• 동력기계공학회지
• /
• 제18권6호
• /
• pp.180-185
• /
• 2014

Due to the larger and high-speed vessels recently constructed, output and speed of the engines for propulsion or power generation is increasing. These high-power and high-speed engine of the ship is becoming as a major contributor causing excessive noise and vibration. Other fittings as well as equipment installed on board, it makes equipment failure or other defect by resonance. This causes a lot of M/H(Man Hour) for repairs and the reliability of the company is invading even be negative because the clients give much comment. Thus, it's being studied for any fittings installed on board to maintain the safe operation and to prevent any problem during the performance in any operating conditions. In this study, it was investigated to solve these problems for the supports of the various fittings for easy installation-related support that each type of intensity and shape and manufacturing method using structural analysis program(DNV Nauticus Hull 3D Beam). Namely, it would be applied to the very large crude carriers in consideration of mechanics of materials of the support equipment by providing the fact that dynamics analysis of the structural characteristics of the equipment and the support of the production installation is easy and productivity can be high standards for geometry and thereby to simplify the analysis task to design changes at the same time and to minimize the reinforcement for the supports.

• Human Ecology Research
• /
• 제59권1호
• /
• pp.23-43
• /
• 2021

This study looked through the text mining analysis to check the status of the virtual assistant service, and explore the needs of consumers, and present consumer-oriented directions. Trendup 4.0 was used to analyze the keywords of AI services in Online News and social media from 2016 to 2020. The R program was used to collect consumer comment data and implement Topic Modeling analysis. According to the analysis, the number of mentions of AI services in mass media and social media has steadily increased. The Sentimental Analysis showed consumers were feeling positive about AI services in terms of useful and convenient functional and emotional aspects such as pleasure and interest. However, consumers were also experiencing complexity and difficulty with AI services and had concerns and fears about the use of AI services in the early stages of their introduction. The results of the consumer review analysis showed that there were topics(Technical Requirements) related to technology and the access process for the AI services to be provided, and topics (Consumer Request) expressed negative feelings about AI services, and topics(Consumer Life Support Area) about specific functions in the use of AI services. Text mining analysis enable this study to confirm consumer expectations or concerns about AI service, and to examine areas of service support that consumers experienced. The review data on each platform also revealed that the potential needs of consumers could be met by expanding the scope of support services and applying platform-specific strengths to provide differentiated services.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.263-283
• /
• 2024

Users' comments after online shopping are critical to product reputation and business improvement. These comments, sometimes known as e-commerce reviews, influence other customers' purchasing decisions. To confront large amounts of e-commerce reviews, automatic analysis based on machine learning and deep learning draws more and more attention. A core task therein is sentiment analysis. However, the e-commerce reviews exhibit the following characteristics: (1) inconsistency between comment content and the star rating; (2) a large number of unlabeled data, i.e., comments without a star rating, and (3) the data imbalance caused by the sparse negative comments. This paper employs Bidirectional Encoder Representation from Transformers (BERT), one of the best natural language processing models, as the base model. According to the above data characteristics, we propose the F_MixBERT framework, to more effectively use inconsistently low-quality and unlabeled data and resolve the problem of data imbalance. In the framework, the proposed MixBERT incorporates the MixMatch approach into BERT's high-dimensional vectors to train the unlabeled and low-quality data with generated pseudo labels. Meanwhile, data imbalance is resolved by Focal loss, which penalizes the contribution of large-scale data and easily-identifiable data to total loss. Comparative experiments demonstrate that the proposed framework outperforms BERT and MixBERT for sentiment analysis of e-commerce comments.

