한국인과 중국인의 단어 연상의미 조사 분석

박선옥(Park Sun-ok) 중앙어문학회 2008 語文論集 Vol.38 No.-

This paper, titled “Word Association Research Methods”, reports on a comparative questionnaire conducted by 200 native Koreans and 200 native Chinese who are requested to answer an associative word within ten seconds per question. The result was explored according to each language: 1) Analyzing associative words indicating paradigmatic and syntagmic relationship from a linguistic viewpoint 2) Analyzing the meanings and features from social and cultural viewpoint; and 3) The meaningful interpretation was carried out by comparing and contrasting the character of the two languages. In this questionnaire, the analysis of words association was conducted by using only six words, which were ‘hobby’, ‘appear’, ‘happen’, ‘broad’, ‘afraid’, and ‘beautiful’, out of twenty words. Approximately 55% of Koreans and 44% of Chinese replied kinds of ‘hobby’in response to the question ‘what word makes you think of ‘hobby’’. ‘Talent’, a word of high frequency in word association has represented the feature of social class well. ‘Disappear’, which has the opposite meaning of ‘appear’, is a word of high frequency in word association of ‘appear’. When seeing any words, Koreans associated them with negative circumstance or objects. However, in case of Chinese, it was vice versa. Chinese presented ‘appear’ as a word association of ‘happen’. Considering ‘miracle’ is associated many times as a word association of ‘happen’ as well as a word association of ‘appear’, Chinese have strongly recognized ‘happen’ and ‘appear’ as having a meaningful relationship than have Koreans. A meaningful analysis result was achieved for the given words ‘broad’ and ‘beautiful’. Unlike researches have done before, which have studied word association from linguistic viewpoint, this findings are significant in that the research involved two groups from different languages and cultures comparing word association. Such a research might also be effectively applied to the communication and lexicon education of Korean learners.

한국인과 중국인의 단어 연상의미 조사 분석과 단어 연상을 활용한 한국어 어휘 교육 방법

박선옥 한국어의미학회 2008 한국어 의미학 Vol.25 No.-

The aim of this paper is threefold: 1) To analyze the result of word association for Koreans and Chinese, to organize a semantic network and examine how to associate; 2) To compare and contrast the results of word association of Koreans and Chinese, thus recognizing features with a background from other languages; 3) To grope for a way to make use of word association for Chinese who are learning Korean. Research of word association was conducted with 200 native Koreans in their twenties and 200 native Chinese of the same age who were requested to answer a questionnaire that consisted of 20 word-association questions within 10 seconds per question. Of the 20 words, only five—‘romance,’ ‘hope,’ ‘run,’ ‘exercise,’ and ‘red’—were analyzed. Koreans associated ‘romance’ with ‘love’, which is an attribute of ‘romance’. On the other hand, Chinese thought of the feelings of ‘happy’ and ‘beautiful.’ Furthermore, lexical field that learners have is chosen as words which students will learn in class, and the error that learners make when they choose inappropriate words would be prevented in advance. Most of all it leads to student-centered learning, and the effect of learning is getting better.

단어 연상을 통한 언어장애아동의 연상어 반응 유형 및 품사 유형 분석

박선희(Sun Hee Park) 한국언어치료학회 2016 言語治療硏究 Vol.25 No.1

Purpose: The purpose of this study was to investigate response words through word association between children with language impairments and normal children. Response words were analyzed to find appropriate stimuli words for the children with language impairment in order to seek effective vocabulary instruction methods for children with language impairments. Methods: Twenty children with language impairments and 20 age-matched normal children participated in this study. Twenty stimuli words were selected based on word frequency, accessibility, and understanding and an investigation was constructed from the literature review. The stimuli words were comprised of ten nouns, five adjectives, and five verbs. Response word types were classified by form, meaning, and pragmatics for the data analysis.Form-based associations were classified by morphology, modification, description, and meaning-based associations were classified by synonym, antonym, coordinate, hypernym, hyponym, and symbolic. Response word of word class were analyzed separately as noun, verb, adjective, adverb, and the like. In the analysis of response words response type and in the analysis of the percentage and word class response words mean, the difference between the two groups was use to compare t-verification. Results: First, form and meaning were significantly different between the children with language impairment and normal children. Children with language impairment expressed form-based association more compared to normal children. Second, noun use was significantly different between the children with language impairments and normal children. The children with language impairment expressed noun association more compared to normal children.

