• Title/Summary/Keyword: Recall information

Search Result 858, Processing Time 0.023 seconds

Performance and Limitations of a Korean Sentiment Lexicon Built on the English SentiWordNet (영어 SentiWordNet을 이용하여 구축한 한국어 감성어휘사전의 성능 평가와 한계 연구)

  • Shin, Donghyok;Kim, Sairom;Cho, Donghee;Nguyen, Minh Dieu;Park, Soongang;Eo, Keonjoo;Nam, Jeesun
    • 한국어정보학회:학술대회논문집
    • /
    • 2016.10a
    • /
    • pp.189-194
    • /
    • 2016
  • 본 연구는 다국어 감성사전 및 감성주석 코퍼스 구축 프로젝트인 MUSE 프로젝트의 일환으로 한국어 감성사전을 구축하기 위해 대표적인 영어 감성사전인 SentiWordNet을 이용하여 한국어 감성사전을 구축하는 방법의 의의와 한계점을 검토하는 것을 목적으로 한다. 우선 영어 SentiWordNet의 117,659개의 어휘중에서 긍정/부정 0.5 스코어 이상의 어휘를 추출하여 구글 번역기를 이용해 자동 번역하는 작업을 실시하였다. 그 중에서 번역이 되지 않거나, 중복되는 경우를 제거하고, 언어학 전문가들의 수작업으로 분류해낸 결과 3,665개의 감성어휘를 획득할 수 있었다. 그러나 이마저도 병명이나 순수 감성어휘로 보기 어려운 사례들이 상당수 포함되어 있어 실제 이를 코퍼스에 적용하여 감성어휘를 자동 판별했을 때에 맛집 코퍼스에서의 재현율(recall)이 긍정과 부정에서 각각 47.4%, 37.7%, IT 코퍼스에서 각각 55.2%, 32.4%에 불과하였다. 이와 더불어 F-measure의 경우, 맛집 코퍼스에서는 긍정과 부정의 값이 각각 62.3%, 38.5%였고, IT 코퍼스에서는 각각 65.5%, 44.6%의 낮은 수치를 보여주고 있어, SentiWordNet 기반의 감성사전은 감성사전으로서의 역할을 수행하기에 충분하지 않은 것으로 나타났다. 이를 통해 한국어 감성사전을 구축할 때에는 한국어의 언어적 속성을 고려한 체계적인 접근이 필요함을 역설하고, 현재 한국어 전자사전 DECO에 기반을 두어 보완 확장중인 SELEX 감성사전에 대해 소개한다.

  • PDF

XML Schema Matching based on Ontology Update for the Transformation of XML Documents (XML 문서의 변환을 위한 온톨로지 갱신 기반 XML 스키마 매칭)

  • Lee, Kyong-Ho;Lee, Jun-Seung
    • Journal of KIISE:Databases
    • /
    • v.33 no.7
    • /
    • pp.727-740
    • /
    • 2006
  • Schema matching is important as a prerequisite to the transformation of XML documents. This paper presents a schema matching method for the transformation of XML documents. The proposed method consists of two steps: preliminary matching relationships between leaf nodes in the two XML schemas are computed based on proposed ontology and leaf node similarity, and final matchings are extracted based on a proposed path similarity. Particularly, for a sophisticated schema matching, the proposed ontology is incrementally updated by users' feedback. furthermore, since the ontology can describe various relationships between concepts, the proposed method can compute complex matchings as well as simple matchings. Experimental results with schemas used in various domains show that the proposed method is superior to previous works, resulting in a precision of 97% and a recall of 83 % on the average. Furthermore, the dynamic ontology increased by 9 percent overall.

