Earticle

A story generation task is to develop a system that can continuously generate natural, consistent, and coherent stories for consecutive scenes. Recently transformer-based language models have shown considerable results at the sentence-level generation for learning human-writing ability. However, it is very crucial to understand the way of developing the story using a combination of various contents. Recent works have mainly focused on human-guided AI story generation methods in which humans as guidance determine the next storyline, and the system creates a story that reflects the storyline well. This study focuses on the way of replacing the human role with the AI-based model. Based on this, this study deals with the methodology for creating a long story spanning multiple scenes rather than creating a story at the level of one scene. In this regard, we propose a novel AI-guided story generation framework with automatic storyline generator. It is a pipeline structure consisting of two modules such as a storyline generator and a story generator, which enables the continuous creation of coherent stories. Particularly, we transform the storyline generation problem into a multiple-choice QA problem to predict the next storyline. This study shows the possibility of generating continuous stories for multiple scenes without any human intervention.

This study aimed to explore the impact of AI image generators on the affective factors of college-level English learners and the correlations among these factors. During a four-week instructional period, 65 participants were asked to use Midjourney as an AI tool for their user experiences. Affective factors including interest, confidence, and participation were measured through pre- and post-surveys. Using Jamovi for analysis, significant improvements were discovered across all affective factors. Noteworthy improvements occurred in confidence, indicating a favorable impact by AI-generated images on English learning. Additionally, correlation analysis demonstrated significant positive relationships between interest and confidence, as well as confidence and participation. This confirms the interconnected nature of these affective elements in the learning process. The findings suggest that the educational use of image-generating AI tools can beneficially influence English learners’ affective domains. The study calls for further investigation into the pedagogical applications of image AI to foster a more interactive, engaged, and self-assured attitude towards language learning.

본 연구는 AI 음악 생성기 사운드로우(Soundraw)를 활용한 8차시의 음악 창작 수업이 학생들에게 미치는 효과를 살펴보고, AI 음악 생성기의 효과적인 활용 방안을 모색하였다. 연구 방법은 질적 연구 중 근거이론 방법으로 자료 수집과 개념 추출 및 범주화 과정을 거쳐 구조화하는 코딩의 과정을 택해 연구를 수행하였다. 분석 결과 AI 음악 생성기를 활용한 음악 창작 수업은 학생들에게 다음과 같은 긍정적인 영향이 있음을 확인할 수 있었다. 첫째, 학생들의 내면과 정서적인 부분뿐만 아니라 생활 전반에 걸쳐 영향을 미치고 있음을 확인할 수 있었다. 특히 학생들의 음악 학습에 대한 관심과 흥미가 향상되었다. 둘째, 학생들의 창의성 신장, 자기효능감 확대, AI 도구에 대한 긍정적 인식을 확장 시킬 수 있음을 확인하였다. 셋째, 음악 창작 수업에 AI 음악 도구를 활용함으로써 급변하는 AI 환경에 학생들이 자신감을 가지고 주도적으로 참여할 수 있는 능력을 길러줄 수 있음을 확인하였다. 본 연구를 통해 AI 도구 활용 수업의 확대와 교사 연구 및 교육인프라 강화 및 AI 윤리교육과 저작권교육이 필요함을 제언한다.

This study examined the effects of an eight-period music composition class utilizing the AI music generator Soundraw on students and explored effective ways to utilize AI music generators. The research method employed a grounded theory approach within qualitative research, employing data collection, concept extraction, categorization, and structured coding. The analysis revealed that music composition classes utilizing the AI music generator had the following positive effects on students. First, the program impacted not only students' inner and emotional well-being but also their overall lives. Specifically, it enhanced students' interest and enthusiasm for music learning. Second, it fostered students' creativity, self-efficacy, and positive perceptions of AI tools. Third, the use of AI music tools in music composition classes fostered students' ability to confidently and proactively participate in the rapidly changing AI environment. This study suggests the need to expand the use of AI tools in classes, strengthen teacher research and educational infrastructure, and provide education on AI ethics and copyright.

In three-dimensional(3D) modeling, texturing plays a crucial role as a visual element, imparting detail and realism to models. In contrast to traditional texturing methods, the current trend involves utilizing AI tools such as Leonardo.Ai and Meshy to create textures for 3D models in a more efficient and precise manner. This paper focuses on 3D texturing, conducting a comprehensive comparative study of AI tools, specifically Leonardo.Ai and Meshy. By delving into the performance, functional differences, and respective application scopes of these two tools in the generation of 3D textures, we highlight potential applications and development trends within the realm of 3D texturing. The efficient use of AI tools in texture creation also has the potential to drive innovation and enhancement in the field of 3D modeling. In conclusion, this research aims to provide a comprehensive perspective for researchers, practitioners, and enthusiasts in related fields, fostering further innovation and development in this domain.