• Asia pacific journal of information systems
• /
• 제23권3호
• /
• pp.131-154
• /
• 2013

New internet technologies have created a revolutionary new platform which allows consumers to make decision about product price and quality quickly and provides information about themselves through the transcript of online reviews. By expressing their feelings toward products or services on virtual opinion platforms, users extend their influence into cyberspace as electronic word-of-mouth (e-WOM). Existing research indicates that an impact of eWOM on the consumer decision process is influential. For both academic researchers and practitioners, investigating this phenomenon of information sharing in online website is essential given the increasing number of consumers using them as sources of purchase decisions. It is worthwhile to examine the extent to which opinion seekers are willing to accept and adopt online reviews and which factors encourage adoption. Discerning the most motivating aspects of information adoption in particular, could help electronic marketers better promote their brand and presence on the internet. The objectives of this study are to investigate how online WOM influences a persons' purchase decision by discovering which factors encourage information adoption. Especially focused on the self-efficacy, this research investigates how self-efficacy affects on information usefulness and adoption of online information. Although people are exposed to same review or comment about product or service, some accept the reviews while others do not. We notice that accepting online reviews mainly depends on the person's preference or personal characteristics. This study empirically examines this issue by using cognitive dissonance theory. Specifically, in the movie industry, we address few questions-is always positive WOM generating positive effect? What if the movie isn't the person's favorite genre? What if the person who is very self-assertive so doesn't take other's opinion easily? In these cases of cognitive dissonance, is always WOM generating same result? While many studies have focused on one direct of WOM which indicates positive (or negative) informative reviews or comments generate positive (or negative) results and more (or less) profits, this study investigates not only directional properties of WOM but also how people change their opinion towards product or service positive to negative, negative to positive through the online WOM. An experiment was conducted quantitatively by using a sample of 168 users who have experience within the online movie review site, 'Naver Movie'. Users were required to complete a survey regarding reviews and comments taken from the real movie page. The data reflected user's perceptions of online WOM information that determined users' adoption level. Analysis results provide empirical support for the proposed theoretical perspective. When user can't agree with the opinion of online WOM information, in other words, when cognitive dissonance between online WOM information and users' preference occurs, perceived self-efficacy significantly decreases customers' perception of usefulness. And this perception of usefulness plays an important role in determining users' intention to adopt online WOM information. Most of researches have been concentrated on characteristics of online WOM itself such as quality or vividness of information, credibility of source and direction of online WOM, etc. for describing effect of online WOM, but our results suggest that users' personal character (e.g., self-efficacy) plays decisive role for acceptance of online WOM information. Higher self-efficacy means lower possibility to accept the information that represents counter opinion because of cognitive dissonance, whereas the people that have lower self-efficacy are willing to accept the online WOM information as true and refer to purchase decision. This study suggests a model for understanding role of direction of online WOM information. Also, our result implicates the importance of online review supervision and personalized information service by confirming switching opinion negative to positive is more difficult than positive to negative through the online WOM information. This implication would help marketers to manage online reviews of their products or services.