Cloning of Korean Morphological Analyzers using Pre-analyzed Eojeol Dictionary and Syllable-based Probabilistic Model (기분석 어절 사전과 음절 단위의 확률 모델을 이용한 한국어 형태소 분석기 복제)

  • Shim, Kwangseob
    • KIISE Transactions on Computing Practices
    • /
    • v.22 no.3
    • /
    • pp.119-126
    • /
    • 2016
  • In this study, we verified the feasibility of a Korean morphological analyzer that uses a pre-analyzed Eojeol dictionary and syllable-based probabilistic model. For the verification, MACH and KLT2000, Korean morphological analyzers, were cloned with a pre-analyzed eojeol dictionary and syllable-based probabilistic model. The analysis results were compared between the cloned morphological analyzer, MACH, and KLT2000. The 10 million Eojeol Sejong corpus was segmented into 10 sets for cross-validation. The 10-fold cross-validated precision and recall for cloned MACH and KLT2000 were 97.16%, 98.31% and 96.80%, 99.03%, respectively. Analysis speed of a cloned MACH was 308,000 Eojeols per second, and the speed of a cloned KLT2000 was 436,000 Eojeols per second. The experimental results indicated that a Korean morphological analyzer that uses a pre-analyzed eojeol dictionary and syllable-based probabilistic model could be used in practical applications.

Health and Nutritional Status of Industrial Workers (근로자의 근무유형별 건강상태와 영양섭취상태 비교 연구)

  • 오현미;윤진숙
    • Korean Journal of Community Nutrition
    • /
    • v.5 no.1
    • /
    • pp.13-22
    • /
    • 2000
  • The study was curried out to collect information to establish a framework for nutrition education for the prevention of chronic degenerative disease. We analyzed differences in diet quality, food habits and health status of workers by work condition. Anthrometric parameters of height, weight and body fat were measured and biochemical parameters including glucose, total cholesterol, GOT, GPT and hemoglobin were determinded for 194 subjects. To assess the nutrient intake and diet quality of workers, dietary intake was measured by the day 24-hour recall method, Average daily nutrient intake, except for phos-phorous and vitamin C was lower than Korean RDA. The obesity related behavior score was significantly better in laborers than in office workers, while chronic degenerative diseases related to food habit score was significantly better in laborers than in office workers, while chronic degenerative diseases related to the food habit score was beet in offices workers than in laborers. Blood pressure, blood glucose levels were significantly higher in laborer than in office workers. Dietary variety score (DVS) food composition group score(FCGS), mean adequacy ratio(MAR) of office worker were better than those of labor workers. When diet quality was evaluated by FCGS(food composition group score) 16.0% of the subjects acquired 5 points and 14.4% of the subjects acquired 2 points. MAR and INQ showed a significantly positive correlation with DVS and FCGS . This results indicated that the onset possibility of hypertension and diabetes mellitus among chronic degenerative disease was higher in laborers than in office workers, while the onset possibility of obesity was higher in office workers than in laborers. In conclusion the overall diet quality of office workers is betters than that of laborers, therefore, nutrition education for prevention of chronic degenerative disease of industrial workers needs to be more focused on the improvement of the health status of laborers.

  • PDF

The Comparison of Growth and Nutrient Intakes in Children with and without Atopic Dermatitis (아토피피부염 유병여부에 따른 영유아의 영양섭취와 성장 비교 연구)

