 as the prediction period. It is expected that this study will contribute to the utilization of scientific methods such as artificial neural networks rather than the use of the classical methodology for real estate market participants in their decision making process.

• Cross-Cultural Studies
• /
• v.45
• /
• pp.109-143
• /
• 2016

This article examines distinctive linguistic shifts of translational English in an effort to verify the validity of the translation universals hypotheses, including simplification, explicitation, normalization and leveling-out, which have been most heavily explored to date. A large-scale study involving comparable corpora of translated and non-translated English newspaper texts has been carried out to typify particular linguistic attributes inherent in translated texts. The main findings are as follows. First, by employing the parameters of STTR, top-to-bottom frequency words, and mean values of sentence lengths, the translational instances of simplification have been detected across the translated English newspaper corpora. In contrast, the portion of function words produced contrary results, which in turn suggests that this feature might not constitute an effective test of the hypothesis. Second, it was found that the use of connectives was more salient in original English newspaper texts than translated English texts, being incompatible with the explicitation hypothesis. Third, as an indicator of translational normalization, lexical bundles were found to be more pervasive in translated texts than in non-translated texts, which is expected from and therefore support the normalization hypothesis. Finally, the standard deviations of both STTR and mean sentence lengths turned out to be higher in translated texts, indicating that the translated English newspaper texts were less leveled out within the same corpus group, which is opposed to what the leveling-out hypothesis postulates. Overall, the results suggest that not all four hypotheses may qualify for the label translation universals, or at least that some translational predictors are not feasible enough to evaluate the effectiveness of the translation universals hypotheses.