Analysis of Bloggers' Influence Style within Blog

Tan, Luke Kien-Weng,Na, Jin-Cheon Korea Institute of Science and Technology Informat 2013 Journal of Information Science Theory and Practice Vol.1 No.2

Blogs are readily available sources of opinions and sentiments which allows bloggers to exert a certain level of influence over the blog readers. Previous studies had attempted to analyze blog features to detect influence within the blogosphere, but had not studied in details influence at the blogger-level. Other studies studied bloggers' personalities with regards to their propensity to blog, but did not relate the personalities of bloggers to influence. Bloggers may differ in their way or manner of exerting influence. For example, bloggers could be active participants or just passive shares, or whether they express ideas in a rational or subjective manner, or they are received positively or negatively by the readers. In this paper, we further analyze the engagement style (frequency, scope, originality, and consistency of the blog postings), persuasion style (appeals to reasons or emotions), and persona (degree of compliance) of individual bloggers. Methods used include similarity analysis to detect the sharing-creating aspect of engagement style, subjectivity analysis to measure persuasion style, and sentiment analysis to identify persona style. While previous studies analyzed influence at blog site level, our model is shown to provide a fine-grained influence analysis that could further differentiate the bloggers' influence style in a blog site.

INFLUENCE ANALYSIS FOR GENERALIZED ESTIMATING EQUATIONS

Jung Kang-Mo The Korean Statistical Society 2006 Journal of the Korean Statistical Society Vol.35 No.2

We investigate the influence of subjects or observations on regression coefficients of generalized estimating equations using the influence function and the derivative influence measures. The influence function for regression coefficients is derived and its sample versions are used for influence analysis. The derivative influence measures under certain perturbation schemes are derived. It can be seen that the influence function method and the derivative influence measures yield the same influence information. An illustrative example in longitudinal data analysis is given and we compare the results provided by the influence function method and the derivative influence measures.

인플루언서를 활용한 광고 콘텐츠의 효과: 소비자 댓글 분석

정태영,황장선 한국광고학회 2023 광고학연구 Vol.34 No.6

The influencer advertising strategy is increasingly recognized as highly effective with its various benefits and has been widely popularized. As getting much attention, relevant research efforts have been devoted to this field. Recent studies have focused on examining the effectiveness of influencer advertising, especially with the type of influencers. In general, the effectiveness of influence advertising has been evaluated with some available indices such as the numbers of ‘likes,’ ‘views,’ and comments. Limited with these indices, the study aims to investigate the actual contents of comments, which can enhance deeper and various understanding of consumer’s responses to the influences’ contents. In the current study, influencers were categorized based on expertise (expert-general) and the number of subscribers (mega-micro) in order to investigate the differences of comments by these categories. Initially, 80 contents from 16 influencers' channels and a total of 4,000 comments were collected for the analysis. Overall, professional and micro generated more comments. The analysis showed that professional influencers tended to yield more positive comments compared to general influencers. Regarding the size of subscribers, mega influencers generated more positive comments in various metrics compared to micro influencers, which is somewhat different from recent previous Additionally, this study aims to enhance understanding of the effectiveness of influencer advertising through analysis of factors such as disclosure of advertisements and the number of replies. 인플루언서를 활용한 커뮤니케이션 전략이 다양한 차원에서 높은 효과가 있다고 인식되면서, 기업들의 인플루언서 광고가 이제는 보편적인 현상으로 받아들여지고 있다. 광고학 분야에서 인플루언서는 최근 중요한 주제로 다루어지고 있으며, 관련한 다양한 연구들이 진행되어 왔다. 근래의 관련 연구들은 인플루언서의 유형에 따라 어떤 효과의 차이가 있는지를 살펴보는 것에 집중되어 왔는데, 본 연구는 효과의 검증을 댓글의 내용을 통해 하고자 하였다. 이는 피상적인 일부 수치들 - ‘좋아요’의 수, 조회수, 댓글의 수-에 의해 콘텐츠의 효과를 검증하기 보다는 실제적인 소비자들의 반응인 댓글의 내용을 분석함으로써 보다 풍부한 효과의 차원들을 살펴보는 것이 필요하다. 본 연구에서는 인플루언서의 유형을 구독자의 수(메가-마이크로)와 전문성(전문-비전문)으로 구분하여 유형별로 댓글의 내용에 어떤 차이가 있는지를 살펴보았다. 총 16명의 인플루언서가 운영하는 채널에 게재된 콘텐츠 80개에 대한 1차 분석 결과, 전문 인플루언서와 마이크로 인플루언서가 더 많은 댓글을 양산해 내고 있음을 알 수 있었다. 해당 콘텐츠에 대한 댓글 4,000개의내용을 분석한 결과에서는 전문 인플루언서가 비전문 인플루언서에 비하여 더 긍정적인 내용의댓글들을 이끌어 내고 있었다. 구독자의 규모에 따른 비교에서는 메가 인플루언서가 대체로 더 많은 지표에서 마이크로 인플루언서보다 긍정적 내용을 도출해 내고 있었다. 본 연구에서는 덧붙여 광고 명시, 대댓글의 수 등에 대한 분석을 통해 인플루언서 광고의 효과성에 대한 이해를돕고자 하였다.

