• Journal of Multimedia Information System
• /
• v.1 no.1
• /
• pp.55-67
• /
• 2014

Image topic and emotion analysis is an important component of online image retrieval, which nowadays has become very popular in the widely growing social media community. However, due to the gaps between images and texts, there is very limited work in literature to detect one image's Topics and Emotions in a unified framework, although topics and emotions are two levels of semantics that often work together to comprehensively describe one image. In this work, a unified model, Joint Topic/Emotion Multi-Modal Hierarchical Latent Dirichlet Allocation (JTE-MMHLDA) model, which extends previous LDA, mmLDA, and JST model to capture topic and emotion information at the same time from heterogeneous data, is proposed. Specifically, a two level graphical structured model is built to realize sharing topics and emotions among the whole document collection. The experimental results on a Flickr dataset indicate that the proposed model efficiently discovers images' topics and emotions, and significantly outperform the text-only system by 4.4%, vision-only system by 18.1% in topic detection, and outperforms the text-only system by 7.1%, vision-only system by 39.7% in emotion detection.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.394-399
• /
• 2018

본 연구는 SNS 텍스트에서 형태소 분석기로 분석되지 않는 비정규토큰 유형 중 고빈도로 나타나는 의존명사 내포 어형의 형태소를 인식할 수 있는 LGG 기반 패턴문법 사전 구축과 그 성능을 평가하는 것을 목표로 한다. SNS 텍스트에서는 기존의 정형화된 텍스트와 달리, 띄어쓰기 오류로 인한 미분석어가 매우 높은 빈도로 나타나는데, 특히 의존명사를 포함한 유형이 20% 이상을 차지하며 가장 빈번한 것으로 나타났다. 이에 본 연구에서는 의존명사를 내포한 비정규토큰의 띄어쓰기 오류 문제를 효과적으로 처리하기 위해, 부분 문법 그래프(Local Grammar Graph: LGG) 프레임에 기반한 패턴문법 사전을 구축하였다. 이를 SNS 코퍼스에 적용하여 성능을 평가한 결과, 정확률 91.28%, 재현율 89%, 조화 평균 90.13%의 성능을 통해 본 연구의 접근 방법론의 유용성과 구축 자원의 실효성을 입증하였다.

• Journal of Educational Research in Mathematics
• /
• v.9 no.1
• /
• pp.321-332
• /
• 1999

This article made overtures of the relationship between interactive mathematics texts nd the prototype design of computer application with Computer Algebra System Math. Engine, linking together in the school mathematics. School teachers and researchers would try to construct mathematical materials with computers in educating students in the middle and high school grades. As the individual users come to manage hyper-media materials, so they meet with the problem of 'Who does control?'A mass user would be concerned with interactive mathematics materials directly or off-line at realtime and manipulate the process of problem-solving symbolically with MathView/sup 11)/ and ON-Math/sup 12)/. Discussion was made in developing the factor in the domestic situation and reaching out their hands for it. In conclusion, a user may reform the information of math-curriculum limitedly.

• The KIPS Transactions:PartA
• /
• v.13A no.6 s.103
• /
• pp.555-560
• /
• 2006

In contrast with the earlier remote education that simply recorded off-line classes, modern remote education emphasizes on offering additional functions that could maximize learning efficiency. Usage of such multimedia information as the texts, graphics, sounds, animations is considered fundamental element in offering the additional functions. This paper designs and implements an encoder/decoder that could accommodate the multimedia information with emphasis on demonstrating execution files. Instructors can demonstrate my type of execution files or application data files, and the remote learners can freely try running the corresponding execution files by themselves. Consequently, a high-level of learning efficiency can be achieved by the proposed encoder/decoder.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.43 no.2
• /
• pp.255-273
• /
• 2019

Perceptions of beauty change and are shared with others in the media of emotional words. In the modern age, a mix of traditional and modern make-up cultures has changed the standards of beauty. Therefore, an analysis using emotional words (an image that consumers have for certain subjects) and an image scale that intuitively shows them can be an important means for understanding changes in the "beauty of the time". This paper considered changes in typical aesthetic characteristics that women pursued through make-up by analyzing emotional words in white make-up powder advertisement texts from the 1920s through the 1930s. Imported modern technologies changed cosmetic manufacturing techniques and advertising methods to create a momentum that changed women's make-up culture from light to heavy make-up or from white to color make-up. Such changes have led to changes in the perception of beauty and were expressed through sensitive vocabularies such as pure, new, fresh, lofty, lively, healthy, and cheery. Such changes reflect social aspects such as women's aspirations for high status, pursuit of security, or women's roles under the wartime regime to show a change from beauty with an attribute of [+cool] to that of [+soft].

• International Journal of Knowledge Content Development & Technology
• /
• v.12 no.4
• /
• pp.41-65
• /
• 2022

This study would understand the overall perception of our society about public libraries, analyzing the texts related to public libraries, utilizing the semantic connection network & sentiment analysis. For this purpose, this study collected data from the last five years with keywords, 'Library' and 'Lifelong Learning Center' from January 1, 2016 through November 30, 2020 through the blogs and cafés of major domestic portal sites. With the collected data, text mining, centrality of keywords, network structure, structural equipotentiality, and sensitivity analyses were conducted. As a result of the analysis, First, 'reading' and 'book' were identified as representative keywords that form the social perception of public libraries. Second, it turned out that there were keywords related to the use of the library and the untact service due to the recent spread of COVID-19. Third, in seeking a plan for the development of public libraries through the keywords drawn to have positive meanings, it is necessary to create continuous services that can form a new image of the library, breaking away from the existing fixed role and image of the library and increase the convenience of use. Fourth, facilities and facilities for library services were recognized from a neutral point of view. Fifth, the spread of infectious diseases, social distancing, and temporary closure and closure of libraries are negatively related to public libraries, and awareness of librarians has been identified as negative keywords.