Hierarchical Structure in Semantic Networks of Japanese Word Associations

( Maki Miyake ),( Terry Joyce ),( Jaeyoung Jung ),( Hiroyuki Akama ) 한국언어정보학회 2007 학술대회 논문집 Vol.2007 No.-

This paper reports on the application of network analysis approaches to investigate the characteristics of graph representations of Japanese word associations. Two semantic networks are constructed from two separate Japanese word association databases. The basic statistical features of the networks indicate that they have scale-free and small-world properties and that they exhibit hierarchical organization. A graph clustering method is also applied to the networks with the objective of generating hierarchical structures within the semantic networks. The method is shown to be an efficient tool for analyzing large-scale structures within corpora. As a utilization of the network clustering results, we briefly introduce two web-based applications: the first is a search system that highlights various possible relations between words according to association type, while the second is to present the hierarchical architecture of a semantic network. The systems realize dynamic representations of network structures based on the relationships between words and concepts.

교육대학교 학생들의 `전기` 용어의 연상 단어 및 정의에 대한 네트워크 분석

송영욱 ( Youngwook Song ) 한국과학교육학회 2016 한국과학교육학회지 Vol.36 No.5

이 연구의 목적은 네트워크 분석법을 활용하여 `전기` 용어에 대한 연상 단어 및 정의에 사용한 핵심 단어가 무엇인지 확인하고, 핵심단어들이 어떻게 활성화되어 인지 구조를 이루는지 알아보는 데 있다. 연구대상은 지방 소재 교육대학교 1학년 대학생 총 83명으로 하였다. 대학생들의 성별과 고등학교 때 물리 과목 이수 여부에 따라 수업전과 수업 후로 나누어 `전기` 용어에 대한 연상 단어 및 정의를 네트워크 분석하였다. 연구 결과 대학생들이 `전기`하면 가장 많이 떠올리는 단어는 수업 전 `에너지`이고 수업 후에는 `전류`, `전자`이다. 그리고 `전기` 정의에 가장 많이 사용한 단어는 수업 전 `에너지`, `흐름`, `전자`이고 수업 후에는 `전자`, `이동`, `전하` 이다. `전기` 용어의 연상 단어에는 성별과 고등학교 때 물리 과목 이수 여부에 따라 조금 다른 네트워크 구조를 이루고 있었지만, 수업 후에는 대학생들의 특성에 상관없이 비슷한 네트워크 구조를 보였다. `전기` 용어의 정의에서는 수업 전 성별에 따라서는 비슷한 네트워크 구조를 갖고 있었고, 고등학교 때 물리 과목 이수 여부에 따라서는 조금 다른 네트워크 구조를 보였다. 하지만 수업 후에는 대학생들의 특성에 상관없이 비슷한 네트워크 구조가 나타났다. 끝으로 대학생들의 `전기` 용어에 대한 네트워크 분석 결과에 대한 교육적 시사점을 논의하였다. This research aimed to identify core words used as associative words and definitions for expressing `electricity` terminology and to find how core ones are activated to form a cognitive structure, using network analysis. The participants targeted 83 university freshmen students in the University of Education located in suburbs. Depending on their gender, whether or not they completed physics in high school, the associative words and definitions were analyzed using the network method, classifying two sections: before-lesson and after-lesson. The result is as follows: At before-lesson associative words for `electricity` terminology, a slightly different network construction was revealed based on their two properties. However, after the class, they showed similar network structure irrespective of their distinctive characteristics. When it comes to other `electricity` definitions, before taking the course, they had similar network connection across the gender but based on physics education status, there appeared subtle differences. Ultimately, after the class they demonstrated similar network structure regardless of their features. In conclusion, this paper suggests educational implications on network analysis, which covers `electricity` terminology of university students.

