• Journal of the Korea Convergence Society
• /
• v.9 no.1
• /
• pp.419-431
• /
• 2018

In this paper, we propose a novel method for monitoring mood trend of Twitter users by analyzing their daily tweets for a long period. Then, to more accurately understand their tweets, we analyze all types of content in tweets, i.e., texts and emoticons, and images, thus develop a multimodal sentiment analysis method. In the proposed method, two single-modal analyses first are performed to extract the users' moods hidden in texts and images: a lexicon-based and learning-based text classifier and a learning-based image classifier. Thereafter, the extracted moods from the respective analyses are combined into a tweet mood and aggregated a daily mood. As a result, the proposed method generates a user daily mood flow graph, which allows us for monitoring the mood trend of users more intuitively. For evaluation, we perform two sets of experiment. First, we collect the data sets of 40,447 data. We evaluate our method via comparing the state-of-the-art techniques. In our experiments, we demonstrate that the proposed multimodal analysis method outperforms other baselines and our own methods using text-based tweets or images only. Furthermore, to evaluate the potential of the proposed method in monitoring users' mood trend, we tested the proposed method with 40 depressive users and 40 normal users. It proves that the proposed method can be effectively used in finding depressed users.

• Informatization Policy
• /
• v.23 no.3
• /
• pp.26-42
• /
• 2016

Recently, with the rapid growth of the O2O market, Fintech combining the finance and ICT technology is drawing attention as innovation to lead "O2O of finance", along with Fintech-based payment, authentication, security technology and related services. For new technology industries such as Fintech, technical sources, related systems and regulations are important but previous studies on Fintech lack in-depth research about systems and technological trends of the domestic Fintech industry. Therefore, this study aims to analyze domestic Fintech trends and find the insights for the direction of technology and systems of the future domestic Fintech industry by comparing Kakao Pay and Samsung Pay, the two domestic representative mobile payment services. By conducting a complete enumeration survey about the tweets mentioning Fintech until June 2016, this study visualized topics extraction, sensitivity analysis and keyword analyses. According to the analysis results, it was found that various topics have been created in the technologies and systems between 2014 and 2016 and different keywords and reactions were extracted between topics of Samsung Pay based on "devices" such as Galaxy and Kakao Pay based on "service" such as KakaoTalk. This study contributes to analyzing the unstructured data of social media by period by using social media mining and quantifying the expectations and reactions of consumers to services through the sentiment analysis. It is expected to be the foundation of Fintech industry development by presenting a strategic direction to Fintech related practitioners.

• Journal of Educational Research in Mathematics
• /
• v.23 no.4
• /
• pp.467-490
• /
• 2013

Correlation is a basic statistical concept which is necessary for understanding the relationship between two variables when they change values. In the middle school curriculum of Korea, only informal definition of correlation is taught with two-way data representations such as scatter plots and contingency tables. In this study, we investigated Korean high school students' understanding of correlation using a test consisting of 35 items about interpretation of scatter plot, contingency table, and text in realistic situation. 216 students from a high school in Seoul took the test for 20 minutes. From the results, we could observe the following: First, students did not have right criteria for determining the strength of correlation presented in scatter plots. Most of students could determine if there is correlation/no correlation and if the correlation is positive/negative by seeing the data presented in scatter plots. However, they did not judge by the closeness to the regression line but rather judged by the closeness between data points. Second, when statements about comparing the strength of correlation in the context of real life situation were given in text, the students had difficulty in understanding the distribution-related characteristic of the bi-variate data. Students had difficulty in figuring out the local distribution characteristic of data, which cannot be guessed merely based on the expression 'The correlation is strong' without statistical knowledge of correlation. Third, a large number of students could not judge the association between two variabels using conditional proportions when qualitative data are given in 2-by-2 tables. They made judgement by the absolute cell count and when the marginal sum of two categories are different for explanatory variable they thought the association could not be determined. From these results, we concluded that educational measures are required in order to remove such misconceptions and to improve understanding of correlation. Considering that the current mathematics curriculum does not cover the concept of correlation, we need to improve the curriculum as well.

• Journal of Information Management
• /
• v.37 no.4
• /
• pp.69-91
• /
• 2006

The purpose of this study is to improve the effectiveness and quality of web service by analyzing the web service problems and suggesting the solutions through the expert service quality evaluation from the point of view of users and website quality evaluation by measurement tools for a whole NDSL website. In case of website analysis, this study analyzed the website completeness of NDSL site and looked into the problem that users can judge by intuition during their use of the site, and evaluated the searchability and usability for web-based service quality evaluation by centering on the service quality of database quality items. After the results of this analysis, it appeared that there was not a big problem on the use. But after searching, several problems were found on loading rates, website completeness, user sensitiveness, the protection of private information, metadata completeness, website accessability, etc. And as a result of the evaluation of website service quality, it does not show the all satisfactory results in the function of search methods and search result printing, mark list and the items related to full-text in the part of searchability and usability. However, comparing with the results of other information organizations, it shows the similar level of quality.

• Informatization Policy
• /
• v.28 no.2
• /
• pp.34-56
• /
• 2021

According to the Fourth Industrial Revolution, demand for and interest in jobs in the field of AI and data science - such as artificial intelligence/data analysts - are increasing. In order to keep pace with this trend, and to supply human resources that can effectively perform such jobs in the relevant fields in a timely manner, job seekers must develop the competencies required by the companies, and universities must be in charge of training. However, it is difficult to devise appropriate response strategies at the level of job seekers, companies and universities, which are stakeholders in terms of supplying suitably competent personnel. Therefore, the purpose of this study is to determine which competencies are required in practice in order to cultivate and supply human talents equipped with the necessary job competencies, and to propose plans for the development of the required competencies at the university level. In order to identify the required competencies in the field of AI and data science, data on job postings on the LinkedIn site, the recruitment platform, were analyzed using text mining techniques. Then, research was conducted with the aim of devising and proposing concrete plans for competency development at the university level by comparing and verifying the results of the international graduate school curriculum in the field of AI and data science, and the interview results with the hiring managers, respectively, with the results of the topic model.

