• 한국컴퓨터정보학회논문지
• /
• 제17권9호
• /
• pp.39-47
• /
• 2012

일반적으로 사람들은 특정 상품에 관한 의견을 표현할 때 그 상품이 갖는 개별속성에 대해 긍부정 성향을 표시한다. 어떤 경우에는 상품이 갖는 동질의 개별 속성에 대해 포괄적으로 긍부정 성향을 표현하거나 상품 자체에 대해 표현하기도 한다. 따라서 의견검색 분야에서 추출 대상이 되는 의견 속성명에는 상품의 개별 속성명, 이 개별 속성들을 포함하는 전체어, 그리고 상품명이 존재한다. 그러나 의견 대상을 상품명이나 전체어로 표현할 때, 경우에 따라 의견문장 표면에 나타나는 속성명과 의견 작성자가 의도한 실제 대상이 일치하지 않을 수도 있다. 본 논문에서는 의견문장으로부터 의견 대상을 추출하는 방법을 제시한다. 무엇보다 우리는 의도한 대상과 일치하지 않는 속성명으로부터 의도한 대상을 추출하기 위한 새로운 방법을 제안한다. 제시하는 방법에서는 단어간 의존관계를 이용하여 의견속성 후보쌍을 추출하고, 추출된 후보쌍들 중 의견 대상과 일반적으로 빈번히 불일치하는 속성명을 선택한다. 선택된 속성명을 작성자가 의도한 개별속성으로 변경한 뒤, 이를 포함한 전체 의견속성 후보쌍들로부터 적합한 의견속성을 추출하기 위해 사람들이 관심 있어할만한 순으로 재배열하게 된다.

• Asian Journal for Public Opinion Research
• /
• 제5권4호
• /
• pp.266-284
• /
• 2018

This paper adopts the big data research method, and draws 491 data from the Tianya Forum about the Simultaneous Renting and Purchasing policy of Guangzhou. The qualitative analysis software Nvivo11 is used to cluster the main questions about the Simultaneous Renting and Purchasing policy in the forum. The 36 high-frequency word frequencies are obtained through text clustering. Through rooted theory analysis, the main driving factors for summarizing people's doubts are 9 main categories, 3 core categories, and the model of driving factors for online forums is established. The study finds that resource factors are the most key factor, economic factors are the important drivers, and policy guiding factors are sub-important drivers.

• 복식문화연구
• /
• 제9권3호
• /
• pp.343-356
• /
• 2001

The purpose of this was to classify consumer groups according to the life styles and analyze buying intention and evaluation criteria of apparel product, opinion to 4p\`s aspect among consumer groups. And it was to clarify relationships between the experience of CATV home shopping and buying intention and evaluation criteria of apparel product, opinion to 4p\`s aspect. The subjects of this study were 270 women living in Chonbuk and Chonnam regardless their experience in CATV home shopping. For data analysis, frequency, percentage, mean, t-test, factor analysis were conducted. The results were as follows; First, the type of life style were classified into the following subdivisions: products confirmed type, price-quality regarded type, time regarded type, new product regarded type. Second, the significant differences among the classified life style groups were found in buying intention, evaluation criteria of apparel product, and opinion to 4p\`s aspect. Third, there were significant differences in buying intention, evaluation criteria of apparel product, and opinion to 4p\`s aspect according to TV home shopping experience.

• 한국의류산업학회지
• /
• 제3권4호
• /
• pp.323-329
• /
• 2001

The purpose of this study was to identify the relationship between clothing involvement and fashion leadership of fashion models and college women. For this study, 113 fashion models and 265 female college students were analyzed. Factor analysis, Correlation, t-test and Regression analysis were used in data analyses. Clothing involvement was factor analyzed resulting five factors such as interest, pleasure, fashionability, risk perception and symbolism. Three clothing involvement factors had highly positive relations with total clothing involvement. Interest, pleasure and fashionability factors were related with each other: Fashionability and interest factors had an effect on fashion opinion-leadership and fashion innovation. Significant differences were found between fashion models and female college students in regard to clothing involvement and fashion leadership. Fashion models and female college students differed significantly in clothing interest and fashionability. Fashion models and female college students differed significantly in fashion opinion-leadership and fashion innovation. Fashion models were more fashion opinion leaders and fashion innovators than female college students.

• 한국컴퓨터정보학회논문지
• /
• 제24권2호
• /
• pp.171-177
• /
• 2019

This paper aims to find the most effective feature selection method for the sake of opinion mining tasks. Basically, opinion mining tasks belong to sentiment analysis, which is to categorize opinions of the online texts into positive and negative from a text mining point of view. By using the five product groups dataset such as apparel, books, DVDs, electronics, and kitchen, TF-IDF and Bag-of-Words(BOW) fare calculated to form the product review feature sets. Next, we applied the feature selection methods to see which method reveals most robust results. The results show that the stacking classifier based on those features out of applying Information Gain feature selection method yields best result.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2017년도 제56차 하계학술대회논문집 25권2호
• /
• pp.344-345
• /
• 2017

Opinion mining and sentiment analysis(OMSA) as a research discipline has emerged during last 15 years and provides a methodology to computationally process the unstructured data mainly to extract opinions and identify their sentiments. The relatively new but fast growing research discipline has changed a lot during these years. This paper presents a scientometric analysis of research work done on OMSA during 2007-2016. For the literature analysis, research publications indexed in Web of Science (WoS) database are used as input data. The publication data is analyzed computationally to identify year-wise publication pattern, rate of growth of publications, research areas.

