온라인 커뮤니티에 드러난 MZ세대의 감성과 여론조사 간 상관관계에 관한 연구

최한별,김수림,양희동 한국IT서비스학회 2023 한국IT서비스학회지 Vol.22 No.3

The ‘MZ generation’ is accustomed to expressing their thoughts and opinions online. As a result, the role of social media in understanding the opinions and public sentiment of the MZ generation has become increasingly important. In particular, the role of social media in understanding the opinions of young people in political contexts such as policies and elections is becoming more significant. Traditionally, in such political situations, various institutions conduct opinion surveys to grasp the opinions of the people. However, existing opinion surveys have many errors and limitations in understanding the specific opinions of the entire population since they are conducted on arbitrary individuals through survey techniques. Online communities are representative social media that share the opinions of the public on specific issues such as politics, economics, and culture. Therefore, online communities are widely used as a means to supplement the limitations of traditional opinion polls. In particular, the MZ generation is familiar with online platforms, and their political support has significant influence on election results and policy decisions. With this regard, this study analyzed the relationship between the sentiment reflected in online community text data by age group on major candidates and public opinion survey support rates during the Korean presidential election for those in their 20s. The analysis showed that negative sentiments reflected in online communities by the MZ generation have a negative correlation with public opinion survey support rates. This study contributes to theory and practice by revealing a significant association between social media and public opinion polls.

온라인 의견을 통한 대한민국 공군의 이미지 분석 : 감성 분석 접근

장우석 ( Jang Woo Seok ) 공군사관학교 2017 군사과학논집 Vol.68 No.1

안보 위협이 급증하면서, 대한민국 공군은 국가 방위 임무를 수행하기 위해 공군의 위상을 국민에게 알려왔다. 이 과정에서 공군의 이미지를 높이기 위해, 국민의 의견에 대한 빠른 피드백의 필요성이 대두되고 있다. 과거 연구는 피드백을 위해 설문조사를 활용하였지만, 이는 국민의 의견보다 전문가 의견에 강한 영향을 받는다. 블로그나 SNS(Social Network Service) 내 온라인 의견은 국민의 생각을 온전히 담고 있으며, 광고보다 파급력이 크다는 점에서 가장 좋은 피드백 수단이 될 수 있다. 이에 본 연구는 공군과 관련하여 국민이 남긴 온라인 의견을 분석하여 국민이 1) 어떤 대상에 대해 2) 어떻게 생각하는지 확인하였다. 텍스트마이닝 기법을 활용하여 추출한 핵심 단어를 분석하여 국민이 공군의 어떤 대상이나 특성에 대해 이미지를 가졌는지 파악하였다. 또한, 온라인 의견이 긍정적으로 작성되었는지 파악하기 위해 감성 분석을 활용하였다. 본 연구는 국민이 직접 작성한 온라인 의견을 활용했다는 점에서 진솔하고 국민의 생각과 일치하는 자료로 군 조직 이미지를 분석했다는 의의가 있다. With increasing the threat of national security, ROKAF(Republic of Korea Air Force) has been informing the status of them for people, which it is a must in national defense. To raise the image of ROKAF, the importance of feedback for people is steadily increasing. Many previous studies have carried out survey to get feedback from the public, survey are likely to be created by experts' opinions more than by the public. So, various online opinions from blog and SNS can be best alternative data to get the feedback related the image of ROKAF. Because these data can reflect the writer's opinion through frank sentences, and tend to more influence other people than advertisement. This study identifies 1) what features(objects) are frequently mentioned and 2) how to evaluate these features in online opinion, by analyzing the posts from blog and SNS. To do this, we extract the keyword to identify the frequently mentioned features. And we conduct the sentiment analysis to analyze the polarity of each online opinion. Major contribution of this study is trial to use online opinion which in concordance with the people's idea, thus, this framework is expected to meet with good feedback from people.

