• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.470-472
• /
• 2022

최근 글로벌 OTT 서비스에서 한국드라마가 세계적 인기를 얻음에 따라 드라마 콘텐츠의 가치가 높아지고 있다. 드라마 대본은 드라마 제작에 있어서 핵심이 되는 데이터로, 특히 대사에는 인물의 특성이 잘 나타나 있다. 본 논문에서는 KoBERT 모델을 활용해 드라마 대사에서 인물의 특성 중 하나인 성별을 구분하고 실험 결과를 제시한다. KoBERT 모델로 대사의 성별을 분류한 뒤, 콘텐츠 분석과 인공지능 창작 측면에서의 활용 가능성에 대해 논의한다.

• Journal of the Korean Data Analysis Society
• /
• v.20 no.6
• /
• pp.3117-3126
• /
• 2018

The operating system update is a basic step to maintain a safe internet use environment. This study analyzed whether the implementation of the operating system update was related to gender and age group during the violation accident prevention act in relation to information protection on the internet, and tried to verify the validity of these factors by analyzing the influence of gender and age group. In this study, logistic regression analysis was conducted based on the information security survey data surveyed by the Korea Internet & Security Agency in 2016. As a result, gender and age were surveyed as factors related to the implementation of operating system updates. As a result of analyzing the impact on the implementation of operating system updates by gender, it is estimated that the odds are 0.419 times higher for women than for men. According to the analysis of the operating system update by age group based on the 50s, which is a vulnerable group of information, the result is that the odds are 13.266 times higher in the 20s than the 50s.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.13 no.6
• /
• pp.129-141
• /
• 2018

The purpose of this study is to identify the effects of entrepreneurship experience and education on entrepreneurship intention, and to test the moderating effect of gender on these relationships. To test the hypothesis, we used GETR(Global Entrepreneurship Trend Report) data that was collected by Korea Entrepreneurship Foundation and was consisted of 40,388 data collected from 2,000 people in 20 countries. First, entrepreneurship experience and entrepreneurship education have significant influence on entrepreneurship intention. Second, gender moderating effects on these relationships were found to have a significant effect on the relationship between entrepreneurship education and entrepreneurship intention. Specifically, the positive effect of entrepreneurship education on entrepreneurial intention was found to be stronger for women than for men. Finally, the analysis of the three-way interaction effect of the social protection confirmed that the positive relationship between entrepreneurial experience and entrepreneurial intention was stronger for women than for men, and this effect was found to be higher in the high social protection group. In other words, women with entrepreneurial experience are more likely to increase their entrepreneurial intentions when they are more aware of social protection than men.

• Journal of Advanced Navigation Technology
• /
• v.16 no.3
• /
• pp.536-544
• /
• 2012

Digital signage provides flight and airport information to the airport visitors and passengers. However, the digital signage has efficiency problem by displaying one type of advertisement to every customers regardless of their personality. We may solvel the inefficiency problem by using a smart digital signage which can recognize the characteristics of the customer We presents a smart digital signage with sex recognition function. The smart digital signage can recognize the sex of the customer to display the custom-made advertisement in realtime so that we can increase the satisfaction level of the airport passengers and visitors.

• Korean Journal of Social Welfare
• /
• v.60 no.4
• /
• pp.5-29
• /
• 2008

The purpose of this study is to investigate the effect of job characteristics of working poor on poverty status, focused on sex differences. The results are as follows. First, there are sex differences in career year, job position and industry for determining poverty entry. And second, career year, job regularity and occupy are different variables for men and women in determining poverty exit. This result says that job characteristics partially affects on poverty status of sex differently. Thus we need to sensitive policy that considers different experiences of men and women working poor as to poverty status mobility.

• The Journal of the Korea Contents Association
• /
• v.18 no.3
• /
• pp.235-245
• /
• 2018

The purpose of this study was to determine the gender differences in affecting factors of perceived stress level. The present study analyzed 2011 data of the Korea Community Health Survey and a total of 229,226 participants was included. To investigate the affecting factors of perceived stress, multiple logistic regression analyses were conducted. There were gender differences in affecting factors of perceived stress by education level, number of family members, household income, and self-care. This suggests that gender differences may exists between perceived stress level and health related quality of life. Further studies are necessary to investigate whether the cause of the gender differences in stress perception.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.59-66
• /
• 2022

This research conducted a study classifying gender of speakers by analyzing feature vectors extracted from the voice data. The study provides convenience in automatically recognizing gender of customers without manual classification process when they request any service via voice such as phone call. Furthermore, it is significant that this study can analyze frequently requested services for each gender after gender classification using a learning model and offer customized recommendation services according to the analysis. Based on the voice data of males and females excluding blank spaces, the study extracts feature vectors from each data using MFCC(Mel Frequency Cepstral Coefficient) and utilizes SVM(Support Vector Machine) models to conduct machine learning. As a result of gender classification of voice data using a learning model, the gender recognition rate was 94%.

• The Journal of Society for e-Business Studies
• /
• v.21 no.1
• /
• pp.65-77
• /
• 2016

As respecting one's privacy becomes an important issue in mobile device data analysis, on-device analysis is getting attention, in which the data analysis is conducted inside a mobile device without sending data from the device to outside. One possible application of the on-device analysis is gender prediction using text data in mobile devices, such as text messages, search keyword, website bookmarks, and contact, which are highly private, and the limited computing power of mobile devices can be addressed by utilizing the word comparison method, where words are selected beforehand and delivered to a mobile device of a user to determine the user's gender by matching mobile text data and the selected words. Moreover, it is known that performing prediction after filtering instances using definite evidences increases accuracy and reduces computational complexity. In this regard, we propose a two-phase approach to on-device gender prediction, where both discriminability and popularity of a word are sequentially considered. The proposed method performs predictions using a few highly discriminative words for all instances and popular words for unclassified instances from the previous prediction. From the experiments conducted on real-world dataset, the proposed method outperformed the compared methods.

• Journal of Korea Game Society
• /
• v.17 no.4
• /
• pp.91-100
• /
• 2017

A player character has a significant influence on immersion. In order to understand the consumers, it is necessary to compare age and gender of player characters, which is the most basic feature of the player character. We selected a prize winning work of 15 years of USA and japanese as research subjects(in RPG and Adventure), classified age and gender of player characters and analyzed the result. In the japanese games, the ratio of pre-set player characters was 94.3% for age and 88.6% for gender. In the USA games, It was the order of the pre-set character which did not specify the age and the customized type character. In this research, we would like to contribute guidelines for player character setting to successfully advance into the USA and Japanese game market.

• Korea journal of population studies
• /
• v.25 no.1
• /
• pp.181-211
• /
• 2002

Using the fourth data of the Korea Labor and Income Panel Study (KLIPS), this paper analyzed sexual differences in the promotion possibility and the promotion experience. Effects on wage of the promotion possibility and the promotion experience have been also discussed in detail. The promotion probability of a male worker in his current job is as high as twice than that of a female worker after controlling other independent variables. However, if we restrict the analysis to workers who either can be or was promoted, the sexual difference in the promotion possibility is greatly narrowed. This result suggests that the continuous career development without disruption is critical for the promotion of female workers. Analysing the sexual difference in wage using Oaxaca and Ransom's methodology, explanatory variables, such as human capital, residential area, etc., explained 69.5% of wage difference between male and female workers. Especially, 13.9% of wage difference was contributed to sexual differences in the promotion possibility and the promotion experience. This kind of empirical result emphasized once again the importance of promotion on wage.