• 한국콘텐츠학회논문지
• /
• 제18권6호
• /
• pp.217-234
• /
• 2018

본 연구는 국내외 스포츠용품 브랜드에 대한 빅데이터 분석을 실시하였다. 이를 위해 소셜 매트릭스 프로그램인 텍스톰과 패션데이터 분석 플랫폼인 MISP를 통해 텍스트 마이닝, TF-IDF, 오피니언 마이닝, 관심도 그래프를 실시하였으며, 스포츠브랜드에 대한 최근 인식을 살펴보기 위해 2017년 1월 1일부터 2017년 12월 31일까지 1년간을 연구대상 기간으로 한정하였다. 분석 결과, 첫째, 각 브랜드를 대표하는 상품을 확인할 수 있었다. 둘째, 각 브랜드를 대표하는 마케팅을 확인할 수 있었다. 셋째, 각 브랜드에서 공통적으로 추출된 단어를 확인할 수 있었다. 넷째, 각 브랜드의 긍정 및 부정에 대한 감정을 확인할 수 있었다.

• Journal of Information Technology Applications and Management
• /
• 제20권2호
• /
• pp.127-146
• /
• 2013

The online social networking services (SNS) have been growing as the means of communication. In this study, we investigated word-of-mouth (WOM) effect under the SNS environment and evaluated the impact of message sender's influence on the WOM effect. Especially, this study focused on the betweenness centrality calculated through the social network analysis (SNA) of SNS network information, and proposed it as the measure of WOM message sender's influence, SNA may provide more accurate and objective measures than subjective self-reporting survey method. Fifty-one Facebook users responded to each of their four Facebook friends, who had been selected based on their betweenness centrality, Statistical analyses were performed using the responses and the betweenness centralities of the Facebook friends. The results showed that the direction (positive vs, negative) of a WOM message in SNS had an impact on the attitude of the message receiver toward the product. Moreover, the betweenness centrality of the message sender as well as his/her opinion leadership had a moderating effect on the WOM effect. Opinion leadership is a measure that has been frequently used for indicating the influence of WOM message sender in the previous studies. Considering the result that the betweenness centrality of the message sender was Significantly correlated to his/her opinion leadership, the betweenness centrality can be used for indicating the influence of WOM message sender.

• 한국정보시스템학회지:정보시스템연구
• /
• 제32권2호
• /
• pp.177-190
• /
• 2023

Purpose Recently, as a new business marketing tool, short form content focused on fun and interest has been shared as hashtags. By extracting positive and negative keywords from media audiences through comment analysis of social media news, various stakeholders aim to quickly and easily grasp users' opinions on major news. Design/methodology/approach YouTube videos were searched using the YouTube Data API and the results were collected. Video comments were crawled and implemented as HTML elements, and the collection results were checked on the web page. The collected data consisted of video thumbnails, titles, contents, and comments. Comments were word tokenized with the R program, comparing positive and negative dictionaries, and then quantifying polarity. In addition, social network analysis was conducted using divided positive and negative comments, and the results of centrality analysis and visualization were confirmed. Findings Social media users' opinions on issue news were confirmed by analyzing and visualizing the centrality of keywords through social network analysis by dividing comments into positive and negative. As a result of the analysis, it was found that negative objective reviews had the highest effect on information usefulness. In this way, previous studies have been reaffirmed that online negative information has a strong effect on personal decision-making. Corporate marketers will analyze user comments on social network services (SNS) to detect negative opinions about products or corporate images, which will serve as an opportunity to satisfy customers' needs.

• 수산해양교육연구
• /
• 제21권1호
• /
• pp.140-150
• /
• 2009

The purpose of the study is to improve in-service fisheries & shipping affiliate teachers informative and professional presentation. The sensible solution to this problem is to analyze about the opinion of in-service fisheries & shipping affiliate teachers about Certification Training Program during 10 years. We provide the suggestion about the coming certification training program that satisfy the need of the trainee and that can be effectively applied into practical teaching movement in school. According to these conclusion, it is estimated that in-service fisheries & marine teacher don't have the negative view of certification training program. By the way Combination subject education program was significantly improved by developing the program on the basis of the fisheries & shipping affiliate teachers' opinion.