온라인 주식 포럼의 핫토픽 탐지를 위한 감성분석 모형의 개발

홍태호(Taeho Hong),이태원(Taewon Lee),리징징(Jingjing Li) 한국지능정보시스템학회 2016 지능정보연구 Vol.22 No.1

Document classification based on emotional polarity has become a welcomed emerging task owing to the great explosion of data on the Web. In the big data age, there are too many information sources to refer to when making decisions. For example, when considering travel to a city, a person may search reviews from a search engine such as Google or social networking services (SNSs) such as blogs, Twitter, and Facebook. The emotional polarity of positive and negative reviews helps a user decide on whether or not to make a trip. Sentiment analysis of customer reviews has become an important research topic as datamining technology is widely accepted for text mining of the Web. Sentiment analysis has been used to classify documents through machine learning techniques, such as the decision tree, neural networks, and support vector machines (SVMs). is used to determine the attitude, position, and sensibility of people who write articles about various topics that are published on the Web. Regardless of the polarity of customer reviews, emotional reviews are very helpful materials for analyzing the opinions of customers through their reviews. Sentiment analysis helps with understanding what customers really want instantly through the help of automated text mining techniques. Sensitivity analysis utilizes text mining techniques on text on the Web to extract subjective information in the text for text analysis. Sensitivity analysis is utilized to determine the attitudes or positions of the person who wrote the article and presented their opinion about a particular topic. In this study, we developed a model that selects a hot topic from user posts at Chinas online stock forum by using the k-means algorithm and self-organizing map (SOM). In addition, we developed a detecting model to predict a hot topic by using machine learning techniques such as logit, the decision tree, and SVM. We employed sensitivity analysis to develop our model for the selection and detection of hot topics from China’s online stock forum. The sensitivity analysis calculates a sentimental value from a document based on contrast and classification according to the polarity sentimental dictionary (positive or negative). The online stock forum was an attractive site because of its information about stock investment. Users post numerous texts about stock movement by analyzing the market according to government policy announcements, market reports, reports from research institutes on the economy, and even rumors. We divided the online forum’s topics into 21 categories to utilize sentiment analysis. One hundred forty-four topics were selected among 21 categories at online forums about stock. The posts were crawled to build a positive and negative text database. We ultimately obtained 21,141 posts on 88 topics by preprocessing the text from March 2013 to February 2015. The interest index was defined to select the hot topics, and the k-means algorithm and SOM presented equivalent results with this data. We developed a decision tree model to detect hot topics with three algorithms: CHAID, CART, and C4.5. The results of CHAID were subpar compared to the others. We also employed SVM to detect the hot topics from negative data. The SVM models were trained with the radial basis function (RBF) kernel function by a grid search to detect the hot topics. The detection of hot topics by using sentiment analysis provides the latest trends and hot topics in the stock forum for investors so that they no longer need to search the vast amounts of information on the Web. Our proposed model is also helpful to rapidly determine customers’ signals or attitudes towards government policy and firms’ products and services.

온라인 리뷰 데이터의 오피니언마이닝을 통한 콘텐츠 만족도 분석 시스템 설계

김문지 ( Moonji Kim ),송은정 ( Eunjeong Song ),김윤희 ( Yoonhee Kim ) 한국인터넷정보학회 2016 인터넷정보학회논문지 Vol.17 No.3

