• Annual Conference on Human and Language Technology
• /
• 2009.10a
• /
• pp.155-159
• /
• 2009

본 논문은 한국어 문서 감정분류를 위한 중요한 어휘 자원인 감정자질(Sentiment Feature)의 의미지향성(Semantic Orientation) 추정을 위해 일반적인 특성과 영역(Domain) 의존적인 특성을 반영하여 한국어 문서 감정분류(Sentiment Classification)의 성능 향상을 얻을 수 있는 기법을 제안한다. 감정자질의 의미지 향성은 검색 엔진을 통해 추출한 각 감정 자질의 스니핏(Snippet)과 실험 말뭉치를 이용하여 추정할 수 있다. 검색 엔진을 통해 추출된 스니핏은 감정자질의 일반적인 특성을 반영하며, 실험 말뭉치는 분류하고자 하는 영역 의존적인 특성을 반영한다. 이렇게 얻어진 감정자질의 의미지향성 수치는 각 문장의 감정강도를 추정하기 위해 이용되며, 문장의 감정 강도의 값을 TF-IDF 가중치 기법에 접목하여 감정자질의 가중치를 책정한다. 최종적으로 학습 과정에서 긍정 문서에서는 긍정 감정자질, 부정 문서에서는 부정 감정자질을 대상으로 추가 가중치를 부여하여 학습하였다. 본 논문에서는 문서 분류에 뛰어난 성능을 보여주는 지지 벡터 기계(Support Vector Machine)를 사용하여 제안한 방법의 성능을 평가한다. 평가 결과, 일반적인 정보 검색에서 사용하는 내용어(Content Word) 기반의 자질을 사용한 경우보다 3.1%의 성능향상을 보였다.

• Fashion & Textile Research Journal
• /
• v.14 no.3
• /
• pp.465-471
• /
• 2012

This thesis collected words, feelings, and psychological images expressed in female faces in their 20s and 60s. The comparative analysis of the characteristics will be based on the effective image of direction and improvement. Through the analyzed station of word of images collected, female faces in 20s of image are positive images such as pretty, cute, and elegant; however, there were also negative images such as gloomy, sharp, and stubborn. Female faces in 60s image are negative image such as scary, gloomy, sharp, and stubborn. To the analyzed station of word's tendency (usually expressed appearance), external-oriented tendency significantly developed in their 20s and 60s. It shows that the importance of appearance is emphasized in women face image in 20s and 60s.

• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.93-98
• /
• 2010

In this paper, we introduce a system that summarizes product evaluation through linguistic analysis to effectively utilize explosively increasing product reviews. Our system analyzes polarities of product reviews by product features, based on which customers evaluate each product like 'design' and 'material' for a skirt product category. The system shows to customers a graph as a review summary that represents percentages of positive and negative reviews. We build an opinion word dictionary for each product feature through context based automatic expansion with small seed words, and judge polarity of reviews by product features with the extracted dictionary. In experiment using product reviews from online shopping malls, our system shows average accuracy of 69.8% in extracting judgemental word dictionary and 81.8% in polarity resolution for each sentence.

• Journal of Korea Game Society
• /
• v.15 no.6
• /
• pp.89-96
• /
• 2015

The purpose of this paper is to analyze quantitative learning motivation on G learning. For the purpose the paper has analyzed the learning motivation factors through students' review on G learning which had been done at La Ballona Elementary School in Culver City, USA in 2010. On the basis of contents analysis method, it showed what factors of G learning influenced students and raised their academic motivation. Students used the positive, active words such as good, fun, learn, accomplish, easy, quest in terms of learning process, interest and achievement. They also showed future G learning intention describing terms such as love and miss. Team Quest has been especially developed for G learning class this time. Students had to help each other to solve the team quests which is different from traditional textbook. The system raised students' academic motivation.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.817-822
• /
• 2015

Relation extraction is an important information extraction technique that can be widely used in areas such as question-answering and knowledge population. Previous studies on relation extraction have been based on supervised machine learning models that need a large amount of training data manually annotated with relation categories. Recently, to reduce the manual annotation efforts for constructing training data, distant supervision methods have been proposed. However, these methods suffer from a drawback: it is difficult to use these methods for collecting negative training data that are necessary for resolving classification problems. To overcome this drawback, we propose a one-class classification model that can be trained without using negative data. The proposed model determines whether an input data item is included in an inner category by using a similarity measure based on lexical information and syntactic patterns in a vector space. In the experiments conducted in this study, the proposed model showed higher performance (an F1-score of 0.6509 and an accuracy of 0.6833) than a representative one-class classification model, one-class SVM(Support Vector Machine).

