• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.145-165
• /
• 2023

Recommendation system plays a significant role on relieving difficulties of selecting information among rapidly increasing amount of information caused by the development of the Internet and on efficiently displaying information that fits individual personal interest. In particular, without the help of recommendation system, E-commerce and OTT companies cannot overcome the long-tail phenomenon, a phenomenon in which only popular products are consumed, as the number of products and contents are rapidly increasing. Therefore, the research on recommendation systems is being actively conducted to overcome the phenomenon and to provide information or contents that are aligned with users' individual interests, in order to induce customers to consume various products or contents. Usually, collaborative filtering which utilizes users' historical behavioral data shows better performance than contents-based filtering which utilizes users' preferred contents. However, collaborative filtering can suffer from cold-start problem which occurs when there is lack of users' historical behavioral data. In this paper, hybrid music recommendation system, which can solve cold-start problem, is proposed based on the playlist data of Melon music streaming service that is given by Kakao Arena for music playlist continuation competition. The goal of this research is to use music tracks, that are included in the playlists, and metadata of music tracks and playlists in order to predict other music tracks when the half or whole of the tracks are masked. Therefore, two different recommendation procedures were conducted depending on the two different situations. When music tracks are included in the playlist, LightFM is used in order to utilize the music track list of the playlists and metadata of each music tracks. Then, the result of Item2Vec model, which uses vector embeddings of music tracks, tags and titles for recommendation, is combined with the result of LightFM model to create final recommendation list. When there are no music tracks available in the playlists but only playlists' tags and titles are available, recommendation was made by finding similar playlists based on playlists vectors which was made by the aggregation of FastText pre-trained embedding vectors of tags and titles of each playlists. As a result, not only cold-start problem can be resolved, but also achieved better performance than ALS, BPR and Item2Vec by using the metadata of both music tracks and playlists. In addition, it was found that the LightFM model, which uses only artist information as an item feature, shows the best performance compared to other LightFM models which use other item features of music tracks.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.287-316
• /
• 2023

As global energy crisis and the COVID-19 pandemic have emerged as social issues, there is a growing demand for companies to move away from profit-centric business models and embrace sustainable management that balances environmental, social, and governance (ESG) factors. ESG activities of companies vary across industries, and industry-specific weights are applied in ESG evaluations. Therefore, it is important to develop strategic management approaches that reflect the characteristics of each industry and the importance of each ESG factor. Additionally, with the stance of strengthened focus on ESG disclosures, specific guidelines are needed to identify and report on sustainable management activities of domestic companies. To understand corporate sustainability strategies, analyzing ESG reports and news articles by industry can help identify strategic characteristics in specific industries. However, each company has its own unique strategies and report structures, making it difficult to grasp detailed trends or action items. In our study, we analyzed ESG reports (2019-2021) and news articles (2019-2022) of six companies in the 'Finance,' 'Manufacturing,' and 'IT' sectors to examine the sustainability strategies of leading domestic ESG companies. Text mining techniques such as keyword frequency analysis and topic modeling were applied to identify industry-specific, ESG element-specific management strategies and issues. The analysis revealed that in the 'Finance' sector, customer-centric management strategies and efforts to promote an inclusive culture within and outside the company were prominent. Strategies addressing climate change, such as carbon neutrality and expanding green finance, were also emphasized. In the 'Manufacturing' sector, the focus was on creating sustainable communities through occupational health and safety issues, sustainable supply chain management, low-carbon technology development, and eco-friendly investments to achieve carbon neutrality. In the 'IT' sector, there was a tendency to focus on technological innovation and digital responsibility to enhance social value through technology. Furthermore, the key issues identified in the ESG factors were as follows: under the 'Environmental' element, issues such as greenhouse gas and carbon emission management, industry-specific eco-friendly activities, and green partnerships were identified. Under the 'Social' element, key issues included social contribution activities through stakeholder engagement, supporting the growth and coexistence of members and partner companies, and enhancing customer value through stable service provision. Under the 'Governance' element, key issues were identified as strengthening board independence through the appointment of outside directors, risk management and communication for sustainable growth, and establishing transparent governance structures. The exploration of the relationship between ESG disclosures in reports and ESG issues in news articles revealed that the sustainability strategies disclosed in reports were aligned with the issues related to ESG disclosed in news articles. However, there was a tendency to strengthen ESG activities for prevention and improvement after negative media coverage that could have a negative impact on corporate image. Additionally, environmental issues were mentioned more frequently in news articles compared to ESG reports, with environmental-related keywords being emphasized in the 'Finance' sector in the reports. Thus, ESG reports and news articles shared some similarities in content due to the sharing of information sources. However, the impact of media coverage influenced the emphasis on specific sustainability strategies, and the extent of mentioning environmental issues varied across documents. Based on our study, the following contributions were derived. From a practical perspective, companies need to consider their characteristics and establish sustainability strategies that align with their capabilities and situations. From an academic perspective, unlike previous studies on ESG strategies, we present a subdivided methodology through analysis considering the industry-specific characteristics of companies.