소셜 네트워크 서비스(SNS)의 활성화로 웹상에는 방대한 양의 온라인 리뷰들이 생산되고 있으며, 이러한 온라인 리뷰들은 다양한 콘텐츠들에 대한 의견 데이터로써 콘텐츠 이용자와 제공자들에게 가치 있는 정보로 활용되고 있다. 한편, 온라인 리뷰에 대한 중요도가 높아짐에 따라 온라인 리뷰를 분석하여 글쓴이의 의견이나 평가, 태도, 감정 등을 추출해 내는 오피니언마이닝에 대한 연구가 활발하게 진행되고 있다. 그러나 기존의 오피니언마이닝 연구들에서는 리뷰의 의견 분류에만 초점을 맞추어 감성 분석 기법을 설계하였기 때문에 리뷰 속에 내포되어있는 작성자의 자세한 만족도까지는 알 수 없었으며, 감성 분석 기법이 특정 콘텐츠에 한정되어있어 도메인이 같지 않은 다른 콘텐츠들에는 적용될 수 없다는 문제점이 있었다. 이에 본 연구에서는 기존 의견 분류 방법에 강도를 주어 좀 더 세밀한 감성 분석을 수행하고, 이 결과를 통계적 척도에 적용하여 리뷰에 내포되어 있는 작성자의 자세한 만족도를 도출 할 수 있는 감성 분석 기법을 제안한다, 그리고 제안한 기법을 바탕으로 도메인에 상관없이 다양한 콘텐츠에 적용되어 콘텐츠의 만족도를 분석 할 수 있는 시스템을 설계하였다. 또한 방대한 양의 리뷰 데이터들을 빠르고 효율적으로 처리하기 위해 빅 데이터 처리도구인 하둡을 기반으로 시스템을 구축하였다. 본 시스템을 통해 콘텐츠 이용자는 보다 효율적인 의사결정을, 제공자들은 빠른 반응분석을 할 수 있어 본 시스템은 사용자의 의견을 필요로 하는 다양한 분야에 매우 실용적으로 활용 될 것으로 기대한다. Following the recent advancement in the use of social networks, a vast amount of different online reviews is created. These variable online reviews which provide feedback data of contents` are being used as sources of valuable information to both contents` users and providers. With the increasing importance of online reviews, studies on opinion mining which analyzes online reviews to extract opinions or evaluations, attitudes and emotions of the writer have been on the increase. However, previous sentiment analysis techniques of opinion-mining focus only on the classification of reviews into positive or negative classes but does not include detailed information analysis of the user`s satisfaction or sentiment grounds. Also, previous designs of the sentiment analysis technique only applied to one content domain that is, either product or movie, and could not be applied to other contents from a different domain. This paper suggests a sentiment analysis technique that can analyze detailed satisfaction of online reviews and extract detailed information of the satisfaction level. The proposed technique can analyze not only one domain of contents but also a variety of contents that are not from the same domain. In addition, we design a system based on Hadoop to process vast amounts of data quickly and efficiently. Through our proposed system, both users and contents` providers will be able to receive feedback information more clearly and in detail. Consequently, potential users who will use the content can make effective decisions and contents` providers can quickly apply the users` responses when developing marketing strategy as opposed to the old methods of using surveys. Moreover, the system is expected to be used practically in various fields that require user comments.

온라인 의견을 통한 대한민국 공군의 이미지 분석 : 감성 분석 접근

장우석 ( Jang Woo Seok ) 공군사관학교 2017 空士論文集 Vol.68 No.1

With increasing the threat of national security, ROKAF(Republic of Korea Air Force) has been informing the status of them for people, which it is a must in national defense. To raise the image of ROKAF, the importance of feedback for people is steadily increasing. Many previous studies have carried out survey to get feedback from the public, survey are likely to be created by experts' opinions more than by the public. So, various online opinions from blog and SNS can be best alternative data to get the feedback related the image of ROKAF. Because these data can reflect the writer's opinion through frank sentences, and tend to more influence other people than advertisement. This study identifies 1) what features(objects) are frequently mentioned and 2) how to evaluate these features in online opinion, by analyzing the posts from blog and SNS. To do this, we extract the keyword to identify the frequently mentioned features. And we conduct the sentiment analysis to analyze the polarity of each online opinion. Major contribution of this study is trial to use online opinion which in concordance with the people's idea, thus, this framework is expected to meet with good feedback from people.