한국의 라틴아메리카 연구동향 분석(방법)의 제안: 토픽모델링, 연관분석 그리고 워드클라우드 분석을 중심으로

이태혁,강지훈 한국외국어대학교 중남미연구소 2023 중남미연구 Vol.42 No.1

The purpose of this study is to analyze the Latin American research trends in Korea through methodological diversity. In other words, based on the leading research related to this research topic, this paper maintains the methodological differentiation of existing qualitative or basic statistics by conducting machine learning-based data analysis. To this end, first, this paper collects data through the Research Information Sharing Service (RISS). The subject and scope of this study is to set to 'Latin America (Jungnammi)' as the title of the paper and and 'Latin America' in the keyword of the abstract, and subsequently are collected according to the definition of crawling in the R software program. Secondly, the data extracted by the definition of crawling is preprocessed for topic modeling, association analysis, and word cloud analysis, which are the research methods of this paper, and then the data is processed with algorithms suitable for each analysis. Third, the unit of analysis of this study is the classification by generation (years). Therefore, based on the results calculated through the analysis of the three big data, the data classified in this way examines trends in Latin American research in Korea. The main topic of research in Latin America, which has been steadily conducted since 1968, is economy (trade)-related topics. and Also other research themes have been studied based on Latin American region-related or global issue.

한국 지중해 지역 연구 현황의 통계적 접근과 해석 -학술지 『지중해지역연구』를 중심으로-

문승호 부산외국어대학교 지중해지역원 2019 지중해지역연구 Vol.21 No.1

In this study, we used the key words of 365 papers printed from 2002 to 2018 in the Journal of “Mediterranean Area Studies” as data to investigate the correlation of each subject. We analyze the tendency of “Mediterranean Area Studies” through analysis of the main text by using statistical methods such as word clouding and association analysis. And then, we could visualize the information between key words and also we measured the association rules of them by using support, confidence, and lift as the criteria. In recent years, integrated learning is becoming a global trend not only in Korea but also in the world. So, we would like to try another statistical approach to the research of the Mediterranean region in the future.

마켓 인사이트를 위한 상품 리뷰의 다차원 분석 방안

박정현(Park Jeong Hyun),이서호(Lee Seo Ho),임규진(Lim Gyu Jin),여운영(Yeo Un Yeong),김종우(Kim Jong Woo) 한국지능정보시스템학회 2020 지능정보연구 Vol.26 No.2

With the development of the Internet, consumers have had an opportunity to check product information easily through E-Commerce. Product reviews used in the process of purchasing goods are based on user experience, allowing consumers to engage as producers of information as well as refer to information. This can be a way to increase the efficiency of purchasing decisions from the perspective of consumers, and from the sellers point of view, it can help develop products and strengthen their competitiveness. However, it takes a lot of time and effort to understand the overall assessment and assessment dimensions of the products that I think are important in reading the vast amount of product reviews offered by E-Commerce for the products consumers want to compare. This is because product reviews are unstructured information and it is difficult to read sentiment of reviews and assessment dimension immediately. For example, consumers who want to purchase a laptop would like to check the assessment of comparative products at each dimension, such as performance, weight, delivery, speed, and design. Therefore, in this paper, we would like to propose a method to automatically generate multi-dimensional product assessment scores in product reviews that we would like to compare. The methods presented in this study consist largely of two phases. One is the pre-preparation phase and the second is the individual product scoring phase. In the pre-preparation phase, a dimensioned classification model and a sentiment analysis model are created based on a review of the large category product group review. By combining word embedding and association analysis, the dimensioned classification model complements the limitation that word embedding methods for finding relevance between dimensions and words in existing studies see only the distance of words in sentences. Sentiment analysis models generate CNN models by organizing learning data tagged with positives and negatives on a phrase unit for accurate polarity detection. Through this, the individual product scoring phase applies the models pre-prepared for the phrase unit review. Multi-dimensional assessment scores can be obtained by aggregating them by assessment dimension according to the proportion of reviews organized like this, which are grouped among those that are judged to describe a specific dimension for each phrase. In the experiment of this paper, approximately 260,000 reviews of the large category product group are collected to form a dimensioned classification model and a sentiment analysis model. In addition, reviews of the laptops of S and L companies selling at E-Commerce are collected and used as experimental data, respectively. The dimensioned classification model classified individual product reviews broken down into phrases into six assessment dimensions and combined the existing word embedding method with an association analysis indicating frequency between words and dimensions. As a result of combining word embedding and association analysis, the accuracy of the model increased by 13.7%. The sentiment analysis models could be seen to closely analyze the assessment when they were taught in a phrase unit rather than in sentences. As a result, it was confirmed that the accuracy was 29.4% higher than the sentence-based model. Through this study, both sellers and consumers can expect efficient decision making in purchasing and product development, given that they can make multi-dimensional comparisons of products. In addition, text reviews, which are unstructured data, were transformed into objective values such as frequency and morpheme, and they were analysed together using word embedding and association analysis to improve the objectivity aspects of more precise multi-dimensional analysis and research. This will be an attractive analysis model in terms of not only enabling more effective service deployment during the evolving E-Commerce market and fierce competitio