Sensitivity analysis for ranked data

한상태 한국통계학회 2014 Journal of the Korean Statistical Society Vol.43 No.1

Sensitivity analysis is to study the influence of a small change in the input data on theoutput of the analysis. Han and Huh (1995) developed a quantification method for theranked data. However, the question of stability in the analysis of ranked data has not beenconsidered. Here, we propose a method of sensitivity analysis for ranked data. Our aim is toevaluate perturbations by using a graphical approach suggested by Han and Huh (1995). Itextends the results obtained by Tanaka (1984) and Huh (1989) for the sensitivity analysis inHayashi’s third method of quantification and those by Huh and Park (1990) for the principalcomponent reduction of the case influence derivatives in regression. A numerical exampleis provided to explain how to conduct sensitivity analysis based on the proposed approach.

대학법인 수익용 부동산의 운영성과 영향요인 분석

길용수(Kil, Yong Soo),이호병(Lee, Ho Byung) 韓國不動産學會 2010 不動産學報 Vol.42 No.-

1. CONTENTS (1) RESEARCH OBJECTIVES The purpose of this study is to analyze the income-producing real estate factors for operating performance of income-producing real estate owned by the educational foundation of private universities. (2) RESEARCH METHOD This study was focused on statistical analysis. The data for this analysis were collected from the Korea Foundation for the Promotion of Private School. This study used the statistical analysis techniques such as cluster analysis and regression analysis. (3) RESEARCH FINDINGS In the result of this study, there was a significant difference between higher return group and lower return group in the parameter values of regression model for operating performance of income-producing real estate owned by the educational foundation of private universities. 2. RESULTS The analysis showed that the main factors for operating performance of income-producing real estate were asset valuation, capital gains and operating profits. The results of the regression analysis showed that there were significant differences in the values of primary parameters between the two cluster groups - higher return group and lower return group.

광역상수도 유속계수와 영향인자에 관한 통계적 분석

김범준,김길호,김형수 한국수자원학회 2016 한국수자원학회논문집 Vol.49 No.5

In case of the application of Hazen-Williams C for design, operation or maintenance of water supply system, field situations always should be reflected on the factors. In this study, the relationships between C factors and influencing factors are analyzed using statistical techniques with 174 measured C factor data collected in periodic inspection for safety diagnosis in multi-regional water supply systems. To analyze their relationships, cross analysis, one-way ANOVA, correlation analysis were conducted. Analysis results showed that C factors had high correlations with both of elapsed year and pipe diameter and were relatively highly affected by coating material among influencing factors with the categorical type. On the other hand, elapsed year, pipe diameter and water type were meaningful influencing factors according to the results of multiple regression analysis. The Cluster analysis revealed that C factors had a tendency of being fundamentally classified on the basis of the elapsed year of about 20 years and the pipe diameter of 1500mm. Although C factors were generally greatly affected by elapsed year, size of pipe diameter relatively had an large influence on values of them in case of large diameter pipes. Lastly, It can be suggested that C factor estimation formulas using multiple regression analysis and clustering analysis in this study, can be applied as decision standards of C factor in multi-regional water supply systems. 유속계수는 상수도 설계, 운영, 유지관리 등의 과정에서 항상 현장 실정이 고려된 값이 사용되어야 한다. 본 연구는 광역상수도 정밀안전진단 과정에서의 174개 실측자료를 바탕으로 유속계수와 주요 인자 간의 관계를 통계적 기법을 활용하여 분석하였다. 이들 관계를 분석하기 위해서 교차분석, 일원배치 분산분석, 상관분석 등을 수행하였으며, 그 결과 유속계수와 사용년수 및 관경이 높은 상관관계를 나타내고 여러 범주형 자료 형태 영향인자 중에 내부도장재가 상대적으로 유속계수에 많은 영향을 주는 것으로 검토되었다. 반면 다중회귀분석의 결과에서는 사용년수, 관경 및 수종이 중요한 영향인자인 것으로 검토되었다. 군집분석 결과, 유속계수는 기본적으로 사용년수 약 20년, 관경 1500mm를 기준으로 분류되는 경향이 있었으며, 유속계수는 전반적으로 사용년수에 많은 영향은 받으나 대구경 관에서는 상대적으로 사용년수보다 관경에 많은 영향을 받는 것으로 검토되었다. 마지막으로 본 연구에서는 회귀분석과 군집분석을 사용하여 유속계수 산정식들을 제안하였으며, 이러한 추정식들은 추후 광역상수도의 유속계수 결정 및 사용 시에 판단기준이 될 수 있을 것으로 판단된다.