• Journal of the Korea Convergence Society
• /
• v.13 no.4
• /
• pp.359-372
• /
• 2022

This study aimed to derive a YouTube content strategy that can be exposed to Trending for a long time by comparing the features of 20 channels in the short/long term using 'YouTube Trending' data in 2021. First, through Pearson's correlation analysis, we found that various factors such as 'the number of title or tag letters' related to long-term exposure, and set this as an index to compare features. As a result, 1)'video title' of about 40-45 letters without excessive special characters, 2)'video length' within 10 minutes, 3)'Video description' is effective when writing 2-3 sentences and adding SNS information or including 3 key tags. Also, it would be more effective if you set key tag pairs such as (먹방, mukbang), (역대급, 레전드) derived through text mining. Through this, the channel will spread globally, bringing various advantages, and will be used as an indicator to evaluate the globality of the channel.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.7
• /
• pp.487-500
• /
• 2020

This research analyzed articles about the disability under the 「The Disabled Person Welfare Law」 in a major daily newspaper. A total of 7,684 articles on disability were collected from homepages of the three newspapers , , and . Through network text analysis and content analysis, we considered about "The perspective of Disability" based on "Multiple Disability Model". As a result of this research, when comparing individual models versus social models, individual models have a higher rate 64.31% than social models 35.69%. According to the newspapers, the major perception of Disability is a traditional individual model, which means disability must be solved by individuals. In addition, due to low social and institutional supports, the public's attention and consideration required for the disabled, socially weak people. This research implied that despite the changing times of looking at disability, three newspapers are still staying in the traditional paradigm. Therefore, It is required that viewing a disability from the perspective on disabled people, and a mature awareness that recognizes the diversity of individual needs. The significance of this study can be found in the fact that no attempt has been made to treat the disability perspectivec in newspaper articles as quantitative and qualitative data.

• Journal of Service Research and Studies
• /
• v.13 no.4
• /
• pp.191-205
• /
• 2023

Artificial Intelligence (AI), especially in the domain of text-generative services, has witnessed a significant surge, with forecasts indicating the AI-as-a-Service (AIaaS) market reaching a valuation of $55.0 Billion by 2028. This research set out to explore the quality dimensions characterizing synthetic text media software, with a focus on four key players in the industry: ChatGPT, Writesonic, Jasper, and Anyword. Drawing from a comprehensive dataset of over 4,000 reviews sourced from a software evaluation platform, the study employed the Latent Dirichlet Allocation (LDA) topic modeling technique using the Gensim library. This process resulted the data into 11 distinct topics. Subsequent analysis involved comparing these topics against established AI service quality dimensions, specifically AICSQ and AISAQUAL. Notably, the reviews predominantly emphasized dimensions like availability and efficiency, while others, such as anthropomorphism, which have been underscored in prior literature, were absent. This observation is attributed to the inherent nature of the reviews of AI services examined, which lean more towards semantic understanding rather than direct user interaction. The study acknowledges inherent limitations, mainly potential biases stemming from the singular review source and the specific nature of the reviewer demographic. Possible future research includes gauging the real-world implications of these quality dimensions on user satisfaction and to discuss deeper into how individual dimensions might impact overall ratings.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.347-373
• /
• 2023

As the significance of ESG (Environmental, Social, and Governance) management amplifies in driving sustainable growth, this study delves into and compares ESG trends and interrelationships from both corporate and societal viewpoints. Employing a combination of Latent Dirichlet Allocation Topic Modeling (LDA) and Semantic Network Analysis, we analyzed sustainability reports alongside corresponding social media datasets. Additionally, an in-depth examination of social media content was conducted using Joint Sentiment Topic Modeling (JST), further enriched by Semantic Network Analysis (SNA). Complementing text mining analysis with the assistance of ChatGPT, this study identified 25 different ESG topics. It highlighted differences between companies aiming to avoid risks and build trust, and the general public's diverse concerns like investment options and working conditions. Key terms like 'greenwashing,' 'serious accidents,' and 'boycotts' show that many people doubt how companies handle ESG issues. The findings from this study set the foundation for a plan that serves key ESG groups, including businesses, government agencies, customers, and investors. This study also provide to guide the creation of more trustworthy and effective ESG strategies, helping to direct the discussion on ESG effectiveness.

• Journal of KIISE
• /
• v.41 no.9
• /
• pp.728-743
• /
• 2014

Finger printing and sequence alignment are well-known approaches for document similarity comparison. A fingerprinting method is simple and fast, but it can not find particular similar regions. A string alignment method is used for identifying regions of similarity by arranging the sequences of a string. It has an advantage of finding particular similar regions, but it also has a disadvantage of taking more computing time. The Multi-Level Alignment (MLA) is a new method designed for taking the advantages of both methods. The MLA divides input documents into uniform length blocks, and then extracts fingerprints from each block and calculates similarity of block pairs by comparing the fingerprints. A similarity table is created in this process. Finally, sequence alignment is used for specifying longest similar regions in the similarity table. The MLA allows users to change block's size to control proportion of the fingerprint algorithm and the sequence alignment. As a document is divided into several blocks, similar regions are also fragmented into two or more blocks. To solve this fragmentation problem, we proposed a united block method. Experimentally, we show that computing document's similarity with the united block is more accurate than the original MLA method, with minor time loss.