• 디지털융복합연구
• /
• 제18권9호
• /
• pp.93-101
• /
• 2020

외부감사시장에서 감사의견구매에 대한 우려가 지속적으로 제기되었으나, 감사의견구매의 존재에 대한 실증적 증거에 대한 연구는 거의 이루어지지 않았다. 이러한 이유로 본 연구는 감사의견구매가 존재하는지를 실증적으로 검증하였다. 연구방법은 먼저 순위형 회귀분석을 사용하여 감사인 교체기업과 미교체기업의 감사의견 표명기준점을 각각 측정하였다. 이후, 차이분석을 수행하여 측정된 감사의견 표명기준점이 감사인 교체기업과 미교체기업 간에 유의한 차이가 존재하는지를 검증하였다. 연구 결과, 감사인 교체기업과 미교체기업 간의 계속기업불확실성 표명의 기준점이 유의한 차이가 존재하지 않는 것으로 나타났으며, 이러한 결과에 따라 외부감사시장에서 감사의견구매가 일반적으로 이루어지는 현상은 아닌 것으로 해석할 수 있다. 본 연구의 공헌점은 외부감사시장에서 감사의견구매가 일반적으로 존재하지 않는다는 것을 실증적으로 검증한 것이다.

• 한국문헌정보학회지
• /
• 제47권4호
• /
• pp.315-334
• /
• 2013

이 연구에서는 토픽 모델링 기법을 이용하여 신문 기사를 대상으로 주제 기반의 오피니언 마이닝을 수행하였다. 언론 매체가 가지는 정파성을 일종의 오피니언으로 간주하여 대선이라는 거대 이슈에 대한 각 매체들의 입장을 분석하였다. 먼저 대량의 신문 기사에서 주제를 추출한 후 매체별 주제 구성의 차이를 살펴보았다. 그리고 주제별 네트워크 분석을 통해 주제의 구조와 내용을 분석하였다. 마지막으로 시계열 분석을 통해서 시기별 주제 분포의 차이를 매체별로 살펴보았다. 그 결과 모든 분석에서 진보매체와 보수매체 모두 자신들의 이데올로기를 따라 기사를 보도하는 경향성이 확인되었다. 이를 통해 주제 기반 오피니언 마이닝이 타당성 있는 의견 분석의 기능을 수행할 수 있음을 확인할 수 있었다.

• 한국의류학회지
• /
• 제24권4호
• /
• pp.549-559
• /
• 2000

In a few studies about product involvement there was confusion in the construct of involvement especially in association with importance. Due to the confusion of the construct unanticipated and inconsistent results were reported in some cases. So this study was mainly to identify the relationship between clothing importance and clothing involvement and also investigated the casual relationships among consumers n, value, clothing importance, clothing involvement fashion opinion leadership, and shopping behavior. The data were collected from 429 female adults using questionnaire, and were analysed with actor and path analysis. Results can be summarized as follows. First, clothing importance was the separate concept from clothing involvement, though they were closely related. Second. it was revealed that the main casual path was valuerlongrightarrowclothing importancelongrightarrowclothing involvementlongrightarrowfashion opinion leadership, shopping preference, shopping frequency, and shopping time. On the whole, the affective dimension of clothing involvement mainly affected them, and consumer's age negatively affected fashion opinion leadership and shopping behavior.

• 영어어문교육
• /
• 제15권2호
• /
• pp.121-150
• /
• 2009

This paper deals with contrastive analysis and interlanguage with respect to adjective ordering. It aimed to investigate how similar and different the orders of descriptive adjectives are in English and Korean, and how Korean EFL learners perceive the sequences of English descriptive adjectives. Data were collected from native English speakers and native Korean speakers and Korean EFL learners. The contrastive analysis showed that the order of English adjectives was size, opinion, condition, age, color, shape, material, and origin, whereas the Korean order was condition, age, opinion, color, size, shape, material, and origin. The relative order of the interlanguage was shown to be age, size, opinion, shape, condition, color, origin, and material, with the exceptions of the order of condition preceding age and that of size being the same position as condition. The interlanguage data manifested different aspects of ordering when compared with English and Korean: Some adjective combinations were similar to both English and Korean; Some were different from English or Korean; Some were different from both English and Korean. These ordering patterns are discussed in terms of such principles as the nouniness principle, the subjectivity/objectivity principle, the iconic principle, etc. On the basis of these results, some helpful suggestions are made.