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.3
• /
• pp.274-279
• /
• 2015

The main goal of this research is to build a sentiment analysis system which automatically determines user opinions of the Stanford Sentiment Treebank in terms of three sentiments such as positive, negative, and neutral. Firstly, sentiment sentences are POS tagged and parsed to dependency structures. All nodes of the Treebank and their polarities are automatically extracted from the Treebank. We train two Support Vector Machines models. One is for a node level classification and the other is for a sentence level. We have tried various type of features such as word lexicons, POS tags, Sentiment lexicons, head-modifier relations, and sibling relations. Though we acquired 74.2% in accuracy on the test set for 3 class node level classification and 67.0% for 3 class sentence level classification, our experimental results for 2 class classification are comparable to those of the state of art system using the same corpus.

• Journal of Internet Computing and Services
• /
• v.14 no.4
• /
• pp.91-100
• /
• 2013

In recent years, online brand communities, whereby firms and customers interact freely, are emerging trend, because customers' opinions collected in these communities can help firms to achieve their innovation effectively. In this study, we examined whether customer opinions containing negative emotions have influence on their adoption for organizational innovation. To that end, we firstly classified negative emotions into five categories of detailed negative emotions such as Fear, Anger, Shame, Sadness, and Frustration. Then, we developed a lexicon for each category of negative emotions, using WordNet and SentiWordNet. From 81,543 customer opinions collected from MyStarbucksIdea.com which is Starbucks' brand community, we extracted terms that belong to each lexicon. We conducted an experiment to examine whether the existence, frequency and strength of terms with negative emotions in each category affect the adoption of customer opinions for organizational innovation. In the experiment, we statistically verified that there is a positive relationship between customer ideas containing negative emotions and their adoption for innovation. Especially, Frustration and Sadness out of the five emotions are significantly influential to organizational innovation.

• Journal of Korea Game Society
• /
• v.18 no.5
• /
• pp.113-122
• /
• 2018

This paper describes an approach to building and evaluating a sentiment dictionary using a Web corpus in the game domain. To build a sentiment dictionary, we collected vocabulary based on game-related web documents from a domestic portal site, using the Twitter Korean Processor. From the collected vocabulary, we selected the words whose POS are tagged as either verbs or adjectives, and assigned sentiment score for each selected word. To evaluate the constructed sentiment dictionary, we calculated F1 score with precision and recall, using Korean-SWN that is based on English Senti-word Net(SWN). The evaluation results show that average F1 scores are 0.85 for adjectives and 0.77 for verbs, respectively.

• Cross-Cultural Studies
• /
• v.48
• /
• pp.135-191
• /
• 2017

The purpose of this study was to select words with "shared cultural charge" that are unique in French culture and to study cultural content hidden in these words. It also explores the cultural phenomenon of same French borrowed words used in the Korean language. The study was conducted from two perspectives: perspective of internal French culture defined by Galisson and inter-cultural perspective. The first section of this study introduces the theory "lexiculture" and definition of the words "shared cultural charge." In the following section, among main items of 795 borrowed words in the Korean language, we examined seven words in areas such as clothing, food, and housing. We studied content of the French culture according to the following three categories: (1) dictionary definition, (2) cultural phenomena, (3) special phenomenon in idiomatic expression. Our study illustrated a special connotation beyond the dictionary definition of words. In the next section, we examined the birth of a new cultural phenomenon and process of acquiring a new meaning in the Korean language. Finally, we analyzed differences and similarities between linguistic and cultural elements in both cultures. In this study, we provide basic data for inter-cultural education between France and Korea.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.195-200
• /
• 2016

본 연구는 MUSE 감성 코퍼스를 활용하여 문장의 극성과 키워드의 극성이 얼마만큼 일치하고 일치하지 않은지를 분석함으로써 특히 문장의 극성과 키워드의 극성이 불일치하는 유형에 대한 연구의 필요성을 역설하고자 한다. 본 연구를 위하여 DICORA에서 구축한 MUSE 감성주석코퍼스 가운데 IT 리뷰글 도메인으로부터 긍정 1,257문장, 부정 1,935문장을, 맛집 리뷰글 도메인으로부터는 긍정 2,418문장, 부정 432문장을 추출하였다. UNITEX를 이용하여 LGG를 구축한 후 이를 위의 코퍼스에 적용하여 나타난 양상을 살펴본 결과, 긍 부정 문장에서 반대 극성의 키워드가 실현된 경우는 두 도메인에서 약 4~16%의 비율로 나타났으며, 단일 키워드가 아닌 구나 문장 차원으로 극성이 표현된 경우는 두 도메인에서 약 25~40%의 비교적 높은 비율로 나타났음을 확인하였다. 이를 통해 키워드의 극성에 의존하기 보다는 문장과 키워드의 극성이 일치하지 않는 경우들, 가령 문장 전체의 극성을 전환시키는 극성전환장치(PSD)가 실현된 유형이나 문장 내 극성 어휘가 존재하지 않지만 구 또는 문장 차원의 극성이 표현되는 유형들에 대한 유의미한 연구가 수행되어야 비로소 신뢰할만한 오피니언 자동 분류 시스템의 구현이 가능하다는 것을 알 수 있다.