한국농수산대학 신입생 자기소개서의 텍스트 마이닝과 연관규칙 분석 (1)

주진수,이소영,김종숙,신용광,박노복,Joo, J.S.,Lee, S.Y.,Kim, J.S.,Shin, Y.K.,Park, N.B. 국립한국농수산대학교 교육개발센터 2020 현장농업연구지 = Journal of practical agricultural resear Vol.22 No.1

본 연구는 2020년 한농대 입학생의 비정형 텍스트인 자소서에서 의미 있는 정보 혹은 규칙을 추출하기 위하여 고교 재학 중 '학업 및 학습경험'과 '교내 활동'을 기술한 두 개 문항에 대하여 텍스트 마이닝에 의한 토픽 분석과 연관성 분석을 하였다. 모집 전형을 구분하지 않은 텍스트 마이닝 분석 결과에서 '학업 및 학습 경험' 항목과 관련된 주요 키워드는 '공부', '생각', '노력', '문제', '친구' 등의 순으로 많이 나타났으며, '교내 활동' 항목과 관련된 주요 키워드는 '활동', '생각', '친구', '동아리', '학교' 등의 순으로 빈도가 높게 나타났다. 그러나 도시 인재 전형과 농수산 인재 전형 신입생들의 키워드 빈도 순위는 두 항목 모두 전형 특성에 따른 약간의 차이를 나타냈다. 빈도 분석에 결과는 빈도수 상위 50위까지의 키워드를 워드 클라우드로 시각화하여 키워드를 알기 쉽게 표현하였다. 연관 분석은 apriori() 함수를 사용하였으며 적정한 계산을 위하여 support(지지도)와 confidence(신뢰도)의 기준값을 항목별로 설정하였다. 먼저 '학업' 항목에 대한 연관 규칙은 46개를 추출하였으며, 그 가운데 {공부} => {생각}, {성적} => {공부} 및 {과목} => {공부} 등의 규칙에서 높은 연관성을 볼 수 있었다. 이 규칙을 바탕으로 매개체 역할의 키워드를 평가하는 관계 중심성 평가와 노드에 연결된 edge의 수에 따라 중요도를 파악하는 연결 중심성 평가에서는 '생각', '공부', '노력', '시간' 등의 키워드가 중심적인 역할을 하는 정보를 획득하였다. 다음으로 '교내 활동' 항목에서는 45개의 연관 규칙을 생성하여 {활동} => {생각}, {동아리} => {활동} 등의 규칙에서 높은 연관성을 볼 수 있었으며, 관계 중심성 평가와 연결 중심성 평가에서는 '생각', '활동', '학교', '시간', '친구' 등의 키워드가 중심 키워드라는 결과를 얻었다. 다음 연구에서는 자소서의 나머지 두 개의 문항 '배려·나눔·협력·갈등관리' 항목과 한농대 '지원동기와 향후 진로계획' 항목을 분석한다. 분석에는 '키워드의 빈도'에 '문서 빈도의 역수'를 곱하여 주로 다량의 문서에서 핵심어를 추출하는 TF-IDF(Term Frequency-Inverse Document Frequency) 분석을 추가한다. In this study we examined the topic analysis and correlation analysis by text mining to extract meaningful information or rules from the self introduction letter of freshman at Korea National College of Agriculture and Fisheries in 2020. The analysis items are described in items related to 'academic' and 'in-school activities' during high school. In the text mining results, the keywords of 'academic' items were 'study', 'thought', 'effort', 'problem', 'friend', and the key words of 'in-school activities' were 'activity', 'thought', 'friend', 'club', 'school' in order. As a result of the correlation analysis, the key words of 'thinking', 'studying', 'effort', and 'time' played a central role in the 'academic' item. And the key words of 'in-school activities' were 'thought', 'activity', 'school', 'time', and 'friend'. The results of frequency analysis and association analysis were visualized with word cloud and correlation graphs to make it easier to understand all the results. In the next study, TF-IDF(Term Frequency-Inverse Document Frequency) analysis using 'frequency of keywords' and 'reverse of document frequency' will be performed as a method of extracting key words from a large amount of documents.

