• 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.

• Journal of Multimedia Information System
• /
• 제9권1호
• /
• pp.61-68
• /
• 2022

The importance of online reviews is prevalent as more people access goods or places online and make decisions to visit or purchase. However, such reviews are generally provided by short sentences or mere star ratings; failing to provide a general overview of customer preferences and decision factors. This study explored and broke down restaurant reviews found on Google Maps. After collecting and analyzing 5,427 reviews, we vectorized the importance of words using the TF-IDF. We used a random forest machine learning algorithm to calculate the coefficient of positivity and negativity of words used in reviews. As the result, we were able to build a dictionary of words for positive and negative sentiment using each word's coefficient. We classified words into four major evaluation categories and derived insights into sentiment in each criterion. We believe the dictionary of review words and analyzing the major evaluation categories can help prospective restaurant visitors to read between the lines on restaurant reviews found on the Web.

• 한국콘텐츠학회논문지
• /
• 제17권7호
• /
• pp.443-454
• /
• 2017

온라인에서 생성되는 관광지 관련 정보들을 활용한 관광지 이미지 분석은 관광소비자들의 관광목적지에 대한 인식을 설명할 수 있는 유의미한 정보를 도출할 수 있으며, 관광소비자들의 특정 관광지에 대한 이미지를 더욱 심층적으로 이해할 수 있다. 본 연구는 온라인 빅데이터를 활용한 대구의 관광지 이미지 실례연구를 실시하여 대구의 관광지 이미지를 분석하고 시사점을 도출하고자 하였다. 국내 포털 사이트를 대상으로 텍스트 마이닝과 사회연결망 분석을 실시하여, 대구의 관광지 이미지를 형성하는 관광지 이미지 요소들을 추출하고 영향 정도를 분석하였다. 연구 결과에 따르면 관광객 인프라시설과 문화와 예술, 역사 등의 관광지 이미지 형성 요소들이 대구의 관광지 이미지를 형성하는 주요한 요소들로 파악되었으며, 특히, '대구중구골목투어'가 전체적인 대구의 관광지 이미지 형성에 핵심적인 역할을 하는 것으로 파악되었다.

• The Journal of Asian Finance, Economics and Business
• /
• 제8권1호
• /
• pp.305-315
• /
• 2021

This article aims to explore the contribution of social media value to a company's financial performance in a digital environment economy since the awareness of companies and investors in the use of social media opens up new mechanisms for disseminating information. Quantitative method is used in this study with Multivariate Analysis of Variance as the analysis tool. The data used is secondary data gathered from Indonesia Stock Exchange (IDX) using 308 companies as samples. In the multivariate test, four kinds of multivariate significance tests were carried out, namely Pillai Trace, Wilk Lambda, Hotelling's Trace, and Roy's Largest Root. It was found that social media value has a small contribution in the difference of the level of profitability and the value of the company in Indonesia, but it doesn't have a contribution to the difference of the level of liquidity. The contribution was an implication of online Word of Mouth (WOM) motives which are interrelated with signal theory and as additional information for investors in relation to single-person decision theory. This study provides an insight into the importance of social media management considering that the world of digital economy will continue to develop, so companies in Indonesia need to take advantage of these opportunities.

• 한국전자통신학회논문지
• /
• 제10권4호
• /
• pp.533-538
• /
• 2015

집단지성은 사회학, 경영학, 정치학, 컴퓨터과학 등 여러 분야와 관련이 된다. 이 논문은 인문학과 과학이 수렴, 융합, 통섭되는 시대의 산물인 사회공학분야로 분류할 수 있다. 오늘의 구성원은 자아실현과 기여에 대한 욕구가 증대되었고, 업무가 복잡해지고 변화가 빨라 사회조직 속에도 자연과학의 메커니즘이 필요하다. 집단지성의 메커니즘을 발산과정과 수렴과정으로 구성하며, 7단계의 프로세스(process)를 설계하고 각 단계의 첫 알파벳을 연결하면 'PROCESS'가 되도록 디자인하였다. 이 논문을 통하여 구성원들의 의견이 반영되는 절차를 적용하여 구현되면, 의사결정 절차에 참여했던 구성원들이 결정사항을 실행할 때에도 적극적으로 참여하는데 기여할 것이며, 온라인 커뮤니티에서의 구체적인 도구와 기법연구는 과제로 남긴다.

• 한국의류학회지
• /
• 제29권6호
• /
• pp.847-858
• /
• 2005

The purpose of this study was to examine consumer purchasing behavior of the online shoppers particularly using online clothing shopping mall and to analyze the key factors of both satisfaction and dissatisfaction of their purchase and to compare the both group by lifestyle segmentation in order to provide the e-CRM strategies. Focus group interviews and survey were conducted in December, 2003 with 30 online shoppers who have an experience of online clothing purchasing. The data analysis included the content analysis, descriptive statistics, K-means and factor analysis. Key findings of the study were as follows: First, online shoppers spent average 3.5 hours on internet and usually purchased clothing while surfing the web. Second, consumers were satisfied with reasonable price and customized service but dissatisfied with delayed delivery, limited product availability in both size and color and return policy. Third, according to the lifestyle segmentation, online shoppers could be characterized as 'Luxurious', 'Trendy' and 'Prudent' 'Luxury-oriented consumers', who value fashion, diet and social activity, tended to purchase basic yet high quality products. However, 'Trend-oriented consumers', to whom fashion trend was most important, purchased various latest fashion products with reasonable price and showed generally positive response to emails sent by e-retailers. And lastly 'Prudence-oriented consumers', whose buying decision was based solely on practicality, appeared to be reluctant to purchase clothing online while seeking more credible information and competitive price. In conclusion, this study has its significance in that it helps promote relationships between customers and e-retailers by providing differentiated e-CRM strategies through each customer groups 'lifestyle segmentation and consumer purchasing behavior analysis.

