• 한국콘텐츠학회논문지
• /
• 제11권5호
• /
• pp.75-83
• /
• 2011

어스팩트 지향 프로그래밍은 시스템에서 크로스커팅 개념을 추출하고 소프트웨어 모듈화를 통하여 기능의 분산과 코드의 혼란을 해결하기 위한 패러다임이다. 현존하는 어스팩트 개발 방법은 크로스커팅 대상 영역을 추출에 어려움이 있기 때문에, 어스팩트 마이닝을 적용하기가 쉽지 않다. 어스팩트 마이닝에서는 기존 프로그램의 리팩토링 요소를 크로스커팅 영역으로 변환하는 기술이 필수적이다. 본 논문에서는 리팩토링에 적합한 크로스커팅 영역 자동 추출을 위한 시스템에서 크로스커팅 개념을 추출하기 위한 어스팩트 마이닝 방법을 제안한다. 소스 모듈의 추상 구문구조 명세를 이용하여, 모듈의 구조적 중복 관계 요소를 추출한다. Apriori 알고리즘을 통하여 중복 구문트리를 생성하고, 크로스커팅 영역 대상인 중복된 소스 모듈을 자동 생성, 최적화 할 수 있다. Berkeley Yacc의 berbose.c 모듈을 제안하는 마이닝 프로세스에 적용해 본 결과, 원본 대비 9.47%의 길이와 부피의 감소하였고, CCFinder 대비 4.92%의 길이 감소, 5.11%의 부피 감소 효과를 확인하였다.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2018년도 제30회 한글 및 한국어 정보처리 학술대회
• /
• pp.652-657
• /
• 2018

With the rapid development of e-commerce, many customers can now express their opinion on various kinds of product at discussion groups, merchant sites, social networks, etc. Discerning a consensus opinion about a product sold online is difficult due to more and more reviews become available on the internet. Opinion Mining, also known as Sentiment analysis, is the task of automatically detecting and understanding the sentimental expressions about a product from customer textual reviews. Recently, researchers have proposed various approaches for evaluation in sentiment mining by applying several techniques for document, sentence and aspect level. Aspect-based sentiment analysis is getting widely interesting of researchers; however, more complex algorithms are needed to address this issue precisely with larger corpora. This paper introduces an approach of knowledge representation for the task of analyzing product aspect rating. We focus on how to form the nature of sentiment representation from textual opinion by utilizing the representation learning methods which include word embedding and compositional vector models. Our experiment is performed on a dataset of reviews from electronic domain and the obtained result show that the proposed system achieved outstanding methods in previous studies.

• 경영정보학연구
• /
• 제22권3호
• /
• pp.81-97
• /
• 2020

최근의 감성분류 연구는 출력변수가 하나인 단일레이블 분류방법을 사용한 연구가 많다. 특히, 이러한 연구는 하나의 극성 값(긍정, 부정)만을 찾는 연구가 많다. 그러나 한 문장 안에는 다중적인 의미가 내포되어 있다. 그 중에서도 감정과 오피니언이 이러한 특징을 갖는다. 본 논문은 두 가지 연구목적을 제시한다. 첫째, 한 문장 안에 다양한 토픽(주제 또는 애스팩트)이 있다는 사실을 기반으로, 해당 문장을 각 애스팩트 별로 감성을 분류하는 애스팩트 마이닝을 수행한다. 둘째, 두개 이상의 종속변수(출력 값)를 한 번에 분석하는 다중레이블 분류방법을 적용한다. 이에 본 연구는 감성분류의 연구가 단일분류기에 의해서만 이루어진 연구를 개선하고자 다중레이블 분류방법에 의한 애스팩트 마이닝을 수행하고자 한다. 이와 같은 연구목적을 달성하기 위해 국내 뮤지컬 데이터를 수집하였다. 분석결과 문장 안에 있는 다양한 애스팩트별 감성을 추출하였고, 유의한 결과를 얻었다.

• East Asian mathematical journal
• /
• 제35권4호
• /
• pp.489-508
• /
• 2019

In this paper we used text mining method to analyze journals of mathematics education posterior to the year of 2016. To figure out trends of mathematics education research. we analyzed the key words largely mentioned in the recent mathematics education journals by Term Frequency and Term Frequency-Inverse Document Frequency method. We also looked at how these keywords match up with the key words that appear of education to prepare for future society. This result can infer the characteristics of mathematics education research in the aspect upcoming research topics.

• 한국컴퓨터정보학회논문지
• /
• 제28권12호
• /
• pp.259-266
• /
• 2023

본 논문에서는 속성기반 오피니언 마이닝(ABOM)을 적용한 협업 필터링의 정확도 성능을 개선할 수 있는 알고리즘을 제안한다. 실험을 위해 국내 스마트폰 사용자의 스마트폰 앱에 대한 총 1,227건의 온라인 소비자 리뷰 데이터가 분석에 사용되었다. KKMA(꼬꼬마)분석기를 이용하여 형태소 분석 및 KOSAC를 사용하여 감성어 분석 후 LDA 토픽 모델링을 사용하여 속성 추출한 가중치 값을 부여한 리뷰별로 토픽 모델링 결과를 이용하여 협업필터링의 평점과 감성스코어의 평점을 합산한 평균값 정확도 오차를 계산한 통계모형 성능 평가인 MAE, MAPE, RMSE를 사용하였다. 실험을 통해 추천 알고리즘 중 전통적인 협업필터링과 LDA 속성 추출과 감성분석을 결합한 속성기반 오피니언 마이닝(Aspect-Based Opinion Mining, ABOM) 기법을 결합하여 온라인 고객의 앱 평점(APP_Score) 대한 정확도를 예측하였다. 분석 결과 전통적인 협업필터링을 구현한 평점의 정확도 보다 속성기반 오피니언 마이닝 CF를 적용한 평점의 예측 정확도가 더 우수한 것으로 나타났다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1998년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.361-369
• /
• 1998