  • Park, Seung-Joo;Lee, Jae-Sun;Ahn, Kang-Mo;Chung, Sang-Jin
    • Korean Journal of Community Nutrition
    • /
    • v.17 no.3
    • /
    • pp.271-279
    • /
    • 2012
  • The prevalence of atopic dermatitis (AD) has increased recently all over the world. Several studies worldwide reported growth retardation associated with AD, but few studies were reported in Korea. Therefore, the objective of this study was to identity the differences in growth and nutrient intakes between Korean children with and without AD. The participants were 71 AD children and age, gender-matched 81 control children aged 10 to 36 months. Demographic information was gathered by questionnaires. Height and weight were measured at clinic and health centers. Height and weight for age, and weight for height were converted as deviation in Z scores using World Health Organization Standard. A 24 hour dietary recall method was performed to estimate nutrient intakes. A higher percentage of AD children had insufficient energy and intakes of calcium, phosphorus, iron, zinc and vitamin B2, defined as intakes lower than 75% of the Dietary Reference Intakes for Korean, compared to the control group (P < 0.001, P < 0.001, P = 0.003, P = 0.001, P = 0.014, P = 0.001, respectively). The percentages of children with height and weight for age Z score below than-1 (stunted) were significantly higher in the AD group (P < 0.001 and P < 0.001, respectively). Multiple food restriction, defined as ${\geq}$ 3 food elimination, was associated with insufficient energy and intakes of calcium, phosphorus, iron, zinc, vitamins A and B2. In conclusion, children with AD need regular nutrient assessment and education about alternative food choices to avoid r food elimination in order to prevent growth retardation or inadequate nutrient intakes. Further longitudinal studies for growth and nutrient intakes should be performed to understand the patterns of growth in children with AD.

Nutritional and Health Status of Women Workers by Working Fields (여성 근로자의 영양섭취 및 건강상태 조사 : 사무직과 납 사업장 근로자의 비교)

  • Kim, Min-Kyoung;Kwon, Se-Mi;Kim, Hee-Seon
    • Korean Journal of Community Nutrition
    • /
    • v.12 no.6
    • /
    • pp.773-781
    • /
    • 2007
  • The objective of this study was to investigate the nutritional and health status of women industrial workers by working fields. One hundred forty eight (105 lead and 43 office) workers were recruited from March 2005 to October 2005. Information on age, education, smoking and drinking status were collected using questionnaire and nutrient intake and diet quality of workers were assessed by average of two-day 24 hr recall method. Biochemical indexes including blood lead level (PbB), indexes for iron status, serum calcium (Ca) and serum lipid profiles were analyzed from fasting venous blood or serum. Results showed that education level of lead workers was lower than that of office workers (p<0.05), but nutrient intake levels were not significantly different by working fields. Overall nutritional status of the subject were good except for calcium, vitamin $B_2$, C and folic acid intakes. PbB of lead workers were significantly higher than that of office workers while mean corpuscular hemoglobin concentration (MCHC) and serum Ca levels were significantly lower in lead workers. MCHC was positively correlated with zinc intake (r=0.166) and serum Ca was positively correlated with vitamin C intake (r=0.179). This study confirms that lead workers need extra care to keep their health and nutritional management especially for the nutrients known to interact with lead. Tailored nutrition education for workers at specific working fields needs to be more focused for the improvement of health status of industrial workers.

The Effect of Net Generation′s Fashion Value on the Purchase-Decision Important Factors at Internet Shopping Mall and the Preference for Fashion Design (N세대의 패션가치관이 인터넷쇼핑몰 구매결정 중요도와 패션디자인 선호도에 미치는 영향)

  • 최정선;유태순
    • Journal of the Korean Society of Clothing and Textiles
    • /
    • v.26 no.1
    • /
    • pp.39-49
    • /
    • 2002
  • The purpose of this study was to characterize the effect of Net fashion value regarding to the factors of purchase-decision at internet shopping mall and the preference for fashion design. The subjects for this sample survey, were junior high school and university students who had dwelled at pusan and ulsan in south korea. This study had 824 samples of each aged from 13 to 24 who had purchasing ability of fashion apparels at the interned shopping mal1. The sampling data in this survey was analyzed by frequency analysis, factor analysis, T-test, LSD-test, MANOVA and ANOVA of SPSS WIN package. The results of this study was as follows; 1. It was proved that advertising, pursuit of services and products, pursuit of information were considered first from Net generations fashion value. Next things were perception of danger and pursuit of convenience. It was proved that they considered it important A/S, recall, exchange and post management. 2. It was proved that there was difference at the preference for fashion design of according to Net generations fashion value. Color was considered to be the most important one. 3. Men had higher political value than women and 1318 teenagers had higher fashion value than semi-adult. Under high school educational course Net generation had more theoretical value than above university educational course Net generation did. Also, with the factor of average monthly income, political value was considered to be the most important. People whose monthly expenditure on purchase was above 50,000 won had higher social value than people whose expenditure was under 50,000 won but under 50,000 won had higher political value than above 50,000 won did.

