• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2018년도 춘계 종합학술대회 논문집
• /
• pp.7-8
• /
• 2018

본 연구에서는 Word2vec을 머신러닝 분류기를 이용해 효율적인 오피니언 마이닝 방법을 제안한다. 본 연구의 목적을 위해 BOW(Bag-of-Words) 방법과 Word2vec방법을 이용해 속성 셋을 구성했다. 구성된 속성 셋은 Decision tree, Logistic regression, Support vector machine, Random forest를 이용해 오피니언 마이닝을 수행했다. 연구 결과, Word2vec 방법과 RF분류기가 가장 높은 정확도를 나타냈다. 그리고 Word2vec 방법이 BOW방법 보다 각 분류기에서 높은 성능을 나타냈다.

• 영어어문교육
• /
• 제10권2호
• /
• pp.67-87
• /
• 2004

The purpose of this paper is to show how the coda of a syllable and word-final clusters are represented in the English syllable structure. Previous theories on the syllable assume that there is only one segment in the coda position. And, as we know, the theories that license only one segment in the coda make it difficult to syllabicate the word-final cluster appropriately when more than two segments in the word-final cluster are encountered. I considered three approaches: the previous syllable structure (Selkirk, 1982; Borowsky 1989), sonority sequencing (Giegerich, 1992; Roca, 1999) and feature analysis (Goldsmith, 1990), But, all the considered methods don't give us a satisfactory explanation regarding word-final clusters. Finally, I will suggest a modified syllable representation as an alternative by placing two different appendixes under the Phonological Word which forms a constituent above the syllable node. From this it is possible to explain the former problematic word-final clusters including morphological information asan inflectional suffix in the structure.

• Asian Journal of Business Environment
• /
• 제6권3호
• /
• pp.21-31
• /
• 2016

Purpose - The purpose of this research is to determine the impact of word of mouth on customer perceived value for restaurants in Malaysia. The objectives of this research include determining how word of mouth (WoM) factors - frequency of word of mouth messages, reputation of word of mouth messenger, richness of word of mouth message, dispersion of word of mouth conversations and manner of word of mouth delivery impact customer perceived value in Malaysian restaurant industry. Research Design, Data, and Methodology - The research follows causal / explanatory research method based on quantitative data. A sample of 150 restaurant customers in Kuala Lumpur, Malaysia was selected using convenience sampling technique. Likert scale questionnaire is used to collect data and data is analysed using regression analysis through SPSS 22. Results - The statistical analysis revealed that independent variable 'manner of delivery' significantly and positively impacts customer perceived value for restaurants in Malaysia. Conclusions - To build strong positive customer perception, Malaysian restaurants can enhance word of mouth campaigns' 'manner of delivery' by making them passionate, exciting and with high emotional appeal.

• 한국콘텐츠학회논문지
• /
• 제20권10호
• /
• pp.679-687
• /
• 2020

본 연구의 목적은 BNC 어휘목록과 2015 교육부 기본 어휘를 중심으로 EBS 연계교재와 대학 수능시험의 어휘를 분석하고자 한다. 어휘점유율과 빈도를 분석하기 위해서 AntWordProfiler 어휘 분석프로그램이 사용되었다. 결과를 보면, 2020 EBS 수능 영어 듣기와 읽기 연계 교재는 각각 BNC 3,000 단어와 4,000 단어를 가지고 약 95%를 이해할 수 있다는 것을 보여준다. 그러나 EBS 듣기와 읽기 교재의 98%의 단어를 이해하기 위해서는 각각 4,000과 8,000 단어가 필요하다는 것을 알 수 있다. 다른 한편으로 2020 수능영어시험 듣기와 읽기의 95%를 이해하기위해서는 각각 2,000과 4,000 단어가 요구되며, 98%의 경우에는 추가적으로 4,000과 7,000의 단어가 필요하다. 결과적으로 EBS 연계교재가 대입수능영어시험보다 더 많은 어휘의 양을 요구한다는 것을 알 수 있다.