• 보건교육건강증진학회지
• /
• 제19권2호
• /
• pp.23-43
• /
• 2002

Purpose: The purpose of this study is to examine and analyse factors related to the actual status and practice of breast-feeding during an infant period to grasp elements detrimental to breast-feeding and, therefore, provide basic information useful for its effective practice and encouragement. Method: From April 1 to June 30, 2001, this study was carried out with the mothers of 337 who were 6 months old, as of the surveyed date, of infants born in 2002 and registered in Seongju-gun Public Health Center, Gyeongsangbug-do Province. The method for its survey included both of the visiting and telephone interviews, and questions were mainly about the mothers' general characteristics(3 questions), infants' general characteristics(3 questions), environmental characteristics of infant delivery( 4 questions), support to breast-feeding(4 questions), understanding of breast-feeding(5 questions), and feeding type during the 1 to 6-month period after birth. Result: 1. The feeding type during the I-month period after birth showed that the breast-feeding accounted for 42.4%, which was higher than dry milk-feeding(30%) or mixed milk-feeding(26.8%). However, it began to be lower than the dry milk-feeding from the 2-month period after birth. During the 6-month period, the breast-feeding accounted for 28.6% which was lower than 56.5% of the dry milk-feeding. 2. The mothers who were encouraged by their delivery clinic to and were educated to breast-feed infants accounted for 55.4% and 41.4%, respectively, which were relatively low. The understanding of breast-feeding indicated that the responses were positive from the view point of mother ＆ infant health, but negative from mother's physical form. 3. It was shown that the lower the educational background of mother(p〈0.05) and the higher the unemployment of mother(p〈0.001), the higher the positive understanding of breast-feeding, and that the higher the entire support to breast-feeding, the more positive their understanding. 4. It was also shown that the lower the educational background of mother(p〈0.05), the higher the unemployment of mother(p〈0.001), the more the experience in breast-feeding at a delivery clinic(p〈0.01) and the faster the initial feeding(p〈0.001), the higher the rate of breast-feeding. 5. The factor having an effect on breast-feeding included a delivery clinic's encouragement to breast-feed(p〈0.001), understanding of breast-feeding(p〈0.01), father's comment on feeding method(p〈0.05) and mother's employment(p〈0.05). Discussion: In order to encourage the breast-feeding, as shown above, it is required, fist of all, to offer pregnant women an education about importance and excellence of breast-feeding and its appropriate method before delivery in advance to result in a positive comprehension of the breast-feeding. To do that, both the publicity activities and program development designed to encourage the breast-feeding must be performed in advance at the government level. In addition to that, the mother-infant space as ‘rooming-in’ available for breast-feeding immediately after delivery must be prepared on the basis of legal and administrative support. Finally, female employees' leave after childbirth must be performed for the purpose of productive welfare and circumstances also be prepared for breast-feeding, such as a children's home at work.

• 비교문화연구
• /
• 제29권
• /
• pp.341-366
• /
• 2012

'Headline Database of Newspaper Articles' is a database which contains about 141,500 newspaper articles from 1949 to March, 2009. They are collected from two perspectives; 'language' and 'language life' by KOKKEN. There were 3312 newspaper articles (about 2.34%) which included the word ONNA at 'Headline Database of Newspaper Articles'. The number of newspaper articles related to ONNA started to increase in 1975 but they decreased afterwards. They increased rapidly in 1980 and maintained the condition. However, they started to decrease rapidly in 1990 and maintained the decreased condition. They increased rapidly again in 2004 and 2007. The main causes of rapid increase were the commercial message of instant noodles "I am the one who is making. I am the one who is eating." in 1975, newspaper articles related to "Starting of full-scale studies on female language" in 1980, comments of "active women" and "men's crime" related to a murder case of an elementary school student in Sasebo City and mixed attendance books in 2004, a comment of "Women are machines which give birth to babies" in 2007. Those six causes of rapid increase suggested that the perception of gender such as 'Men need to work outside and Women need to do housework and take care of child' which was fixed until then was changing and becoming a stereotype of virtual reality rather than reality. The vocabulary related to ONNA appeared 3411 times among 3312 newspaper articles which included ONNA. Typical forms of the vocabulary related to ONNA were and . They appeared 2390 times and occupied 70% of the whole data. (3411 times) The form of ONNANOKO among the vocabulary related to ONNA appeared 113 times and occupied a high rate. ONNANOKO(113) and other words such as SHOJO(115), JOJI(28), YOJO(9) (152 in total) implied that appearing of young women at newspaper articles were increasing. Also, the vocabulary related to 'female language' such as ONNAKOTOBA(28) ONNANOKOTOBA(10) and a woman's heart such as ONNAGOKORO(35) and ONNANOKIMOCHI(34) appeared frequently. The vocabulary related to JOSEI were divided into <$JOSEI^{**}$> and <$^{**}JOSEI$>. <$JOSEI^{**}$> were mainly related to an occupation. <$^{**}JOSEI$> were mainly used to express women by regional groups such as or combined with modifiers to express women such as . In case with modifiers, WAKAIJOSEI appeared 35 times and showed the highest frequency. It had negative evaluations in many cases. The vocabulary related to JOSI appeared on the form of <$JOSI^{**}$> and mainly associated with 'a girl's school' and 'a female student'.