Korean Unknown-noun Recognition using Strings Following Nouns in Words (명사후문자열을 이용한 미등록어 인식)

  • Park, Ki-Tak;Seo, Young-Hoon
    • The Journal of the Korea Contents Association
    • /
    • v.17 no.4
    • /
    • pp.576-584
    • /
    • 2017
  • Unknown nouns which are not in a dictionary make problems not only morphological analysis but also almost all natural language processing area. This paper describes a recognition method for Korean unknown nouns using strings following nouns such as postposition, suffix and postposition, suffix and eomi, etc. We collect and sort words including nouns from documents and divide a word including unknown noun into two parts, candidate noun and string following the noun, by finding same prefix morphemes from more than two unknown words. We use information of strings following nouns extracted from Sejong corpus and decide unknown noun finally. We obtain 99.64% precision and 99.46% recall for unknown nouns occurred more than two forms in news of two portal sites.

Relationship among Nutritional Intake Status, Eating Behaviors and Related Factors of the Elderly in Cheongju City (청주시 노인들의 영양섭취 실태와 식행동 및 관련요인과의 연관성)

  • Choi, Mee-Sook;Han, Kyung-Hee
    • Journal of the Korean Society of Food Culture
    • /
    • v.17 no.2
    • /
    • pp.131-140
    • /
    • 2002
  • This study was performed to assess the effect of eating behaviors and health-related variables on overall dietary quality. Ninety-four(male 21, female 73) elderly who were over 60 residing in middle income areas in Cheongju city participated. Information on general characteristics of the elderly, health-related life style, regularity of meal, meal balance and desirable eating habits were obtained by interview based on questionnare. Dietary nutrient intake data were obtained through the 24 hour recall method. The mean age and BMI of the subjects were 73.3 years old and 23.3(male 21.8 female 23.7) respectively. The proportions of underweight and hypertension were 19.2% and 36.2%. Most nutrients except vitamin $B_2$ and calcium were consumed over 75% of the RDA. The Mean Adequacy of Ratio(MAR) of nutrient intake was 0.64(male 0.72, female 0.62). The average score of regularity of meal, meal balance, and desirable eating habits was 14.4 out of a possible 16, 13.7 out of a possible 24 and 5.5 out of a possible 16 points respectively. Male than female, older subjects than young subjects, and those living with their spouses than with other family or living alone had better scores in eating behaviors. Smoking, chewing ability and eating alone vs eating with company affected overall of regulality of meal and meal balance(p<0.05). Positive correlation (p<0.05) was also dietary quality. There was a positive correlation between the mean adequacy ratio, score observed between scores in regularity of meal and meal balance. Therefore, the elderly should be encouraged to eat a variety of food, maintain good dental health, keep regularity of meal and have meals with company to help improve overall dietary quality and eventually achieve optimal nutritional status.

Email Extraction and Utilization for Author Disambiguation (저자 식별을 위한 전자메일의 추출 및 활용)

  • Kang, In-Su
    • The Journal of the Korea Contents Association
    • /
    • v.8 no.6
    • /
    • pp.261-268
    • /
    • 2008
  • An author of a paper is represented as his/her personal name in a bibliographic record. However, the use of names to indicate authors may deteriorate recall and precision of paper and/or author search, since the same name can be shared by many different individuals and a person can write his/her name in different forms. To solve this problem, it is required to disambiguate same-name author names into different persons. As features for author resolution, previous studies have exploited bibliographic attributes such as co-authors, titles, publication information, etc. This study attempts to apply email addresses of authors to disambiguate author names. For this, we first handle the extraction of email addresses from full-text papers, and then evaluate and analyze the effect of email addresses on author resolution using a large-scale test set.