Recently, the improvement of on-board satellite sensors covering hyperspectral image sensors, high spatial resolution sensors provide data on earth in diverse aspect. The application field relating remotely sensed data also varies depending on what type of job one wants. The various resolution of sensors from low to extremely high is also available on the market with a user defined specific location. The expense to purchase remote sensed data is going down compare to the cost it need past few years ago in terms of research or private use. Now, the satellite remote sensed data is used on the field of forecasting, forestry, agriculture, urban reconstruction, geology, or other research field in order to extract meaningful information by applying special techniques of image processing. There are many image processing packages available worldwide and one common aspect is that they are expensive. There need to be a advanced satellite data processing package for people who can not afford commercial packages to apply special remote sensing techniques on their data and produce valued-added product. The study was carried out with the purpose of developing a special satellite data processing package which covers almost every satellite produced data with normal image processing functions and also special functions needed on specific research field with friendly graphical user interface (GUI). And for the people with any background of remote sensing with windows platform.

• 한국정보시스템학회지:정보시스템연구
• /
• 제29권4호
• /
• pp.137-151
• /
• 2020

Purpose Domestic asset management fintech companies are expected to grow by leaps and bounds along with the implementation of the "Data bills." Contrary to the market fever, however, academic research is insufficient. Therefore, we want to analyze user reviews of asset management fintech companies that are expected to grow significantly in the future to derive strengths and complementary points of services that have been provided, and analyze key elements of asset management fintech companies. Design/methodology/approach To analyze large amounts of review text data, this study applied text mining techniques. Bank Salad and Toss, domestic asset management application services, were selected for the study. To get the data, app reviews were crawled in the online app store and preprocessed using natural language processing techniques. Topic Modeling and Aspect-Sentiment Analysis were used as analysis methods. Findings According to the analysis results, this study was able to derive the elements that asset management fintech companies should have. As a result of Topic Modeling, 7 topics were derived from Bank Salad and Toss respectively. As a result, topics related to function and usage and topics on stability and marketing were extracted. Sentiment Analysis showed that users responded positively to function-related topics, but negatively to usage-related topics and stability topics. Through this, we were able to extract the key elements needed for asset management fintech companies.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 춘계정기학술대회
• /
• pp.253-260
• /
• 2001

Understanding and adapting to changes of customer behavior is an important aspect for a company to survive in continuously changing environment. The aim of this paper is to develop a methodology which detects changes of customer behavior automatically from customer profiles and sales data at different time snapshots. For this purpose, we first define three types of changes as emerging pattern, unexpected change and the added / perished rule. Then we develop similarity and difference measures for rule matching to detect all types of change. Finally, the degree of change is evaluated to detect significantly changed rules. Our proposed methodology can evaluate degree of changes as well as detect all kinds of change automatically from different time snapshot data. A case study for evaluation and practical business implications for this methodology are also provided.

• 대한물리의학회지
• /
• 제14권3호
• /
• pp.55-62
• /
• 2019

PURPOSE: Text-mining has been shown to be useful for understanding the clinical characteristics and patients' concerns regarding a specific disease. Low back pain (LBP) is the most common disease in modern society and has a wide variety of causes and symptoms. On the other hand, it is difficult to understand the clinical characteristics and the needs as well as demands of patients with LBP because of the various clinical characteristics. This study examined online texts on LBP to determine of text-mining can help better understand general characteristics of LBP and its specific elements. METHODS: Online data from www.spine-health.com were used for text-mining. Keyword frequency analysis was performed first on the complete text of postings (full-text analysis). Only the sentences containing the highest frequency word, pain, were selected. Next, texts including the sentences were used to re-analyze the keyword frequency (pain-text analysis). RESULTS: Keyword frequency analysis showed that pain is of utmost concern. Full-text analysis was dominated by structural, pathological, and therapeutic words, whereas pain-text analysis was related mainly to the location and quality of the pain. CONCLUSION: The present study indicated that text-mining for a specific element (keyword) of a particular disease could enhance the understanding of the specific aspect of the disease. This suggests that a consideration of the text source is required when interpreting the results. Clinically, the present results suggest that clinicians pay more attention to the pain a patient is experiencing, and provide information based on medical knowledge.

• Geomechanics and Engineering
• /
• 제3권1호
• /
• pp.17-28
• /
• 2011

This paper presents an analytical solution for steady state flow into a close-ended cylindrical permeameter. The soil medium is considered to be uniform, isotropic, and of infinite thickness. Laplace equation is solved by considering rotational symmetry and by using curvilinear coordinates obtained from conformal mapping. The deduced shape factors, which are compared to approximate relationships obtained from both numerical and physical modelling, and idealizations involving ellipsoidal cavities, are proposed for use in field measurements. It is shown that some of the shape factors obtained are significantly different from published values and show a much higher dependence of the rate of flow on the aspect ratio, than deduced from approximate solutions.