• 지능정보연구
• /
• 제24권1호
• /
• pp.53-74
• /
• 2018

해외 시장 의존형 경제구조를 지닌 우리나라에서 관광산업은 국가경제에 중요한 산업으로 이를 육성하기 위해 정확한 관광 수요 예측이 필요하다. 그에 따라 많은 연구들이 출국 수요를 예측하기 위해 노력해왔으며 출국수요에 영향을 미치는 요인에 대해 다각도로 연구가 이루어져 왔다. 특히 정보기술의 발전으로 최근에는 출국자들의 출국지 선택 등 관광객의 의사결정에 온라인 뉴스, 소셜 네트워크 서비스 등의 온라인 미디어가 많은 영향을 끼치고 있다. 이에 본 연구는 온라인 미디어가 발생시키는 구전 효과가 출국 수요에 미치는 영향을 살펴보고 그 영향 관계를 규명하고자 하였다. 온라인 미디어는 쉽게 접근이 가능하고 공유가 활발하다는 측면에서 구전 효과가 발생되어 사용자들의 의사결정에 영향을 주고 있다. 이를 위해 본 연구에서는 온라인 미디어를 공적 미디어인 뉴스와 사적 미디어인 블로그로 구분하였으며 실제 아시아 5개국의 출국자 수에 이들 미디어가 미치는 영향 관계를 패널 모형을 통해 분석하였다. 그 결과, 온라인 뉴스의 구전 효과는 출국자 수에 부정적인 영향을 미치지만 블로그의 경우 긍정적 영향 관계를 보였다. 따라서 향후 출국 수요 예측에 있어 온라인 미디어의 구전 효과를 반영해야 하며 이는 미디어의 종류에 따라 차별적으로 적용해야 함을 시사한다. 또한 각 국가별로 온라인 미디어의 특성에 따라 미치는 영향 관계가 차이가 있음을 분석하였다. 즉, 출국 국가에 따라 온라인 미디어의 영향력이 다름에 따라 국가별로 차별적인 예측 및 관리 모형이 필요하다. 본 연구 결과를 통해 관광산업종사자들의 국가와 미디어별 온라인 미디어 기반의 마케팅 전략 수립에 도움을 줄 수 있으리라 기대된다.

• 보건의료산업학회지
• /
• 제12권2호
• /
• pp.149-162
• /
• 2018

Objectives : This study aimed to develop tools to measure the social responsibility activities of hospitals using ISO 26000 and to verify the validity and reliability of the developed tools. We verified the content and structural validity, as well as the internal consistency of the proposed measurement tool for hospitals' social responsibility. Methods : We conducted an online survey on hospitals/employees from Feb 26 to Mar 12, 2018, and analyzed selected 197 respondents from the survey by removing incomplete responses. Results : The developed hospitals' CSR (HSR) measurement tool consists of 36 items with 5 factors: "consumer issues", "labor practices", "community involvement & development", "fair operating practice", and "environment". Analysis revealed high reliability with Cronbach' alpha of 0.981. Conclusions : It was verified that the developed HSR tool fully reflected hospital characteristics. This tool can be used to diagnose hospitals' social responsibility and to support strategic decision on social responsibility.

• International Journal of Advanced Culture Technology
• /
• 제8권3호
• /
• pp.54-60
• /
• 2020

Online cybercrime has various causes. The criminal guilty language, Criminal lingo is active in the shaded area with the bilateral aspect of the word on cyber. It has been continuously producing massive risk factors in cyberspace. Criminals are shared and disseminated online. It has been linked with fake news and aids to suicide that has recently become an issue. Thus the criminal lingo has become a real danger factor on cyber interface. Recently, Criminal lingo is shared and distributed as cyber hazard information. It is transformed that damaging to the youth and ordinary people through the internet and social networks. In order to take action, it is necessary to construct an expert system based on AI to implement a smart management architecture with block-chain technology. In this paper, we study technically a new smart management architecture which uses artificial intelligence based decision algorithm and block-chain tracking technology to prevent the spread of criminal lingo factors in the evolving cyber world. In addition, through the off-line regular patrol program of police units, we proposed the conversion of online regular patrol program for "cyber harem area".

• 산업경영시스템학회지
• /
• 제44권2호
• /
• pp.66-77
• /
• 2021

Companies widely use survey to identify customer requirements, but the survey has some problems. First of all, the response is passive due to pre-designed questionnaire by companies which are the surveyor. Second, the surveyor needs to have good preliminary knowledge to improve the quality of the survey. On the other hand, text mining is an excellent way to compensate for the limitations of surveys. Recently, the importance of online review is steadily grown, and the enormous amount of text data has increased as Internet usage higher. Also, a technique to extract high-quality information from text data called Text Mining is improving. However, previous studies tend to focus on improving the accuracy of individual analytics techniques. This study proposes the methodology by combining several text mining techniques and has mainly three contributions. Firstly, able to extract information from text data without a preliminary design of the surveyor. Secondly, no need for prior knowledge to extract information. Lastly, this method provides quantitative sentiment score that can be used in decision-making.