Earticle

Despite advances in Natural Language Processing (NLP) and Large Language Models (LLMs), developing a CBT chatbot that provides emotional support and fosters continuous engagement remains a challenging task. To address this, we proposed SupportlyChat, which is a fine-tuned LLaMA with a custom dataset and provides emotion analysis visualization. We curated the custom dataset by integrating mental health conversation dataset and HappyDB dataset which collects people’s happy moments. We conducted a user study with 10 participants using conditions including standard chatbot responses, emotion analysis reports with standard responses, and emotion analysis reports with empathetic responses. The findings indicate that participants found empathetic responses helpful in shifting towards positive thinking with our proposed method. Additionally, they preferred emotional visualization for its ability to enhance professionalism and recognize inherent emotions. Based on these findings, we suggest utilizing empathetic responses in psychological counseling to emotionally support clients and using emotion analysis reports to promote continuous engagement.

We look at the business model development of a fan community platform ‘Weverse’ from two-sided platform (TSP) to multi-sided platform (MSP) and investigate its platform business model. From the Rocket Model’s theoretical perspective, the results reveal that Weverse firstly focuses on inviting artists as many as possible starting from BTS, then attracts new artists’ fans naturally. For success of this TSP, it forms MSP, ‘Weverse Shop’ to meet two sides’ relevant needs timely and filtered. In third stage of connection, various partnerships are attempted in terms of open platform strategies. For instance, by combining ‘VLive’ and Weverse, Naver’s fan platform business is transferred to Weverse. For core transaction through direct and indirect monetization, several cobranding activities are tried. Lastly, regarding optimization, newly born Weverse being launched in the first half of 2022 is supposed to create further synergies with Naver’s R&D capabilities in data, AI, and other technologies like metaverse platform ‘ZEPETO’ which already sells clothing items of Weverse artists.

The more precisely an AI system collects and analyzes user information, the more effectively it can tailor future recommendations for each user. However, gathering comprehensive information for individual users remains a significant challenge because they may have concerns about privacy or find the process bothersome. To encourage users to willingly provide diverse and meaningful personal information, we applied two widely discussed concepts in psychology and economics to conversational agents: Self-Disclosure and Utility Theory. Our study revealed that while both conversational strategies influenced user experience, the Utility Theory strategy, when combined with questions targeting opinions and emotions, enhanced users’ willingness to disclose personal information and improved their overall disclosure experience. These results highlight the importance of tailoring conversational strategies to information types to encourage self-disclosure effectively. Based on these findings, we propose design considerations for efficiently gathering user information through conversation.

Genshin Impact is an open-world action role-playing game launched by miHoYo in 2020 and has been released on multiple platforms. Due to the excellent character design, it has received widespread attention once it was released, and it has been ranked in the top 10 best-selling lists in several countries after a few weeks of launch. This article will first analyze the map design of the game's open world, and what elements are used on the game map to allow players to immerse themselves in it. Then, in the gameplay of the game, a rich and varied combat system is formed by using the relationship between the elements to restrain each other.There is also a card drawing system added to it, which makes the acquisition of characters full of randomness and allows more players to participate in it. It is concluded that the novel design and rich and varied play methods have made the game Genshin Impact high in popularity, occupying the forefront of the app download list for a long time.

The rapid advancement of generative AI technologies is transforming the field of package design, enabling the quick creation of diverse design options. This study aims to develop a systematic prompt engineering methodology for the effective utilization of generative AI in package design. The research focuses on key design elements, including form, color, typography, and material, with the goal of deriving optimized prompt patterns. By applying the derived prompt patterns to real-world package design projects, the study evaluates their effectiveness and identifies areas for improvement. The research methodology also involves a literature review and case studies to establish a theoretical foundation and explore effective prompt patterns. The study presents a framework for translating traditional packaging design principles into AI-readable prompts, demonstrating the potential of prompt engineering as a bridge between human creativity and AI capabilities. This research advances the integration of generative AI into the design field, broadening its applicability and enhancing overall efficiency. The study acknowledges its limitations and highlights the need for future research to refine prompts and expand the framework to address the evolving needs of the packaging industry.