AI는 사용자의 프롬프트를 해석하여 데이터를 서베이하고 산출물을 생성한다. 사용자는 프롬프트에 자연어를 양방향 대화의 형식으로 입력하는데, AI에게 정확한 의사를 전달하기 위한 방법론이 프롬프트 엔지니어링이다. H대 학교 전공 교과목 수업 중 주얼리 제작 아이데이션 시 생성형 AI를 활용하였고, 훈련 평가 과정에서 프롬프트 관련 연구의 필요성이 관찰되었다. 본 연구로 도출된 프롬프트 방법론으로 산출물 편차를 줄이고, 상향 평준화를 통해 주 얼리 제작 아이데이션을 위한 프롬프트 역량을 강화하고자 한다. 선행 연구를 통한 프롬프트 엔지니어링 적용 결과, 프롬프트의 고도화와 AI 산출물의 완성도는 양의 상관관계가 있음을 확인하였다. 본 연구를 통해 프롬프팅에 대한 근본적 원리를 익히고, AI 활용에 대한 도움이 되기를 바란다.

AI interprets user prompts, surveys data, and generates output. Users input natural language into the prompt in the form of a two-way conversation, and the methodology for conveying accurate intentions to AI is called prompt engineering. Generative AI was used during jewelry production ideation during a major course at H University, and the need for prompt-related research was observed during the training evaluation process. Using the prompt methodology derived from this study, we aim to reduce deviations in output and strengthen prompt capabilities for jewelry production ideas through upward standardization. As a result of applying prompting engineering through previous research, it was confirmed that there is a positive correlation between the advancement of prompts and the completeness of AI output. In the future, through this study, we hope to learn the fundamental principles of prompting and to be helpful in utilizing AI.

This research explores texts created by the AI text generator. Since artificial intelligence (AI) technologies were highly advanced, the world has had AI text generators programmed to generate unlimited writings. In this study, the texts provided by one public AI text generator, Talk to Transformer are investigated through two-way analysis approaches. First, 50 texts made by Talk to Transformer are structurally and textually analyzed, and second, the prospective users’ perspectives of the AI-written texts will be discussed through two survey experiments, involving two different groups (the native-like English speaking student group and the native professional group). The results show that there are few correlations in selections between human- or AI-written texts, but there are more negative evaluation remarks on the AI texts, such as “machine-like writings”, “sources from the Internet”, “all mimics from human writings”, etc. Such negative perspectives of the readers derive the doubtfulness and hesitation of using AI-written texts, especially in teaching environments.

This study aims to highlight the importance of designing future-oriented English learning environments and content. By examining the experiences of pre-service English teachers and utilizing text-to-image AI generators, the study identifies key themes essential for the innovation. These themes include the creation of classroom environments that allow direct knowledge experience, the integration of VR and AI-integrated immersive textbooks, and the use of hologram-based textbooks for experiential learning. The findings emphasize the necessity of flexible and advanced educational resources that enhance student engagement, comprehension, and practical application of knowledge. The implications for educational practice include the need for dynamic classroom design, the integration of advanced technologies, and the evolving role of teachers as facilitators in technologically-enhanced learning environments. Additionally, the study suggests that future research should focus on longitudinal studies, diverse educational contexts, and the potential of AI in educational resource development. This study underscores the importance of embracing technological advancements to transform English education, making it more engaging and effective, and better aligned with the demands of the future-oriented educational context.

최근 인공지능 기술은 산업전반에 걸쳐서 활용되고 있다. 현재 예술 창작도구는 NFT 산업에서 사용되고 있으며, 이를 활용한 작품이 전시, 판매되기도 하였다. 미술 분야의 창작도구는 Gerated Photos, Google Deep Dream, Skech-RNN, Auto draw가 있으며, 음악분야의 인공지능 창작도구는 Beat Blender, Google Doodle Bach, AIVA, Duet, Neural Synth 등이 있다. 인공지능 예술 창작도구의 특징은 다음과 같다. 첫째, 예술분야 인공지능 창작도구는 기존의 작품 데이터를 바탕으로 새로운 작품을 창작하는 데에 활용되고 있다. 둘째, 창작 결과물을 빠르고 신속하게 도출하여 창작자에게 아이디어를 제공하거나, 창작 재료를 다양하게 구현해 볼 수 있다. 향후 인공지능 창작물은 인공지능 기술이 미술, 영상, 문학, 음악 등 콘텐츠 기획 및 제작에 많은 영향을 끼칠 것이다.