서비스 중요도를 사용한 서비스나무분석의 개선

박종훈(Jong Hun Park),황영훈(Young Hun Hwang),이상천(Sang Cheon Lee) 한국산업경영시스템학회 2017 한국산업경영시스템학회지 Vol.40 No.2

The purpose of this paper is to improve the service tree analysis introduced recently by Geum et al. [15]. Service tree analysis structures the service based on the customer participation perspective and provides a qualitative analysis method categorizing the service elements on the basis of its impact to top service. This paper attempts to apply the concept of reliability importance to the service tree analysis as a perspective of quantitative analysis, which is considered little in Geum et al. [15]. Reliability importance is a measure of the structural impact of the components that make up the system on the system lifetime in reliability engineering field and often used in fault tree analysis. We transform the reliability importance into service importance in accordance with service tree analysis, so that the influence of service elements on the service can be judged and compared. The service importance is defined as the amount of change of the service according to the change of the service element, therefore, it can be utilized as an index for determining a service element for service improvement. In addition, as an index for paired service elements, the relationship between the two service components can be measured by joint service importance. This paper introduces conceptual changes in the process of applying reliability importance to service analysis, and shows how to use the service importance for identifying the priority of service element for the final service and improving customer satisfaction through an example. By using the service importance and joint service importance in service tree analysis, it is possible to make efficient decision making in the process of determining the service elements for analyzing and improving the service.

우이신설선 건설이 주변 아파트 가격에 미치는 영향에 관한 연구

한다솜,최창규 한국지역개발학회 2018 한국지역개발학회 학술대회 Vol.2018 No.6

The price of a house is affected by various factors such as the individual characteristics of the real estate and the environment. Among them, transportation access is the most influential factor in housing price. This study analyzed the indirect effect of traffic accessibility on apartment prices. Especially in the case of Ui-Sinseol Line, the influence of the station area will be different due to the characteristics of light rail. The effect of the opening of Ui-Sinseol New Line on the surrounding apartments was analyzed by multiple regression analysis. First, we estimate the basic model for the whole sample and then analyze the model according to the distance from the station. Next, we analyzed the influence of the subway station by the construction phase of Ui-Sinseol Line, and estimated the regression model by dividing the western and eastern regions. Among them, the East - West dummy model is the best model to predict the transaction price. Second, the apartment trading period was divided into three periods before construction, after construction, after completion, and after completion. This model was not much different from the basic model. Third, the regression model was estimated by dividing the western and eastern regions. The influence of the station area was not significant in the east area. The east side was close to Line 4, so the influence of station area did not appear well. The western area is the same as the basic model, and the influence of station area is significant. Therefore, the influence of the station area of the Ui-Sinseol Line was found only in the western part of Ui-Sinseol Line. Ui-Sinseol Line has lower influence on price than existing subway station and it is different according to surrounding environment. Lastly, it is found that the apartment transaction price is higher when the distance from the subway station is more than 500m and the number of subscribers is less than the average and the number of subscribers is less than 500m. It was found that apartment prices were low when the number of visitors exceeded the average of 500m from the subway station. As a result, we can see that the influence of the station area on the apartment price has more influence on the street distance than the number of the passengers.