• 영어어문교육
• /
• 제10권3호
• /
• pp.159-175
• /
• 2004

This paper investigated the types of errors on English pronunciation and intelligibility of Korean EFL students, and the relationship between the pronunciation accuracy and intelligibility. Thirty one students were evaluated by six English native speakers in terms of overall intelligibility and accuracy In five areas such as nuclear stress, word stress, syllable structure, consonants and vowels. According to the findings of the study, pronunciation errors were made by the subjects more frequently In word stress than any other area of pronunciation accuracy. The Pearson correlation analysis showed that intelligibility was related with word stress, syllable structure, consonants and vowels, and the stepwise multiple regression analysis indicated that, among the above five areas of pronunciation accuracy, word stress best accounted for the intelligibility of a given sentence. In the conclusion, the importance of teaching pronunciation of in those five areas with a special focus on word stress was emphasized m terms of intelligibility.

• 컴퓨터교육학회논문지
• /
• 제17권6호
• /
• pp.115-122
• /
• 2014

현 청소년들의 학교내 생활환경에서 문제점으로 대두되는 폭력 및 자살사고 발생률 증가에 대한 예방차원의 빅 데이터 처리 분석 시스템을 목표로 연구하였고 설계의 경제성과 용이성, 적용의 신속성 등을 고려해서 많은 이용률을 가지고 있는 오픈 소스인, 하둡 시스템(Hadoop system)의 맵리듀스(MapReduce) 알고리즘과 분산 병렬 환경을 위한 HDFS(Hadoop Distibuted File System) 구성을 사용하여 실험하였다. 연구에서 사용된 분석기법은 기존의 통계적인 분석기법들이 가지는 난이도를 피하기 위해 상업적인 사회 망의 비정형 대화 자료를 이용해서 폭력성 어휘에 대한 단어 수(word count) 분석을 적용하여 폭행, 자살사고를 사전에 감지하여 예방하는 감성분석(sentiment analysis) 시스템을 텍스트 마이닝 관점에서 제안하여 실험하였다.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.321-329
• /
• 2007

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.

• Journal of Contemporary Eastern Asia
• /
• 제16권2호
• /
• pp.110-144
• /
• 2017

Unlike most languages, written Chinese has no spaces between words. Word segmentation must be performed before semantic network analysis can be conducted. This paper describes how to perform Chinese word segmentation using the Stanford Natural Language Processing group's Stanford Word Segmenter v. 3.8.0, released in June 2017.

• Journal of Sport and Applied Science
• /
• 제7권2호
• /
• pp.13-19
• /
• 2023

Purpose: The purpose of this study is to provide directions and implications related to eco-friendly marketing and products of outdoor brand companies by empirically analyzing the influence of outdoor brand's eco-friendly activities on brand image and word of mouth. Research design, data, and methodology: In this study, a survey was conducted on those who have purchased outdoor brand products through the convenience sampling method, and a total of 470 effective samples were collected. Frequency analysis, reliability analysis, confirmatory factor analysis, and structural equation model analysis were conducted based on the collected data. Results: As a result of the analysis, first, it was found that eco-friendly marketing among the eco-friendly activities of outdoor brands did not have a positive effect on the brand image. Second, among the eco-friendly activities of outdoor brands, eco-friendly products were found to have a positive effect on the brand image. Third, it was found that the brand image had an effect on word of mouth intention. Conclusions: Academic and practical implications were discussed based on the research results that eco-friendly marketing of outdoor brands does not have a positive effect on brand image, eco-friendly products have a positive effect on brand image, and brand image affects word of mouth.

• 한국콘텐츠학회논문지
• /
• 제19권10호
• /
• pp.620-629
• /
• 2019

의사 결정을 위한 토론이나 토의의 내용을 객관적 요약하고 분류하는 자동화된 회의록 요약 시스템이 요구되고 있다. 본 논문은 기존에 사용되었던 회의록 요약 시스템을 보완할 수 있도록 word2vec 모델을 이용한 회의록 요약 시스템을 설계하고 구현한다. 제안 시스템은 형태소 분석 과정에서 불용어를 제거하고 문서에서 공통적인 의견을 가진 대표 문장을 추출하기 위해 추가로 word2vec 모델로 학습을 수행한다. 제안 시스템은 회의 과정에서 수집되는 문서를 분석하여 자동으로 분류하고 다양한 의견들 중 안건을 대표하는 대표 문장을 추출한다. 회의 진행자는 제안 시스템을 통해 회의에서 다뤄지는 모든 안건을 보다 빠르게 확인하고 관리할 수 있다. 제안 시스템은 대규모 토론이나 토의의 여러 가지 안건을 분석하여 대표 의견이 될 수 있는 문장을 요약하여 빠른 정확한 의사 결정을 지원한다.