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.111-129
• /
• 2023

With the diffusion of digital innovation, the adoption of innovative medical technologies based on artificial intelligence is increasing in the medical field. This is driving the launch and adoption of AI-based SaMD(Software as a Medical Device), but there is a lack of research on the factors that influence the adoption of SaMD by medical institutions. The purpose of this study is to identify key factors that influence medical institutions' decisions to adopt AI-based SaMDs, and to analyze the weights and priorities of these factors. For this purpose, we conducted Delphi surveys based on the results of literature studies on technology acceptance models in healthcare industry, medical AI and SaMD, and developed a research model by combining HOTE(Human, Organization, Technology and Environment) framework and HABIO(Holistic Approach {Business, Information, Organizational}) framework. Based on the research model with 5 main criteria and 22 sub-criteria, we conducted an AHP(Analytical Hierarchy Process) analysis among the experts from domestic medical institutions and SaMD providers to empirically analyze SaMD adoption factors. The results of this study showed that the priority of the main criteria for determining the adoption of AI-based SaMD was in the order of technical factors, economic factors, human factors, organizational factors, and environmental factors. The priority of sub-criteria was in the order of reliability, cost reduction, medical staff's acceptance, safety, top management's support, security, and licensing & regulatory levels. Specifically, technical factors such as reliability, safety, and security were found to be the most important factors for SaMD adoption. In addition, the comparisons and analyses of the weights and priorities of each group showed that the weights and priorities of SaMD adoption factors varied by type of institution, type of medical institution, and type of job in the medical institution.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.7
• /
• pp.915-929
• /
• 2023

Improvements in people's quality of life, diversification of leisure activities, and changes in population structure have led to an increase in the demand for tourism and an expansion of the diversification of tourism activities. In particular, for coastal cities where land and marine tourism elements coexist, various factors influence their tourism demands. Tourism requires the construction of infrastructure and content development according to the demand at the tourist destination. This study aims to improve the prediction accuracy and explore influencing factors through time series analysis of tourism scale using agent-based data. Basic local governments in the Busan area were examined, and the data used were the number of tourists and the amount of tourism consumption on a monthly basis. The univariate time series analysis, which is a deterministic model, was used along with the SARIMAX analysis to identify the influencing factor. The tourism consumption propensity, focusing on the consumption amount according to business types and the amount of mentions on SNS, was set as the influencing factor. The difference in accuracy (RMSE standard) between the time series models that did and did not consider COVID-19 was found to be very wide, ranging from 1.8 times to 32.7 times by region. Additionally, considering the influencing factor, the tourism consumption business type and SNS trends were found to significantly impact the number of tourists and the amount of tourism consumption. Therefore, to predict future demand, external influences as well as the tourists' consumption tendencies and interests in terms of local tourism must be considered. This study aimed to predict future tourism demand in a coastal city such as Busan and identify factors affecting tourism scale, thereby contributing to policy decision-making to prepare tourism demand in consideration of government tourism policies and tourism trends.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.2
• /
• pp.35-52
• /
• 2023

