• Annual Conference on Human and Language Technology
• /
• 2011.10a
• /
• pp.94-97
• /
• 2011

본 논문은 자동으로 한글 트위터 메시지(트윗: tweet)에 포함된 감정을 분석하는 방법에 대하여 기술한다. 제안된 시스템에 의하여 수집된 트윗들은 어떤 질의에 대해 긍정 혹은 부정으로 분류된다. 이것은 일반적으로 어떤 상품을 구매하기 원하는 고객이나, 상품에 대한 고객들의 평가를 수집하기 원하는 기업에게 유용하다. 영문 트윗에 대한 연구는 이미 활발하게 진행되고 있지만 한글 트윗, 특히 감정 분류에 대한 연구는 아직 공개된 것이 없다. 수집된 트윗들은 기계 학습(Naive Bayes, Maximum Entropy, 그리고 SVM)을 이용하여 분류하였고 한글 특성에 따라 자질 선택의 기본 단위를 2음절과 3음절로 나누어 실험하였다. 기존의 영어에 대한 연구는 80% 이상의 정확도를 가지는 반면에, 본 실험에서는 60% 정도의 정확도를 얻을 수 있었다.

• Journal of Intelligence and Information Systems
• /
• v.20 no.1
• /
• pp.67-101
• /
• 2014

The use of new technology greatly shapes the marketing strategies used by companies to engage their consumers. Among these new technologies, social media is used to reach out to the organization's audience online. One of the most popular social media channels to date is the microblogging platform Twitter. With 500 million tweets sent on average daily, the microblogging platform is definitely a rich source of data for researchers, and a lucrative marketing medium for companies. Nonetheless, one of the challenges for companies in developing an effective Twitter campaign is the limited theoretical and empirical evidence on the proper organizational usage of Twitter despite its potential advantages for a firm's external communications. The current study aims to provide empirical evidence on how firms can utilize Twitter effectively in their marketing communications using the association between brand personality and brand engagement that several branding researchers propose. The study extends Aaker's previous empirical work on brand personality by applying the Brand Personality Scale to explore whether Twitter brand communities convey distinctive brand personalities online and its influence on the communities' level or intensity of consumer engagement and sentiment quality. Moreover, the moderating effect of the product involvement construct in consumer engagement is also measured. By collecting data for a period of eight weeks using the publicly available Twitter application programming interface (API) from 23 accounts of Twitter-verified business-to-consumer (B2C) brands, we analyze the validity of the paper's hypothesis by using computerized content analysis and opinion mining. The study is the first to compare Twitter marketing across organizations using the brand personality concept. It demonstrates a potential basis for Twitter strategies and discusses the benefits of these strategies, thus providing a framework of analysis for Twitter practice and strategic direction for companies developing their use of Twitter to communicate with their followers on this social media platform. This study has four specific research objectives. The first objective is to examine the applicability of brand personality dimensions used in marketing research to online brand communities on Twitter. The second is to establish a connection between the congruence of offline and online brand personalities in building a successful social media brand community. Third, we test the moderating effect of product involvement in the effect of brand personality on brand community engagement. Lastly, we investigate the sentiment quality of consumer messages to the firms that succeed in communicating their brands' personalities on Twitter.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.75-94
• /
• 2011

In this paper, we explore the information diffusion mechanism under social network environments by investigating the effect of message characteristics on the volume and speed of retweeting in Twitter, a popular online social media service. To this end, we select eight main keywords (i.e., '무상급식', '반값등록금', '나가수', '평창', '김연아', '박태환', '아이폰', '갤럭시') that have been popular on online social media in recent days. Each keyword represents various social aspects of Korea that recently grab people's attention such as political issues, entertainment, sports celebrities, and the latest digital products, and eventually holds distinctive message characteristics. Analyzing the frequency and velocity of retweeting for each keyword, we find that more than half of the sample messages posted on Twitter contain personal opinions for the certain keyword, but we also find that the tweets which include objective messages with hyperlink are the fastest ones when being retweeted by other followers. In overall, when being retweeted, the group of messages related to the certain keyword present distinctive diffusion patterns and speed according to message characteristics. From academic perspective, the findings in the study broaden our theoretical knowledge of information diffusion mechanism over online social media. For practitioners, the results also provide managerial implications regarding how to strategically utilize online social media for marketing communications with customers.

• Journal of Digital Convergence
• /
• v.11 no.5
• /
• pp.225-235
• /
• 2013

Recently, in order to promote their marketing promotion, the entrepeneurs attach importance to many SNS services and execute it. The representative elements of the SNS service are interactivity, information offering. This study analyzes empirical effects on the SNS service depending on the Relationship Commitment and shows the strategies to enlarge the use frequency and the On-line Word-of-Mouth. The conclusion of this study shows that the Interactivity has a higher positive effects on Affective Commitment than those on information offering and Information offering has stronger positive effects on calculative commitment than interactivity. Also, these effects enlarge the high use frequency more than the low use frequency. This study also shows that the information offering affect the On-line Word-of-Mouth more positively than the Interactivity. And this study shows that SNS service affects the positive effects on the relationship commitment rather than the On-line Word-of-Mouth. Based on the results, the practical implications are offered.