With the rise of short-form content and the growing integration of generative AI (Artificial Intelligence Generated Content, AIGC) technologies in drama production, this study extends the AI Device Use Acceptance (AIDUA) model to examine the factors influencing acceptance and rejection of AIGC dramas based on Chinese traditional mythology. Drawing on survey data from 528 Chinese viewers and employing structural equation modeling, the study identifies six key factors—social influence, hedonic motivation, perceived anthropomorphism, artistic quality, novelty, and cultural traditionality—as significant predictors of performance expectancy. Emotional responses, shaped by performance expectancy, were found to differentially influence acceptance and rejection intentions. The findings underscore the importance of emotional appraisal in user responses to AIGC content and provide empirical insights for the digital transformation of traditional intellectual property (IP) and the strategic planning of culturally resonant AIgenerated content.

We propose SQLGo, an interactive learning tool designed to help learne.rs intuitively understand the execution flow of SQL queries. SQLGo combines Common Table Expression based visualization techniques with a Large Language Model (LLM)-powered conversational interface to clearly convey intermediate operations and procedural semantics embedded in SQL.Most existing SQL learning tools provide only tabular query results, failing to adequately explain the intermediate states and execution process of a query. As a result, learners often struggle to grasp the actual execution flow underlying SQL’s declarative structure. SQLGo addresses these limitations by offering an interactive environment that supports procedural reasoning and encourages active learner engagement, thereby enabling more effective SQL learning.Through this system, learners are expected to intuitively grasp the execution flow of queries and gain a deeper and more meaningful learning experience compared to conventional tools.

We compare Over-the-Tops (OTTs), Netflix and Amazon Prime Video (APV) with five success factors of innovation. Firstly, Netflix offers better personalized service than APV, because APV has collaborative filtering algorithms to recommend safe bets, not the customers really want. Secondly, APV’ user interface is undercooked to lock the members in, even if it has more content and better price offer than Netflix retaining its loyal customers despite the price increase. Thirdly, Netflix has simple subscription model with three tiering, but APV has complicated pricing model having annual and monthly, APV and Prime Video (AV) app, Amazon subscription and extra payment of Amazon Prime Channels (APCs). Fourthly, Amazon has fewer partnership than Netflix especially when it comes to local TV series. Instead, Amazon has live TV channel collaboration including sports content. Lastly, both have strategic and operational agility in their organization well.

Recently, there has been an increasing trend in the role of social media in tourism marketing. We analyze changes in tourism marketing trends using tourism marketing keywords through social media networks. The aim is to understand marketing trends based on the analyzed data and effectively create, maintain, and manage customers, as well as efficiently supply tourism products. Data was collected using web data from platforms such as Naver, Google, and Daum through TexTom. The data collection period was set for one year, from December 1, 2022, to December 1, 2023. The collected data, after undergoing refinement, was analyzed as keyword networks based on frequency analysis results. Network visualization and CONCOR analysis were conducted using the Ucinet program. The top words in frequency were 'tourists,' 'promotion,' 'travel,' and 'research.' Clusters were categorized into four: tourism field, tourism products, marketing, and motivation for visits. Through this, it was confirmed that tourism marketing is being conducted in various tourism sectors such as MICE, medical tourism, and conventions. Utilizing digital marketing via online platforms, tourism products are promoted to tourists, and unique tourism products are developed to increase city branding and tourism demand through integrated tourism content. We identify trends in tourism marketing, providing tourists with a positive image and contributing to the activation of local tourism.

This study explores the impact of grade level and cultural contexts on AI perception among Korean and Chinese university students, focusing on the field of design education. The design field was chosen as it represents an intersection of technological innovation and practical application, making it an ideal context for analyzing human-AI interaction. A survey of 250 students (125 from each country) assessed AI knowledge, AI perception, AI-human role collaboration, and AI learning experiences. The results showed that Korean students scored higher in AI knowledge and perception, while Chinese students excelled in AI learning experiences. Academic progression was found to have a significant influence on AI perception, revealing common patterns that transcend national contexts. However, the interaction effects between nationality and academic progression were not statistically significant, suggesting that academic development impacts students in both countries similarly. This study not only examines differences between nations but also uncovers universal trends across academic levels, emphasizing the importance of designing AI education strategies that account for cultural differences while fostering universal competencies through practical experience and knowledge accumulation.