Recently, as the non-face-to-face environment has developed due to COVID-19 and environmental pollution, the importance of online digital healthcare is increasing, and venture start-ups and activities such as health care, telemedicine, and digital treatments are also actively underway. This study conducted the impact on the acceptability of digital healthcare smartwatches with an integrated approach of the expanded integrated technology acceptance model (UTAUT2) and the behavioral inference model (BRT). The most advanced integrated technology acceptance model for innovative technology acceptance research was used to identify major factors such as utility expectations, social effects, convenience, price barriers, lack of alternatives, and behavioral intentions. For the study, about 410 responses from ordinary people in their teens to 60s across the country were collected, and based on this, the hypothesis was verified using structural equations after testing reliability and validity of the data. SPSS 23 and AMOS 23 were used for research analysis. Studies have shown that personal innovation has a significant impact on the reasons for acceptance (use value, social impact, convenience of use), attitude, and non-use (price barriers, lack of alternatives, and barriers to use). These results are the same as the results of previous studies that confirmed the influence of the main value of innovative ICT on user acceptance intention. In addition, the reason for acceptance had a significant effect on attitude, but the effect of the reason for non-acceptance was not significant. It can be analyzed that consumers are interested in new ICT products and new services, but purchase them more carefully and selectively. This study has evolved from the acceptance analysis of general-purpose consumer innovation technology to the acceptance analysis of consumer value in smartwatch digital healthcare, which is a new and important area in the future. Industrially, it can contribute to the product's purchase and marketing. It is hoped that this study will contribute to increasing research in the digital healthcare sector, which will play an important role in our lives in the future, and that it will develop into in-depth factors that are more suitable for consumer value through integrated approach models and integrated analysis of consumer acceptance and non-acceptance.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.4
• /
• pp.21-35
• /
• 2023

Expectations surrounding generative AI technology and its profound ramifications are sweeping across various industrial domains. Given the anticipated pivotal role of the startup ecosystem in the utilization and advancement of generative AI technology, it is imperative to cultivate a deeper comprehension of the present state and distinctive attributes characterizing venture capital (VC) investments within this domain. The current investigation delves into South Korea's landscape of VC investment deals and prognosticates the projected VC investments by juxtaposing these against the United States, the frontrunner in the generative AI industry and its associated ecosystem. For analytical purposes, a compilation of 286 investment deals originating from 117 U.S. generative AI startups spanning the period from 2008 to 2023, as well as 144 investment deals from 42 South Korean generative AI startups covering the years 2011 to 2023, was amassed to construct new datasets. The outcomes of this endeavor reveal an upward trajectory in the count of VC investment deals within both the U.S. and South Korea during recent years. Predominantly, these deals have been concentrated within the early-stage investment realm. Noteworthy disparities between the two nations have also come to light. Specifically, in the U.S., in contrast to South Korea, the quantum of recent VC deals has escalated, marking an augmentation ranging from 285% to 488% in the corresponding developmental stage. While the interval between disparate investment stages demonstrated a slight elongation in South Korea relative to the U.S., this discrepancy did not achieve statistical significance. Furthermore, the proportion of VC investments channeled into generative AI enterprises, relative to the aggregate number of deals, exhibited a higher quotient in South Korea compared to the U.S. Upon a comprehensive sectoral breakdown of generative AI, it was discerned that within the U.S., 59.2% of total deals were concentrated in the text and model sectors, whereas in South Korea, 61.9% of deals centered around the video, image, and chat sectors. Through forecasting, the anticipated VC investments in South Korea from 2023 to 2029 were derived via four distinct models, culminating in an estimated average requirement of 3.4 trillion Korean won (ranging from at least 2.408 trillion won to a maximum of 5.919 trillion won). This research bears pragmatic significance as it methodically dissects VC investments within the generative AI domain across both the U.S. and South Korea, culminating in the presentation of an estimated VC investment projection for the latter. Furthermore, its academic significance lies in laying the groundwork for prospective scholarly inquiries by dissecting the current landscape of generative AI VC investments, a sphere that has hitherto remained void of rigorous academic investigation supported by empirical data. Additionally, the study introduces two innovative methodologies for the prediction of VC investment sums. Upon broader integration, application, and refinement of these methodologies within diverse academic explorations, they stand poised to enhance the prognosticative capacity pertaining to VC investment costs.

