• Human Ecology Research
• /
• v.59 no.1
• /
• pp.23-43
• /
• 2021

This study looked through the text mining analysis to check the status of the virtual assistant service, and explore the needs of consumers, and present consumer-oriented directions. Trendup 4.0 was used to analyze the keywords of AI services in Online News and social media from 2016 to 2020. The R program was used to collect consumer comment data and implement Topic Modeling analysis. According to the analysis, the number of mentions of AI services in mass media and social media has steadily increased. The Sentimental Analysis showed consumers were feeling positive about AI services in terms of useful and convenient functional and emotional aspects such as pleasure and interest. However, consumers were also experiencing complexity and difficulty with AI services and had concerns and fears about the use of AI services in the early stages of their introduction. The results of the consumer review analysis showed that there were topics(Technical Requirements) related to technology and the access process for the AI services to be provided, and topics (Consumer Request) expressed negative feelings about AI services, and topics(Consumer Life Support Area) about specific functions in the use of AI services. Text mining analysis enable this study to confirm consumer expectations or concerns about AI service, and to examine areas of service support that consumers experienced. The review data on each platform also revealed that the potential needs of consumers could be met by expanding the scope of support services and applying platform-specific strengths to provide differentiated services.

• The Research Journal of the Costume Culture
• /
• v.32 no.2
• /
• pp.215-231
• /
• 2024

The changing media landscape has diversified how and what is discussed about fashion. This study aims to examine expert discussions about fashion shows on social media from the perspective of fashion criticism. To achieve this goal objectively, a text mining program, Leximancer, was used. In total, 58 videos were collected from the panel discussion section of Showstudio from S/S 21 to S/S 24, and the results of text mining on 24,080 collected texts after refinement are detailed here. First, the researchers examined the frequency of keywords by season. This revealed that in 2021-2022, digital transformation, diversity, and fashion films are now commonly used to promote fashion collections, often replacing traditional catwalk shows. From 2023, sustainability and virtuality appeared more frequently, and fashion brands focused on storytelling to communicate seasonal concepts. In S/S 2024, the rise of luxury brand keywords and an increased focus on consumption has been evident. This suggests that it is influenced by social and cultural phenomena. Second, the overall keywords were analyzed and categorized into five concepts: formal descriptions and explanations of the collection's outfits, sociocultural evaluations of fashion shows and designers, assessments of the commerciality and sustainability of the current fashion industry, interpretations of fashion presentations, and discussions of the role of fashion shows in the future. The significance of this study lies in its identification of the specificity of contemporary fashion criticism and its objective approach to critical research.

• Journal of the Korean association of regional geographers
• /
• v.18 no.4
• /
• pp.445-463
• /
• 2012

This paper focuses on media literacy as a trial for reestablishing the relationship between media and geography education. So far, a geographical phenomenon represented through media has been treated as a transparent window on the world, but now needs to be recognized as a product of representation constructed socially by a range of subjects and their purposes. The epistemological turn of media has brought interest on social construction and media literacy in terms of teaching and learning. It is required that teaching and learning geography through media should be turned from the existing massmedia in education(or the education using media) to the education for fostering an active media literacy to analyze and reason critically how the media as text is constructed and selected. This geography education as media literacy is very important because it enables students to reveal the ideology and power relation embedded in the media as text, as well as to stimulate and enrich their geography imagination through an active work.

• Korean Medical Education Review
• /
• v.19 no.3
• /
• pp.158-168
• /
• 2017

There is a more urgent call for educational methods of machine learning in medical education, and therefore, new approaches of teaching and researching machine learning in medicine are needed. This paper presents a case using machine learning through text analysis. Topic modeling of news articles with the keyword 'asbestos' were examined. Two hypotheses were tested using this method, and the process of machine learning of texts is illustrated through this example. Using an automated text analysis method, all the news articles published from January 1, 1990 to November 15, 2016 in South Korea which included 'asbestos' in the title and the body were collected by web scraping. Differences in topics were analyzed by structured topic modelling (STM) and compared by press companies and periods. More articles were found in liberal media outlets. Differences were found in the number and types of topics in the articles according to the partisanship and period. STM showed that the conservative press views asbestos as a personal problem, while the progressive press views asbestos as a social problem. A divergence in the perspective for emphasizing the issues of asbestos between the conservative press and progressive press was also found. Social perspective influences the main topics of news stories. Thus, the patients' uneasiness and pain are not presented by both sources of media. In addition, topics differ between news media sources based on partisanship, and therefore cause divergence in readers' framing. The method of text analysis and its strengths and weaknesses are explained, and an application for the teaching and researching of machine learning in medical education using the methodology of text analysis is considered. An educational method of machine learning in medical education is urgent for future generations.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.63-69
• /
• 2021

