http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Flor Gutierrez De la Cruz (검색결과 6 건)
- 무료
- 기관 내 무료
- 유료
-
Flor Gutierrez De la Cruz,김근형 한국인터넷전자상거래학회 2022 인터넷전자상거래연구 Vol.22 No.5
Newspaper articles are text data that record major issues or events that occur in the society we live in. Analyzing newspaper article text can derive interesting patterns of social phenomena. In this paper, topic modeling analysis was conducted by dividing the text of COVID-19-related newspaper articles by article writing period and newspaper type, and its meaning and implications were derived from a social and technical perspective. Texts of COVID-19-related articles were collected from Bigkinds, which provides news articles from various newspapers published in Korea, basic text analysis and major topics were extracted to examine major issues and countermeasures of COVID-19. The extracted topics were divided into the article writing period (2021 and 2022) and the newspaper type (national and local newspapers), and some implications were derived accordingly. First, the main topics of COVID-19-related news articles were 'political support', 'social response', 'corona quarantine', and 'overseas situation'. Second, the 'policy support' topic was widely covered in national newspapers in 2022 due to the influence of the 2022 presidential election. Third, it can be seen that local governments are more interested in support and consideration for the socially disadvantaged than the central government, and that they were also more active ahead of the presidential election. Fourth, the 'COVID-19 Quarantine' topic was more covered in local newspapers than in national newspapers. Fifth, from a technical point of view, it was expected that performing T-verification as a method of measuring the accuracy of the extracted topics could be a good technical method for optimizing topic modeling.
-
-
Tangerine Peel Research Trend Analysis Using Text Mining
강정운,김민철,Flor Gutierrez De la Cruz (사)한국조리학회 2022 한국조리학회지 Vol.28 No.9
This study was conducted through the analysis of data on tangerine peel for the industrialization in Jeju Special Self-Governing Province. This study confirmed the possibility of tangerine peel as a healthy functional food in daily life as people's interest in their own health increased. The purpose of this research is to analyze the keywords of tangerine peel through text mining, data analysis technology and to discuss the direction of Jeju’s tangerine peel industrialization. This study uses text mining to focus on 108 research provided by RISS and compares the differences in the keywords used throughout the articles by dividing them every 10 years from 1990 to 2022. As a result of this study, it can be expected that tangerine peel can be used as a health functional food due to the increasing research on health-related efficacy of the components of tangerine peel. In addition, since 2020, various studies have demonstrated the emergence of new keywords such as paint and coal, which suggests a new perspective of the purpose of the components of tangerine peel. The outcome of this study can be used as a reference for strategies in the industrialization of citrus peel in the future.
-
DATA SET SECURITY EFFECTS ON RECOMMENDATION SYSTEMS
Liaq Ridda,Flor Gutierrez De la Cruz 대한산업공학회 2023 대한산업공학회 춘계학술대회논문집 Vol.2023 No.5
Recommendation systems are trending nowadays, and with the vast deployment of these systems, data protection is required. This paper focuses on the security efforts in a recommendation system for a dataset. In some domains (e.g., the medical, or financial sector), data security and the impact of data manipulation on a system are more relevant than others. The work’s primary goal is to focus on data security effects on recommendation systems and how to protect our dataset from intruders if any data is changed. In this project, the data set was attacked by an intruder, which changed the dataset which was correctly, and as a result, the output that was predicted was wrong, and as an effect of that, the user failed to proceed and complete the task on time, and the project failed. We apply classification using a convolutional neural network (CNN) on two different datasets separately. We measure the effect of the data manipulation over these networks. We compare the result of a neural network trained on the original dataset with the one trained with the modified dataset. We consider a dataset containing ten different cases. We modify the dataset by changing the output values of one use case. Once the values are modified, we train a separate neural network based on this new dataset. The recommendation system was trained and tested on the modified data, and the results were wrongly calculated due to the data set differing from the original data set. When we apply a similar training and testing process on both Neural Networks, the modified dataset has incorrect results for 10 percent of the dataset.
-
DATA SET SECURITY EFFECTS ON RECOMMENDATION SYSTEMS
Liaq Ridda,Flor Gutierrez De la Cruz 한국경영과학회 2023 한국경영과학회 학술대회논문집 Vol.2023 No.5
Recommendation systems are trending nowadays, and with the vast deployment of these systems, data protection is required. This paper focuses on the security efforts in a recommendation system for a dataset. In some domains (e.g., the medical, or financial sector), data security and the impact of data manipulation on a system are more relevant than others. The work’s primary goal is to focus on data security effects on recommendation systems and how to protect our dataset from intruders if any data is changed. In this project, the data set was attacked by an intruder, which changed the dataset which was correctly, and as a result, the output that was predicted was wrong, and as an effect of that, the user failed to proceed and complete the task on time, and the project failed. We apply classification using a convolutional neural network (CNN) on two different datasets separately. We measure the effect of the data manipulation over these networks. We compare the result of a neural network trained on the original dataset with the one trained with the modified dataset. We consider a dataset containing ten different cases. We modify the dataset by changing the output values of one use case. Once the values are modified, we train a separate neural network based on this new dataset. The recommendation system was trained and tested on the modified data, and the results were wrongly calculated due to the data set differing from the original data set. When we apply a similar training and testing process on both Neural Networks, the modified dataset has incorrect results for 10 percent of the dataset.
-
KCI
DBpia연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