• Information Systems Review
• /
• v.18 no.3
• /
• pp.209-233
• /
• 2016

Internet companies that utilize social network have increased in number. The introduction of diverse social media services facilitated innovative changes in e-business. Social network service (SNS), which is a domain of social media, is a web-based service designed to strengthen human relations in the Internet and build new social relations. The remarkable growth of social network services and the profit generation and perception of this service are the new growth engines of this digital age. Given this development, many global IT companies views SNS as the most powerful form of social media. Thus, they invest efforts to develop business models using SNS.2) This study verifies the impact of privacy exposure in SNS as a result of privacy invasion. This study examines the purpose of using the SNS and user's awareness of the significance of personal information, which are key factors that affect self-disclosure of personal information. This study utilizes theory of reasoned action (TRA) to provide a theoretical platform that describes the specific behavior and emotional response of individuals. This study presents a research model that considers negative attitude (negatude). In this model, self-disclosure in SNS is considered a TRA. TRA is a subjective norm, a behavioral intention, and a key variable of exposure behavior. A survey was conducted on college students at Y university in Seoul to empirically verify the research model. The students have experiences in using SNS. A total of 198 samples were collected. Path analysis was applied to analyze the relations of factors. The results of path analysis show the statistically insignificant impact of privacy invasion on negatude, subjective norm, behavioral intention, and exposure behavior. The impact of unrecognized privacy invasion was also considered insignificant. The impacts of intention to use SNS on negatude, subjective norm, behavioral intention, and exposure behavior was significant. A significant impact was also found for the significance of personal information on subjective norm, behavioral intention, and exposure behavior, whereas the impact on negatude was insignificant. The impact of subjective norm on behavioral intention was significant. Lastly, the impact of behavioral intention on exposure behavior was insignificant. These findings are significant because the study examined the process of self-disclosure by integrating psychological and social factors based on theoretical discussion.

• Information Systems Review
• /
• v.20 no.4
• /
• pp.1-23
• /
• 2018

A smart phone has been widely spread around world and makes people enjoy online shopping in any time and any place. Recently it also changes the distribution environment. O2O (Online-to-Offline) service becomes new normal due to its convenience of ease shopping of product and services. O2O service market shows steady and steep growth, It is reported that, however, 80% of the businesses has been discontinued within the first year because of unstable business models, customer dissatisfaction and distrust of service. Therefore, it is very important research issue to find out influential factors promoting continuous usage intention of O2O service. Previous study shows that it only considers online characteristics and lack of analysis about offline characteristics and social impact factors. The purpose of this paper is to find out continuous usage intention factors of O2O services by literature review, case analysis, and empirical test. A comprehensive research model and related hypothesis are developed and tested by using a structural equation, Survey was carried out among users who have used O2O service including payment service for at least once. Finally 611 samples are selected out of total 813 surveys. The result shows that the model is theoretically proved and 12 out of 17 hypotheses are accepted. The contribution of this paper is that it provides a new theoretical research model about continuous usage intention factors as well as practical guidelines about promoting continuous usage and growth strategies of O2O service.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.19 no.4
• /
• pp.127-139
• /
• 2024

This study investigates the impact of edutech characteristics and both tangible and intangible educational services on the intention to re-enroll, which is directly related to the management performance of private institutes. The study aims to propose strategies to improve re-enrollment intentions and management performance based on the findings. Private education has grown continuously, complementing the limitations of public education and increasing parental dependence. This study tested the hypothesis that edutech characteristics, intangible services, and tangible services, increasingly utilized with the development of information and communication technology, would influence re-enrollment intentions. It also examined whether rapport-building behavior with parents would have a moderating effect on this relationship. The hypothesis testing results showed that among the edutech characteristics, content, intangible services such as reliability and empathy, and tangible services such as tangibility and payment accessibility positively impacted re-enrollment intentions. The hypothesis that rapport-building behavior would moderate the relationship between educational services and re-enrollment intentions was supported for empathy in intangible services and tangibility in tangible services. Based on these findings, the study proposed three strategies to improve management performance of private institutes. First, in terms of improving and managing edutech characteristics, it suggested introducing and updating edutech content and ensuring operational stability. Second, for improving and managing intangible services, it recommended managing instructor recruitment and training to enhance quality and competence, maintaining professionalism through continuous education by credible institutions, and providing level-based education for students based on the qualitative improvement of educational programs. Third, to improve and manage tangible services, it suggested setting appropriate tuition fees, offering various payment methods (online, mobile, card, bank transfer) unrestricted by time and place, and equipping interiors and facilities that enable focused learning. Additionally, considering the moderating effect of rapport-building behavior, it emphasized that improvements and management requiring costs are necessary, but making parents feel a high level of tangibility through rapport-building is also important. Furthermore, given the increasing importance of edutech based on information and communication technology, the study highlighted the need for various support measures such as government technological support and venture certification system support for institutes with an entrepreneurial spirit aiming to introduce innovative technologies such as AI technology based on large language models and AR/VR-applied metaverse environments. This study is expected to help improve the management performance of private institutes by specifically suggesting items and methods for improvement and management in the educational field.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.59-83
• /
• 2018