When a person sees a sentence and understands the sentence, the person understands the sentence by reminiscent of the main word in the sentence as an image. Text-to-image is what allows computers to do this associative process. The previous deep learning-based text-to-image model extracts text features using Convolutional Neural Network (CNN)-Long Short Term Memory (LSTM) and bi-directional LSTM, and generates an image by inputting it to the GAN. The previous text-to-image model uses basic embedding in text feature extraction, and it takes a long time to train because images are generated using several modules. Therefore, in this research, we propose a method of extracting features by using the attention mechanism, which has improved performance in the natural language processing field, for sentence embedding, and generating an image by inputting the extracted features into the GAN. As a result of the experiment, the inception score was higher than that of the model used in the previous study, and when judged with the naked eye, an image that expresses the features well in the input sentence was created. In addition, even when a long sentence is input, an image that expresses the sentence well was created.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.3
• /
• pp.531-541
• /
• 2018

This study researched text mining and text network analysis to analyze the images of Nonghyup Insurance for consumers. With the recent development of social media, many texts are being produced and reproduced, and texts of social media provide important information to companies. Text mining and text network analysis are used in many studies to identify image of company and product. As a result of the text analysis, the positive image of the Nonghyup Insurance is safety and stability. Negative images of the Nonghyup Insurance is concern and anxiety. As a result of the textual network analysis, Centered mage of Nonghyup Insurance is safety and concern. This paper allows researchers to extract several lessons learned that are important for the text mining and text network analysis.

• Smart Media Journal
• /
• v.2 no.2
• /
• pp.14-19
• /
• 2013

Recently, due to the increase of the use of scanned images, the text segmentation techniques, which play critical role to optimize the quality of the scanned images, are required to be updated and advanced. In this study, an algorithm has been developed based on the modification of Gaussian mixture model (GMM) by integrating the calculation of Gaussian detection gradient and the estimation of the number clusters. The experimental results show an efficient method for text segmentation in natural scenes such as storefronts, street signs, scanned journals and newspapers at different size, shape or color of texts in condition of lighting changes and complex background. These indicate that our model algorithm and research approach can address various issues, which are still limitations of other senior algorithms and methods.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.21 no.1
• /
• pp.86-93
• /
• 2018

Since media articles, which have a great influence on public opinion, are transmitted to the public through various media, it is very difficult to analyze them manually. There are many discussions on methods that can collect, process, and analyze documents in the academia, but this is mostly done in the areas related to politics and stocks, and national-defense articles are poorly researched. In this study, we will explain how to build an automatic analysis system of national defense articles that can collect information on defense articles automatically, and can process information quickly by using topic modeling with LDA, emotional analysis, and extraction-based text summarization.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.9-15
• /
• 2024

Tree-based algorithms have been the dominant methods used build a prediction model for tabular data. This also includes personal credit data. However, they are limited to compatibility with categorical and numerical data only, and also do not capture information of the relationship between other features. In this work, we proposed an ensemble model using the Transformer architecture that includes text features and harness the self-attention mechanism to tackle the feature relationships limitation. We describe a text formatter module, that converts the original tabular data into sentence data that is fed into FinBERT along with other text features. Furthermore, we employed FT-Transformer that train with the original tabular data. We evaluate this multi-modal approach with two popular tree-based algorithms known as, Random Forest and Extreme Gradient Boosting, XGBoost and TabTransformer. Our proposed method shows superior Default Recall, F1 score and AUC results across two public data sets. Our results are significant for financial institutions to reduce the risk of financial loss regarding defaulters.

• Journal of Korea Multimedia Society
• /
• v.9 no.9
• /
• pp.1196-1207
• /
• 2006

In this paper, study on organization factors and algorithm of semiotics in Animation text within Roland Gerard Barthes's Structurism semiotics theory. It is possible through this approach that we can analyse the effective mechanism which delivers messages(or text) of animation, instead of plain analysis of classical semiotics. and then It will be able to keep watch on the blind viewpoint of the pure aesthetics which does not consider a social duty. In the expression of single sentence by the view of Barthes's semiotics theory, the text of animation is 'one sign has duplex role'. when it is explained another, the animation of mass media is special processing that makes conception and significance. in other words, the order of domination likely natural rule assimilate mass people to itself by the animation of mass media