한국농수산대학 신입생 자기소개서의 텍스트 마이닝과 연관규칙 분석 (2)

주진수,이소영,김종숙,신용광,박노복,Joo, J.S.,Lee, S.Y.,Kim, J.S.,Shin, Y.K.,Park, N.B. 국립한국농수산대학교 교육개발센터 2020 현장농업연구지 = Journal of practical agricultural resear Vol.22 No.2

본 연구는 2020년 한농대 입학생의 자소서에 서술된 학생들의 다양한 교내외 활동, 대학 지원 동기, 학업계획 및 향후 영농·영어계획 등의 텍스트 데이터를 대상으로 텍스트 마이닝에 의한 토픽 분석과 연관성 분석을 하였다. 텍스트 마이닝 결과에서 문항 3의 동아리 활동을 비롯한 다양한 활동 사례와 그 과정에서 배우고 느낀 점에 대한 키워드는 '친구' 빈도가 압도적으로 높았으며, '생각', '시간', '의견', '활동', '사람', '학교', '선생님', '학생', '동아리' 등의 키워드 순으로 많이 사용되었다. 문항 4의 대학 지원동기 및 졸업 후 진로계획에 대한 서술 데이터에는 '생각', '농업', '한농대', '농장', '지식', '공부', '사람', '관심', '전문', '아버지' 등의 키워드 빈도가 높게 나타났으며, 이 가운데 '아버지', '한농대', '전문', '농장' 등의 키워드는 다른 질문에 비하여 상위에 나타나는 특징을 보였다. 연관규칙 분석 결과에서 키워드 간 규칙의 발생 빈도이자 중요성을 나타내는 지지도는 문항 3에서 {친구} <=> {생각}, 문항 4에서 {생각} <=> {한국농수산대학} 규칙에서 가장 높게 나타났다. 두 단어 사이 연관성을 나타내는 신뢰도는 문항 3에서 {선생님} => {친구}, 문항 4에서 {농업, 한국농수산대학} => {생각}에서 높게 나타났다. 두 단어 간 밀접성을 나타내는 향상도는 문항 3에서 {친구} <=> {선생님}, 문항 4에서 {지식} <=> {전문}에서 높게 나타났다. 즉 두 단어는 우연히 함께 사용되지 않고 한 단어가 나타나면 뒤에 반드시 나머지 단어가 사용되었다는 것을 의미한다. 또한 키워드 간의 매개체 역할의 분석, 즉 키워드들 사이에 최단 경로를 파악하는 관계 중심성 분석과 연결 edge 수를 평가하는 연결 중심성 분석에서 문항 3은 '친구', '생각', '학교', '시간' 및 '사람', 문항 4는 '생각', '한국농수산대학', '지식' 및 '지원' 등의 키워드의 중심성이 매우 높은 결과를 나타냈다. In this study we examined the topic analysis and correlation analysis by text mining from the self introduction letter of freshman at Korea National College of Agriculture and Fisheries(KNCAF) in 2020. The analysis items of the 3rd question were and the 4th question were the motivation for applying to college, the academic plan and the career plan. The text mining to the 3rd question showed that the frequency of 'friends' was overwhelmingly high, followed by keywords such as 'thought', 'time', 'opinion', 'activity', and 'club'. In the 4th question, keyword frequency such as 'thought', 'agriculture', 'KNCAF', 'farm', 'father' was high. The result of association rules analysis for each question showed that the relationship with the highest support level, which means the frequency and importance of the rule, was the {friend} <=> {thought}, {thought} <=> {KNCAF}. The confidence level of a correlation between keywords was the highest in the rules of {teacher}=>{friend}, {agriculture, KNCAF}=>{thought}. Also the lift level that indicates the closeness of two words was the highest in the rules of {friend} <=> {teacher}, {knowledge} <=> {professional}. These keywords are found to play a very important roles in analyzing betweenness centrality and analyzing degree centrality between keywords. The results of frequency analysis and association analysis were visualized with word cloud and correlation graphs to make it easier to understand all the results.