A study on the Similarity and Results of Opinion polls for Reviews by Online Media through Sentiment Analysis

Suyeon Sun,Jenny Park,Baek Sujin,Haejin Chung,Jung Bokmoon,Park Sohyun,Seunghun Baek,Eung-Kyo Suh 한국차세대컴퓨팅학회 2021 한국차세대컴퓨팅학회 학술대회 Vol.2021 No.11

The main research topic of this study is how much ‘opinion mining’ of online comments on specific keywords reflects actual public opinion. In detail, we compared and analyzed how much the results of sentiment analysis for comments by platform reflect the actual opinion poll results. We analyzed the most mentioned keywords by platform and by parking in the comments classified as positive, and the most mentioned keywords by platform and by parking in the comments classified as negative. As a result of the study, it was found that the results of the polls were similarly reflected in the order of the Naver News model, Naver News + YouTube model, and YouTube model. In addition, it was possible to find out keywords with high interest by positive/negative public opinion through positive/negative word cloud analysis by parking and platform.

온라인 공간의 정치 양극화는 심화될 것인가?: 선거 기사 댓글에 대한 경험적 분석

엄기홍 ( Eom Ki-hong ),김대식 ( Kim Dae-sik ) 한국지능정보사회진흥원 2021 정보화정책 Vol.28 No.4

The purpose of this research is to investigate the attributes of the online world and to analyze their influence on democracy. The research focuses on the mayoral by-elections that were held in Seoul and Busan, South Korea, on April 4, 2021. The study demonstrates the characteristics of online spaces and the polarization of the online public through news articles and user comments from the Internet. The research includes topic modeling to measure the diversity of media reports, sentiment analysis to measure online public opinion, and interrupted time series analysis to understand how a particular event influences online attitudes. A combination of these methods is used to attempt to estimate the strength of political polarity in the online environment. The study shows diverse media reports by election region and candidate, where the online public repeatedly reveals high negative and low positive attitudes towards each candidate. Moreover, political polarity can differ based on the level of interest in an election. Although voters pay less attention to a by-election than a presidential election, there is a solid political polarity in the online world. Hence, the research recommends preparing measures to alleviate the polarization as politics requires significant online participation.

What drives Malaysian online fashion shopping? The mediating role of perceived value

Salem Suha Fouad,Alanadoly Alshaimaa Bahgat 한국마케팅과학회 2022 Journal of Global Fashion Marketing Vol.13 No.1

This study investigates the indirect effects of consumer fashion involvement, opinion seeking and online buying experience on online purchasing behaviour of fashion products by adapting the functional perspective of the perceived values: quality and price. Partial least squares structural equation modelling (PLS-SEM) is used to examine the proposed study’s framework with data collected through a survey (n = 346) to examine respondents’ opinions on the mentioned variables. The authors also assessed the proposed framework using Importance-Performance Map Analysis (IPMA). The study results reveal that perceived quality mediates the relationship between fashion involvement, online shopping experience and online purchasing, which is not observed in opinion seeking. On the other hand, only perceived price mediates the relationship between opinion seeking, online shopping experience and online buying behaviour. At the construct level, IPMA revealed that perceived price and online shopping experience are crucial for enhancing online purchasing behaviour of fashion products. This study contributes to the existing literature by evaluating the effects of fashion involvement, opinion seeking and online experience on perceived value in terms of quality and price and how this may improve consumers’ online purchasing behaviour