• 지식경영연구
• /
• 제23권3호
• /
• pp.65-88
• /
• 2022

기업은 브랜드 인지도 제고와 제품 판매를 위한 공중과의 소통 창구로 소셜미디어를 적극 활용해 왔다. 특히 팬데믹은 효과적인 비대면 소통 채널로서 소셜미디어의 역할이 부상하는 계기가 되었다. 그러나 기업의 사업 성격에 따른 소셜미디어 활용 전략의 차이에 관한 연구는 부족한 실정이다. 이에 본 연구는 기업을 B2B와 B2C로 구분하여 두 집단 간 이용자 인게이지먼트에 영향을 미치는 소셜미디어 콘텐츠 구성 요소에 차이가 있는지를 실증적으로 알아보았다. 분석을 위해 국내 시가총액 상위 100대 기업 중 페이스북 팬페이지를 운영하는 기업 22개를 대상으로 2020년 1월 1일부터 12월 31일까지 게재한 콘텐츠를 살펴보았다. 그 결과 B2C 기업은 콘텐츠 제작 시 B2B 기업보다 동영상을 더 많이 사용해 생생함을 강조했으며, 정보 검색 용이성 측면에서 해시태그를 더 많이 사용했고, 본문에서는 제품명을 더 많이 언급한 것으로 나타났다. 반면 B2B 기업은 콘텐츠 제작 시 이미지를 선호했으며, 용이한 정보 검색을 위해 하이퍼링크를 더 많이 사용했고, 본문에서 제품보다는 회사명을 더 많이 언급했다. 콘텐츠 구성 요소와 인게이지먼트 간의 관계에서 B2B 기업은 이미지가 포함된 경우와 본문 길이가 긴 경우 인게이지먼트 지표(좋아요, 댓글, 공유 수)가 높아졌으나, 하이퍼링크와 URL이 포함된 경우 반대로 인게이지먼트가 낮아졌다. B2C 기업에서는 본문 길이가 길수록 인게이지먼트가 유의미하게 증가함을 확인하였다. 본 연구는 기업 실무자나 운영자가 회사의 특성에 맞춰 인게이지먼트를 높일 수 있는 소셜미디어 전략을 수립하는 데 실무적인 시사점을 제공한다.

• 한국산업정보학회논문지
• /
• 제28권5호
• /
• pp.15-30
• /
• 2023

근래에 트랜스포머(Transformer) 구조를 기초로 하는 ChatGPT와 같은 생성모델이 크게 주목받고 있다. 트랜스포머는 다양한 신경망 모델에 응용되는데, 구글의 BERT(bidirectional encoder representations from Transformers) 문장생성 모델에도 사용된다. 본 논문에서는, 한글로 작성된 영화 리뷰에 대한 댓글이 긍정적인지 부정적인지를 판단하는 텍스트 이진 분류모델을 생성하기 위해서, 사전 학습되어 공개된 BERT 다국어 문장생성 모델을 미세조정(fine tuning)한 후, 새로운 한국어 학습 데이터셋을 사용하여 전이학습(transfer learning) 시키는 방법을 제안한다. 이를 위해서 104 개 언어, 12개 레이어, 768개 hidden과 12개의 집중(attention) 헤드 수, 110M 개의 파라미터를 사용하여 사전 학습된 BERT-Base 다국어 문장생성 모델을 사용했다. 영화 댓글을 긍정 또는 부정 분류하는 모델로 변경하기 위해, 사전 학습된 BERT-Base 모델의 입력 레이어와 출력 레이어를 미세 조정한 결과, 178M개의 파라미터를 가지는 새로운 모델이 생성되었다. 미세 조정된 모델에 입력되는 단어의 최대 개수 128, batch_size 16, 학습 횟수 5회로 설정하고, 10,000건의 학습 데이터셋과 5,000건의 테스트 데이터셋을 사용하여 전이 학습시킨 결과, 정확도 0.9582, 손실 0.1177, F1 점수 0.81인 문장 감정 이진 분류모델이 생성되었다. 데이터셋을 5배 늘려서 전이 학습시킨 결과, 정확도 0.9562, 손실 0.1202, F1 점수 0.86인 모델을 얻었다.