조직에서의 위계적 리더십 : Pelz 효과의 재검증

김경수,노현재,김인숙,김광숙,양동민 한국인사관리학회 2013 조직과 인사관리연구 Vol.37 No.1

본 연구는 Pelz 효과의 재검증을 통해 단일수준에 국한되어 연구되고 있는 리더십 연구들의 한계점을 극복하고 집단수준, 부서수준에서의 단일분석과 더불어 두 가지 수준을 동시에 고려한 다분석수준을 통해, 정확한 분석이 이루어지지 않은 Pelz(1952) 이론의 분석수준에 대한 가정을 실증하고자 하였다. 이를 위해 설문조사를 통해 얻은 17개 조직, 34개 부서, 83명의 상사, 235명의 부하 데이터를 활용하였다. 실증분석 결과, 첫째, 관리자의 상향적 영향력은 부하의 직무만족, 직무성과와 유의한 정의 관계가 있는 것으로 나타났다. 둘째, 단일수준(집단) 분석 결과에 있어서는 관리자의 상향적 영향력, 부하의 성과(직무만족과 성과), 그리고 두 변수 간 관계가 모두 집단전체수준(group wholes)에서 일어남이 확인되어 동일한 집단에 속한 부하들은 관리자의 상향적 영향력 정도에 따라 유사한 정도의 높은 또는 낮은 직무만족과 직무성과를 보이는 것으로 나타났다. 또한 부서수준 분석결과에 따르면 상사의 상향적 영향력, 부하의 성과(직무만족과 직무성과), 그리고 두 변수간의 관계가 부서전체수준(department wholes)에서 성립하는 것으로 확인되어 동일한 부서에 속한 관리자들의 상향적 영향력이 유사하게 나타나고 이에 따라 부하의 직무만족과 직무성과 역시 유사한 정도를 가지는 것으로 나타났다. 셋째, 집단수준과 부서수준을 동시에 고려한 다분석수준 결과에 따르면 불연속성 가설보다는 상동관계 가설이 보다 타당한 것으로 나타났다. 이러한 결과는 Pelz의 이론이 집단수준에서는 성립하는 반면 부서수준에서는 성립하지 않는다는 것을 보여준다. 본 연구의 결론부분에서는 이러한 결과가 가지는 시사점과 향후 연구방향 및 본 연구가 가지는 한계점에 대한 논의가 이루어졌다. This paper attempted to overcome limitations of leadership studies that focus only on the group level of analysis by retesting the Pelz effect from a multiple-level of analysis. Data from 235 subordinates and their 83 managers of 34 departments in 17 different firms showed that (1) managers' upward influence positively related to subordinates' job satisfaction and performance and (2) managers' upward influence, subordinates' job satisfaction and performance varied between groups and the relationships among the variables covaried between groups. These results indicate that subordinates in the same group show similar level of job satisfaction and performance depending on managers' upward influences. Second, the results also showed that managers' upward influence, subordinates' job satisfaction and performance at the group level varied between departments and the relationships among the variables covaried between departments. Third, the results from the multiple-level of analysis showed that the homology hypothesis rather than the discontinuity hypothesis was valid. These results support Pelz's assertion that managers' upward influence affects job satisfaction and performance of subordinates in the same group. However, theses results did not support Pelz's assertion that the relationship between managers' upward influence and subordinates' job satisfaction and performance at the group level varied within departments. The results from the multiple-level of analysis indicate that the relationship between managers' upward influence and subordinates' job satisfaction and performance at the group level reflects the department level. In other word, managers show similar level of upward influence because they are in the same departments and subordinates in the same group show similar level of job satisfaction and performance because they are in the same department. In the conclusion section the implications of the study results, directions of future study, and the limitations of this study were discussed.

전국 통행기종점 자료를 이용한 지역간 상호관련성 분석

백승걸(Baek Seung-Kirl) 대한국토·도시계획학회 2003 國土計劃 Vol.38 No.3

Interregional relations are very important information for national development and planning. Previous researches focus only on social-economic variables such as population etc. Therefore, they analyse only total trip and indirect interregional relations such as movement of population. But they did not analysed direct interregional relations such as interregional trip. They did not analyzed trip purpose or trip mode that were detailed information for interregional relations. This paper analyse total trip and trip by trip purpose or trip mode. This paper use influence analysis, factor analysis and cluster analysis. Influence is ratio that is interregional trip divided by total production trip. Factor analysis is used to uncover the latent structure of a set of variables. Cluster analysis is an exploratory data analysis tool for solving classification problems. We can obtain new information for interregional relations from regional origin and destination trip tables.