• Journal of Korean Academy of Nursing
• /
• v.53 no.4
• /
• pp.439-452
• /
• 2023

Purpose: This study aimed to derive considerations for the enactment of nursing law by analyzing the trends and social perceptions of nursing law mentioned in major daily newspapers, cafes, and blogs. Methods: Main texts and comments that included nursing law as a keyword were collected from major daily news and online postings from January 2021 to August 2022. The data collected through web crawling were analyzed using a TousFlux program used for big data analysis. Results: During the period of study, the awareness level around nursing law enactment increased. In particular, public concern over nursing law enactment intensified due to the two political parties' policy pledges related to nursing law in January 2022 and the failure to introduce the nursing law to the national assembly judiciary committee in May 2022. Except in December 2021, public perception of nursing law enactment was generally favorable, with public opinion tilting more in favor of than against enactment. Conclusion: Public opinion should be considered when drafting and implementing the nursing law to make it easier for the people to understand what the law constitutes. In addition, it is necessary to pay attention to and continuously promote the relationship between medical care and nursing in the nursing law system of developed nations. Lastly, nursing law enactment can enhance nurses' retention intention and provide a sense of efficacy to medical services.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.91-111
• /
• 2016

It is crucial for the social media based marketing practices to perform sentiment analyze the unstructured data written by the potential consumers of their products and services. In particular, when it comes to the companies which are interested in global business, the companies must collect and analyze the data from the social media of multinational settings (e.g. Youtube, Instagram, etc.). In this case, since the texts are multilingual, they usually translate the sentences into a certain target language before conducting sentiment analysis. However, due to the lack of cultural differences and highly qualified data dictionary, translated sentences suffer from misunderstanding the true meaning. These result in decreasing the quality of sentiment analysis. Hence, this study aims to propose a method to perform a multilingual sentiment analysis, focusing on Korean-Chinese cases, while avoiding language translations. To show the feasibility of the idea proposed in this paper, we compare the performance of the proposed method with those of the legacy methods which adopt language translators. The results suggest that our method outperforms in terms of RMSE, and can be applied by the global business institutions.

• Korean Journal of Community Nutrition
• /
• v.19 no.6
• /
• pp.550-557
• /
• 2014

Objectives: This study was conducted to examine the preferences and needs of typical Korean females adults for food and nutrition information provided by the mass media. Methods: A total of 343 females (77 in their 20s, 85 in their 30s, 88 in their 40s and 93 in their 50s) residing in the Seoul/Gyeonggido area was surveyed on general characteristics, main sources of food and nutrition information and needs for sources and contents of nutrition information. Results: The survey showed that typical Korean females obtained knowledge of food and nutrition mainly through the Internet (30.4%) and broadcasting (29.0%). Typical Korean females were interested in 'dietary management for weight control' (21.9%), 'the prevention and treatment of disease' (20.0%), 'food safety' (16.8%), 'proper dietary habits' (14.6%), 'cookery' (11.8%), 'functional foods' (9.6%), 'restaurant details' (3.5%) and 'life-cycle-specific dietary guideline' (1.6%). Needs for food and nutrition program forms on TV were 'educational programs' (34.3%), 'documentaries' (20.8), 'expert lecture-style' (13.0%), 'entertainment programs' (11.9%), 'expert conversation' (11.4%), 'news-style' (4.6%) and 'public campaign advertisements' (4.0%). On the Internet, 38.6% of the respondents preferred to get information provided by food and nutrition-related institutions (38.6%) while 26.1% preferred webtoons for nutritional information. The favored forms in mobile applications were 'monitoring their diets' (29.5%), 'data-based texts information' (21.4%), 'experts feedback' (20.6%), 'communities' (15.1%) and 'games' (13.1%). The rates of the preference to obtain information from experts such as nutritionists and dietitians and doctorsor dietitian turned reporters increased markedly with older ages. Conclusions: Since the mass media is a main source of food and nutrition information for the general public, the effectiveness and accuracy of the information provided should be enhanced by taking the needs of the public into account. The quality of information should be improved by involving more nutrition experts.

• Journal of Internet of Things and Convergence
• /
• v.8 no.2
• /
• pp.41-48
• /
• 2022

This study tried to empirically explore which issues related to the social service agency for public(as below SSA), that is, social perceptions were formed, by using mess media related to the SSA. This study is meaningful in that it identifies the overall social perception and trend of SSA through public opinion. In order to extract media trend data, the search used the big data analysis system, Textom, to collect data from the representative portals Naver News and Daum News. The collected texts were 1,299 in 2020 and 1,410 in 2021, for a total of 2,709. As a result of the analysis, first, the most derived words in relation to the frequency of text appearance were 'SSA', 'establishment', and 'operation'. Second, as a result of the N-gram analysis, the pairs of words directly related to the SSA 'SSA and public', 'SSA and opening', 'SSA and launch', and 'SSA and Department Director', 'SSA and Staff', 'SSA and Caregiver' etc. Third, in the results of TF-IDF analysis and word network analysis, similar to the word occurrence frequency and N-gram results, 'establishment', 'operation', 'public', 'launch', 'provided', 'opened', ' 'Holding' and 'Care' were derived. Based on the above analysis results, it was suggested to strengthen the emergency care support group, to commercialize it in detail, and to stabilize jobs.