• Asian Journal for Public Opinion Research
• /
• 제3권2호
• /
• pp.84-105
• /
• 2016

The instability of social norms on the Internet causes the diversity of social identification. Meanwhile, the anonymity of online social identity and the chaos of the role-playing among the interacting participants cause an ambiguity of identity recognition, which intensifies anxiety about interpersonal interaction. Methods that promote face-to-face interpersonal interaction through the reconstruction of the identification to the social system and intergroup trust is worth further research. Based on a telephone survey of urban residents in thirty-six cities in China (N=1080), the study focuses on the influence of Internet use on interpersonal interaction of urban residents and the mediation effect of social identification. The results show that Internet use has a negative effect on the interpersonal interactions of urban residents, and social identification plays a mediating effect between Internet use and interpersonal interaction. Implications of the results are discussed.

• 한국통신학회논문지
• /
• 제40권12호
• /
• pp.2488-2490
• /
• 2015

본 논문에서는 페이스북에 게시된 글의 어휘 분석 및 호불호를 평가하여, 게시된 글에 대한 정확한 평가를 할 수 있는 시스템을 제안하였다. 기존 평가시 스템과의 성능 비교를 통하여 제안 시스템의 평가 정확도가 높음을 확인하였다.

• 정보학연구
• /
• 제12권3호
• /
• pp.7-17
• /
• 2009

This research is about the design of an opinion drawing and analysis system through statistical based Web Mining of web contents, where data of opinions are automatically drawn and analyzed concerning web documents that are scattered around in various web sites that exist within the internet. Furthermore, provides a search service that can easily classify positive/negative opinions and also provide searching and statistical information. Users, who want to search for opinions, can input a specific keyword to observe opinions of others easily. In addition, there is a merit in materializing the monitoring system.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2012년도 춘계학술발표대회
• /
• pp.406-409
• /
• 2012

'나꼼수 비키니 시위'에 대 긍정적(지지), 부정적(비판) 의견을 담은 트위터 데이터를, 단어의 출현에 주목하여 Naïve Bayes (NB)와 Support Vector Machine (SVM)을 적용하여 자동분류 한 결과, NB가 75.98%로, 73.65%인 SVM 보다 약간 더 나은 성능을 보였다. 본 실험을 통해, 기계학습을 이용한 대중의견(opinion) 자동분류 시스템을 실용화할 때의 고려사항에 대해 살펴 본다.

• Asian Journal for Public Opinion Research
• /
• 제7권1호
• /
• pp.1-22
• /
• 2019

In the age of continuous media change and the coexistence of multiple forms of media, the relationship between the public's media use and political participation is an urgent area of study. This paper makes use of large national sample surveys from 2002, 2011, and 2015, summarizes the change of the public's media use by descriptive statistics analysis, and finds that while the Internet has become an important communication channel, the use of Internet for political information and political participation is still overestimated. Compared to the weak impact of different media channels for political information on political participation, the frequency of media exposure and Internet use play a significant role in political participation. Because of the negative effect of the frequency of Internet use on political participation, the democratization function of the Internet needs to be treated with caution. This paper describes media use and its roles in contemporary China, analyzes the impact of media use on political participation, and extends the cross-cultural application of the theory of political communication.

• Asian Journal for Public Opinion Research
• /
• 제9권3호
• /
• pp.293-306
• /
• 2021

The news and views of Pakistani television channels are extensively shared on digital media for information or analysis where the general public discusses overt and covert agendas by mentioning their factual and presentational style. This study contributes to the contemporary studies of media perception through focus group interviews with 72 randomly selected master's and bachelor's students studying Media and Communication at the School of Media and Communication Studies, University of Management and Technology, Lahore, Pakistan to provide information about the feelings and observations of future journalists and media literates. In summary, the findings of our research exposed the negative perception of Pakistani electronic media among the participants due to what they perceived as biased, inaccurate, and unethical reporting.