온라인 공간에서 비정상 정보 유포 기법의 시간에 따른 변화 분석

이시형 한국인터넷정보학회 2020 인터넷정보학회논문지 Vol.21 No.3

Online communities, such as Internet portal sites and social media, have become popular since they allow users to share opinions and to obtain information anytime, anywhere. Accordingly, an increasing number of opinions are manipulated to the advantage of particular groups or individuals, and these opinions include falsified product reviews and political propaganda. Existing detection systems are built upon the characteristics of manipulated opinions for one particular time period. However, manipulation tactics change over time to evade detection systems and to more efficiently spread information, so detection systems should also evolve according to the changes. We therefore propose a system that helps observe and trace changes in manipulation tactics. This system classifies opinions into clusters that represent different tactics, and changes in these clusters reveal evolving tactics. We evaluated the system with over a million opinions collected during three election campaigns and found various changes in (i) the times when manipulations frequently occur, (ii) the methods to manipulate recommendation counts, and (iii) the use of multiple user IDs. We suggest that the operators of online communities perform regular audits with the proposed system to identify evolutions and to adjust detection systems. 인터넷 포털 사이트와 사회 관계망 서비스 등의 온라인 공간(online communities)은 시간과 공간의 제약 없이 접속 가능하다는 장점 때문에 많은 사용자들이 의견을 교환하고 정보를 얻기 위해 사용하고 있다. 이와 함께 특정 개인이나 집단의 이익을 위해 의도적으로 유포하는 비정상 정보도 증가하고 있는데 허위 상품 평이나 정치적 선동 의견이 이에 해당한다. 기존에는 이러한 비정상 정보탐지를 위해 한 시점에서의 비정상 정보를 수집하고 특징을 분석하여 검열 시스템을 제안하였다. 그러나 비정상 정보를 유포하는기법은 기존의 탐지 시스템을 회피하고 보다 효율적으로 정보를 전파하기 위해 지속적으로 변화하므로 탐지 시스템도 이에 맞추어변화할 필요가 있다. 따라서 본 논문에서는 비정상 정보 유포 기법의 시간에 따른 변화를 관찰하는 시스템을 제시한다. 이 시스템은클러스터링(clustering)을 활용해 비정상 정보를 유포 방식에 따라 군집(cluster)으로 분류하며 이러한 군집의 변화를 분석하여 유포 방식의 변화를 추적한다. 제안한 시스템을 검증하기 위해 3번의 선거 기간 전후에 포털 사이트에서 수집된 백만 개 이상의 의견을 대상으로 실험하였으며, 그 결과 비정상 정보 게재에 자주 사용되는 시간, 추천수 조작 방법, 다수의 ID 활용 방법 등에 대한 변화를 관찰할 수 있었다. 이 시스템을 주기적으로 사용해 탐지 시스템을 개선한다면 보다 빠르고 정확하게 비정상 정보의 유포를 탐지할 수있을 것이다.

온라인 뉴스 포털의 사용자 의견의 영향력과 법제화 과정에 대한 탐색적 연구; ‘윤창호법’ 제정 관련 비정형 빅데이터를 중심으로

백창원,노승국 한국경찰연구학회 2021 한국경찰연구 Vol.20 No.1

우리의 삶 속에서 법의 변화는 사회에서 일어나는 문제를 반영해왔다. 특히 사건 사 고에 대한 처벌을 다루고 있는 형법은 시대의 흐름 속에서 여론의 추이를 반영하며 변 화되어왔다. 이러한 여론 수렴의 장이 과거의 광장에서 점차 사이버 공간으로 이동하고 있다. 이에 본 연구는 온라인에서 생성된 사용자 의견이 어떻게 형법 법제화에 영향을 미치는지에 대한 메커니즘을 ‘윤창호법’ 제정과 관련된 비정형 빅데이터를 활용하여 추 적하였다. 탐색적 연구 결과 윤창호 사건 전반에 걸친 온라인 여론의 흐름의 변화와 함 께 입법·사법·행정 분야의 반응간의 연관성을 찾아볼 수 있었다. 앞으로 온라인에서 생 성된 여론이 형법은 물론 양형기준 변화 검토 시 중요한 고려 요소로 간주될 가능성이 있을 것으로 기대된다. The changes in the law in our lives have reflected the problems that arise in society. In particular, the criminal law, which deals with punishment for incidents, has changed, reflecting the trend of public opinion in the course of the times. This field of public opinion gathering is gradually shifting from past squares to cyberspace. Thus, this study tracked the mechanisms for how online generated user opinions affect criminal law legislation using unstructured big data related to the enactment of the "Yoon Chang-ho Act". As a result of the exploratory research, we found a link between the responses in the legislative, judicial, and administrative sectors along with changes in the flow of online public opinion throughout the Yoon Chang-ho case. In the future, it is expected that public opinion generated online will be considered an important consideration factor when reviewing criminal laws as well as changes in sentencing standards.