• Journal of Korea Society of Industrial Information Systems
• /
• v.26 no.5
• /
• pp.79-94
• /
• 2021

Despite the importance of the supply chain risk due to the negative word-of-mouth (NWOM) in social media, related research is insufficient. Thus, this study analyzes how the NWOM of the product is distributed through social media and the characteristics of the distributor based on social exchange theory. For this purpose, we collected information on car recalls from four companies using Twitter from the National Highway Traffic Safety Administration (NHTSA). Based on the Seed Tweet, a Re-Tweet (RT) network was constructed to examine the distribution and spread of NWOM, and regression analysis was performed to test the hypothesis. As a result, it was confirmed that NWOM is a small world network structure that spreads around hub users connected to many users. Moreover, it was found that the more interactive and reciprocal relations the first distributor has, the greater the speed and scale of distribution of NWOM.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.3
• /
• pp.427-436
• /
• 2013

Social media is drawing attention among companies for its potential as a marketing tool. There are many types of social media and their characteristics are varied, and thus choosing the appropriate social media considering the purpose of the company is important. In this paper, we conduct comparative analysis on the popular social media such as Facebook, Twitter, Naver blog, Youtube, Cyworld and Me2day using multidimensional scaling method. The result shows that there are differences in the effectiveness of enhancing diverse dimensions of corporate image among social media. This result can be used in developing social media based marketing strategy.

• The Korean Journal of Franchise Management
• /
• v.2 no.2
• /
• pp.24-44
• /
• 2011

Many companies are increasingly using social network service(SNS) as an online marketing tool, and its marketing activation has been in the limelight as a differentiation strategy most recently. The purpose of this study is to analyze online marketing cases utilizing SNS and to apply it in Franchise Enterprise in order to activate its marketing activities. This study is more concerned with the cases of facebook, twitter, and blog among social network services and suggests some ways of utilizing them in Franchise Enterprise as follows: Based on the examples of facebook, firstly, we set up the role as a homepage in individul, Franchise Enterprise, and other organizations. Secondly, we also set up the role as an organizing tool in communities, and thirdly, setting up the role as a location map tool. Regarding some applications in marketing tool of Franchise Enterprise, we suggest the role as a public relation tool of the company and brand, and also propose the role of brand planning and development. Finally, we suggest a way of overcoming the limitation in offline operations.

• Journal of Digital Convergence
• /
• v.10 no.6
• /
• pp.83-92
• /
• 2012

The purpose of this current study is to examine CEO image presented in messages of CEO twitter and perceived by CEO twit followers. To conduct this study, we selected two CEOs, ChanJin Lee and HyeonMyeong Pyo who are top ranking based on a number of followers in Korea. We investigated each CEO's Tweet, RT, Reply, and RT+Reply using three CEO image factors: CEO personality, CEO quality, and CEO outward characteristics. Also, followers were asked what image mostly they have based on those three image factors. The results showed that for ChanJin Lee, CEO quality were more presented in twitter than CEO personality and CEO outward characteristics, and CEO Lee's followers also perceived that Lee has more CEO quality image than others. Pyo, HyeonMyeong has CEO quality image in twitter than others, and his followers thought that he had more CEO outward characteristics image than others.

• Journal of the Korean Society for information Management
• /
• v.30 no.1
• /
• pp.285-302
• /
• 2013

This study identified topic shifts and patterns over time by analyzing an enormous amount of Twitter data whose characteristics are high accessibility and briefness. First, we extracted keywords for a certain product and used them for representing the topic network allows for intuitive understanding of keywords associated with topics by nodes and edges by co-word analysis. We conducted temporal analysis of term co-occurrence as well as topic modeling to examine the results of network analysis. In addition, the results of comparing topic shifts on Twitter with the corresponding retrieval results from newspapers confirm that Twitter makes immediate responses to news media and spreads the negative issues out quickly. Our findings may suggest that companies utilize the proposed technique to identify public's negative opinions as quickly as possible and to apply for the timely decision making and effective responses to their customers.

• International Commerce and Information Review
• /
• v.13 no.4
• /
• pp.3-21
• /
• 2011

In this study, several experiments were designed to test the effectiveness of social media in export marketing. In particular, the experiments were made using Twitter and Facebook. The results showed that users' interest were able to increase the effects combined with B2B and B2C marketing events. The B2C marketing events could be made by personal target Event, Poll event, guest comments and social commerce. The B2B marketing was performed using Page Manager, Affiliate page, building and affiliate marketing group. Special features of Facebook such as social plug-in, Twitter integration, and Photo Tagging were found effective. A couple of implications were found in this study. First, the link between social media channel system was key success factor in effective export marketing. Second, the corporate marketing mix and social media consistent with the marketing mix strategy, communication between the managers and the managers' competencies were obtained for the key success factors.