• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.248-251
• /
• 2011

본 연구에서는, 웹 문서로부터 특정 상품에 대한 의견 문장을 분석하는 오피니언 마이닝(Opinion Mining) 연구의 일환으로, 특히 함께 공기하는 자질 명사에 따라 그 극성 값이 달라지는 '비결정 오피니언어휘'의 처리를 위해서 도메인을 '맛집'으로 한정하여 공기하는 도메인 키워드의 목록을 결정하고, 이를 부분문법그래프(Local Grammar Graphs) 방법론을 통해서 이들 간의 어휘 통사적 관계를 결정해 주었다.

• Proceedings of the Korea Contents Association Conference
• /
• 2018.05a
• /
• pp.7-8
• /
• 2018

This study proposes an analysis of the Word2vec-based machine learning classifiers for the sake of opinion mining tasks. As a bench-marking method, BOW (Bag-of-Words) was adopted. On the basis of utilizing the Word2vec and BOW as feature extraction methods, we applied Laptop and Restaurant dataset to LR, DT, SVM, RF classifiers. The results showed that the Word2vec feature extraction yields more improved performance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.747-748
• /
• 2009

사용자가 웹 상에 작성한 상품평은 다양한 정보를 포함하고 있는 데이터이다. 대부분의 사람들이 상품을 구입하기 전에 상품평을 통해서 상품에 대한 많은 정보를 얻는다. 이에 따라 대량의 상품평 데이터로부터 유용한 정보를 추출하여 요약하는 오피니언 마이닝에 대한 연구가 활발히 진행되고 있다. 본 논문에서는 사용자가 많은 상품평들을 모두 읽어보지 않고 상품에 대한 오피니언과 장점과 단점을 쉽게 알 수 있도록 연관 규칙 마이닝을 적용하는 오피니언 마이닝 방법을 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.1188-1190
• /
• 2011

오피니언 마이닝은 웹에 있는 문서를 분석하여 작성자의 의견을 요약된 형태로 보여주는 기술이다. 오피니언 마이닝을 이용해 문서 작성자의 주관적 의견을 알 수 있고 이를 통해 작성자의 성향이나 관심사와 같은 정보를 얻을 수 있다. 많은 네티즌들은 소셜 네트워크 서비스를 통해 자신의 의견이 담긴 글을 타인과 공유 하며 네트워크상의 인맥을 넓혀 나간다. 오피니언 마이닝을 통해 개인이 작성한 글들을 분석하여 관심사를 파악하고 비슷한 관심사를 가진 친구를 추천하는 친구 추천 시스템을 제안한다.

• The KIPS Transactions:PartD
• /
• v.18D no.4
• /
• pp.237-244
• /
• 2011

Opinion Mining summarizes with classifying sensitive opinions of customers in huge online customer reviews for the attributes of products or services by positive and negative opinions. Because the customers represent their interests through subjective opinions as well as objective facts, the existing opinion mining techniques, which can analyze just the sensitive opinions, need to be expanded.. In this paper, We propose the novel entity association network model which expands the existing opinion mining techniques. The entity association model can not only represent positive and negative degree of the sensitive opinions, but also can represent the degree of the associations and relative importances between entities. We designed and implemented the customer reviews analysis system based on the entity association network model. We recognized that the system can represent more abundant information than the existing opinion mining techniques.

• The Journal of Society for e-Business Studies
• /
• v.19 no.2
• /
• pp.95-108
• /
• 2014

Opinion Mining is one of the application domains of text mining which extracting opinions from documents, and much researches are currently underway. Most of related researches focused on the sentiment classification which classifies the documents into positive/negative opinions. However, there is a little interest in extracting the features characterizing the individual product. In this paper, we propose the technique classifying the opinion documents according to the product features, and selecting the those features characterizing each product. In the proposed method, we utilize the document clustering technique and develope a new algorithm for evaluating the similarity between documents. In addition, through experiments, we prove the usefulness of proposed method.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.9 s.180
• /
• pp.2387-2396
• /
• 2000

Wear and operation characteristics of Nylon and Acetal pinion against steel gear were studied to gain a better understanding of their tribological and mechanical behavior. Tests were conducted with power circulating gear test rig under unlubricated conditions. Specific wear rates were measured as a function of applied load and total revolution. The worn tooth surfaces were examined with a profile projector and camera. Nylon pinion showed lower specific wear rates than Acetal pinion, but it revealed breakage at high load. Principal wear depths were developed at tooth tip and below the pitch line of pinion. Life estimation for the Nylon pinion was made by taking into account steel gear equivalent Hertz stress and average sliding velocity. The dominant wear mechanisms were adhesion and abrasion.

• Journal of Advanced Marine Engineering and Technology
• /
• v.36 no.5
• /
• pp.700-706
• /
• 2012

The core technology of a starting device in the packaged power system is the pinion gear shifting device and to limit the initial starting voltage. Although the conventional products have been used the starting controller using mechanical contactor, these have a big problem such as the uncertainty for the start of starting motor after a pinion gear is completely shifted or the arc demage due to high current. In this study, in order to solve these problems, we designed and fabricated a new product to achieve the safety and reliability as follows: the pinion gear-shifting control circuits to eliminate the uncertainty of the start, the starting control system using semiconductor device to prevent the arc demage of contactor caused by high current, a start safety devices for soft starting of series motor. In addition, we obtained the electrical safety by separating the pinion gear control circuit and the source circuit of motor.

• Journal of the Korean Society for Library and Information Science
• /
• v.47 no.4
• /
• pp.315-334
• /
• 2013

This study performs opinion mining of newspaper articles, based on topics extracted by topic modeling. We analyze the attitudes of the news media towards a major issue of 'presidential election', assuming that newspaper partisanship is a kind of opinion. We first extract topics from a large collection of newspaper texts, and examine how the topics are distributed over the entire dataset. The structure and content of each topic are then investigated by means of network analysis. Finally we track down the chronological distribution of the topics in each of the newspapers through time serial analysis. The result reveals that both the liberal newspapers and the conservative newspapers exhibit their own tendency to report in line with their adopted ideology. This confirms that we can count on opinion mining technique based on topics in order to analyze opinion in a reliable fashion.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.8 no.6
• /
• pp.544-550
• /
• 2015

The opinion mining technique which analogize significant information from SNS message is increasingly important because opinions communicated through SNS are increasing. This paper propose SEIAS(SNS Emotional Information Analysis Strategy) based on opinion mining that analogize emotional information from SNS setting a different weight according to position of antonym and adverb. Firstly, the proposed SEIAS constructs a emotion dictionary for opinion mining analysis, Secondly, it collects SNS data on real time, compare it with emotion dictionary and calculates opinion value of SNS data. Specially, it increases the precision of opinion analysis result compared to the existing SO-PMI because it sets up the different value according to the position of antonym and adverb when it calculates the opinion value of data.