With the increasing importance of sentiment analysis to grasp the needs of customers and the public, various types of deep learning models have been actively applied to English texts. In the sentiment analysis of English texts by deep learning, natural language sentences included in training and test datasets are usually converted into sequences of word vectors before being entered into the deep learning models. In this case, word vectors generally refer to vector representations of words obtained through splitting a sentence by space characters. There are several ways to derive word vectors, one of which is Word2Vec used for producing the 300 dimensional Google word vectors from about 100 billion words of Google News data. They have been widely used in the studies of sentiment analysis of reviews from various fields such as restaurants, movies, laptops, cameras, etc. Unlike English, morpheme plays an essential role in sentiment analysis and sentence structure analysis in Korean, which is a typical agglutinative language with developed postpositions and endings. A morpheme can be defined as the smallest meaningful unit of a language, and a word consists of one or more morphemes. For example, for a word '예쁘고', the morphemes are '예쁘(= adjective)' and '고(=connective ending)'. Reflecting the significance of Korean morphemes, it seems reasonable to adopt the morphemes as a basic unit in Korean sentiment analysis. Therefore, in this study, we use 'morpheme vector' as an input to a deep learning model rather than 'word vector' which is mainly used in English text. The morpheme vector refers to a vector representation for the morpheme and can be derived by applying an existent word vector derivation mechanism to the sentences divided into constituent morphemes. By the way, here come some questions as follows. What is the desirable range of POS(Part-Of-Speech) tags when deriving morpheme vectors for improving the classification accuracy of a deep learning model? Is it proper to apply a typical word vector model which primarily relies on the form of words to Korean with a high homonym ratio? Will the text preprocessing such as correcting spelling or spacing errors affect the classification accuracy, especially when drawing morpheme vectors from Korean product reviews with a lot of grammatical mistakes and variations? We seek to find empirical answers to these fundamental issues, which may be encountered first when applying various deep learning models to Korean texts. As a starting point, we summarized these issues as three central research questions as follows. First, which is better effective, to use morpheme vectors from grammatically correct texts of other domain than the analysis target, or to use morpheme vectors from considerably ungrammatical texts of the same domain, as the initial input of a deep learning model? Second, what is an appropriate morpheme vector derivation method for Korean regarding the range of POS tags, homonym, text preprocessing, minimum frequency? Third, can we get a satisfactory level of classification accuracy when applying deep learning to Korean sentiment analysis? As an approach to these research questions, we generate various types of morpheme vectors reflecting the research questions and then compare the classification accuracy through a non-static CNN(Convolutional Neural Network) model taking in the morpheme vectors. As for training and test datasets, Naver Shopping's 17,260 cosmetics product reviews are used. To derive morpheme vectors, we use data from the same domain as the target one and data from other domain; Naver shopping's about 2 million cosmetics product reviews and 520,000 Naver News data arguably corresponding to Google's News data. The six primary sets of morpheme vectors constructed in this study differ in terms of the following three criteria. First, they come from two types of data source; Naver news of high grammatical correctness and Naver shopping's cosmetics product reviews of low grammatical correctness. Second, they are distinguished in the degree of data preprocessing, namely, only splitting sentences or up to additional spelling and spacing corrections after sentence separation. Third, they vary concerning the form of input fed into a word vector model; whether the morphemes themselves are entered into a word vector model or with their POS tags attached. The morpheme vectors further vary depending on the consideration range of POS tags, the minimum frequency of morphemes included, and the random initialization range. All morpheme vectors are derived through CBOW(Continuous Bag-Of-Words) model with the context window 5 and the vector dimension 300. It seems that utilizing the same domain text even with a lower degree of grammatical correctness, performing spelling and spacing corrections as well as sentence splitting, and incorporating morphemes of any POS tags including incomprehensible category lead to the better classification accuracy. The POS tag attachment, which is devised for the high proportion of homonyms in Korean, and the minimum frequency standard for the morpheme to be included seem not to have any definite influence on the classification accuracy.