Recently, artificial intelligence technology is being used throughout the industry. Currently, Currently, AI art generators are used in the NFT industry, and works using them have been exhibited and sold. AI art generators in the art field include Gated Photos, Google Deep Dream, Sketch-RNN, and Auto Draw. AI art generators in the music field are Beat Blender, Google Doodle Bach, AIVA, Duet, and Neural Synth. The characteristics of AI art generators are as follows. First, AI art generator in the art field are being used to create new works based on existing work data. Second, it is possible to quickly and quickly derive creative results to provide ideas to creators, or to implement various creative materials. In the future, AI art generators are expected to have a great influence on content planning and production such as visual art, music composition, literature, and movie.

본 연구의 목적은 EFL 환경에서 DALLE-2, 그리고 Midjourney와 같은 이미지 생성형 인공지능 도구 활용 쓰기 활동이 대학생 영어학습자들의 정의적 영역에 미치는 영향을 알아보는 데에 있다. 이를 위해 강원도의 한 교원양성대학에 재학 중인 27명의 대학 영어학습자들을 대상으로 3주동안 연구가 진행되었다. 이 기간 동안 학생들은 이미지 생성형 인공지능 도구 중 하나인 Midjourney를 활용한 영어 쓰기 활동에 참여하였다. 실험 연구 가운데 학생들의 정의적 요인의 변화를 알아보기 위해 흥미도, 자신감, 참여도, 주도적 학습능력, 학습 동기와 같은 영역을 포함한 사전과 사후 온라인 설문이 시행되었다. 그 결과, 정의적 영역에서 전반적으로 긍정적인 변화가 나타났으며, 하위 항목 중 특히 흥미도와 자신감 영역에서 통계적으로 유의미한 차이가 나타났다. 다소 짧았던 연구 기간과 인지적 변화에 대한 중점 부재 등과 같은 한계점은 있었으나, 본 연구는 EFL 환경에서의 영어 쓰기 능력 향상을 위한 기반으로서 이미지 생성형 인공지능 도구의 활용 가능성을 제시했으며, 향후 더욱 더 깊이 있는 질적 연구의 필요성을 제안하고 있다.

The purpose of this pilot study is to investigate the effects of image generative artificial intelligence tools such as DALLE-2, and Midjourney on the affective domains of university English language learners in writing practice. The focal participants were 27 students from one of the teachers’ colleges in Gangwon Province. For the week experiment, the students were involved in creating images using one of the image-generative AI tools, Midjourney. Pre and post surveys were administered online to assess changes in the students’ affective domains which covered aspects such as interest, confidence, participation, self-directed learning ability, and learning motivation. The results showed a significant positive change in the overall average of the affective domains. Significant statistical differences were found using the paired samples t-test, especially in the subcategories of interest and confidence. Despite limitations such as the short duration of the study and the focus on affective rather than cognitive changes, the findings suggest that generative AI tools can have the potential to enhance English learners’ interest and confidence in English writing, which can serve as a foundation for improving writing skills in EFL settings. This study paves the way for future research on English learners’ cognitive changes in writing and deeper qualitative insights in this field.

본 연구의 목적은 인공지능을 활용한 <독해 질문 자동 생성기>를 개발하는 데에 있다. 이를 위하여 독해 질문의 유형을 ‘사실적 질문’과 ‘추론적 질문’으로 구분하였다. 사실적 질문은 텍스트에 답이 명시적으로 제시되어 있는 질문이다. 이에 비하여 추론적 질문은 텍스트에 답이 명시적으로 제시되어 있지는 않지만, 독자가 배경지식을 활용하여 답할 수 있는 질문이다. 또한 텍스트의 유형을 ‘서사체 텍스트’와 ‘설명체 텍스트’로 구분하였다. 서사체 텍스트에는 동화, 소설 등이 포함된다. 이에 비하여 설명체 텍스트에는 설명문, 논설문 등이 포함된다. 이와 관련된 데이터를 수집한 후에, 인공지능을 활용한 <독해 질문 자동 생성기>를 개발하였다. 이 질문 생성기는 4가지 기능을 제공한다. 첫 번째와 두 번째 기능은 사용자가 텍스트와 정답을 입력하면, 인공지능이 자동으로 질문을 생성하는 기능이다. 이를 통하여 사용자는 질문을 만드는 데에 드는 시간과 노력의 부담을 덜 수 있다. 이에 비하여 세 번째와 네 번째 기능은 사용자가 데이터를 추가하여, 새로운 인공지능 학습 모델을 만들 수 있는 기능이다. 이를 통하여 사용자는 자신의 연구 분야와 목적에 맞는 새로운 질문 생성기를 만들 수 있다. 본 연구에서 개발한 <독해 질문 자동 생성기>는 국어 교과의 읽기(독서) 분야 뿐만 아니라 여러 분야에서 활용할 수 있을 것으로 기대된다.

The purpose of this study is to develop <Automatic Reading comprehension Questions Generator> using artificial intelligence. For this purpose, the types of reading comprehension questions were divided into ‘literal questions’ and ‘inferential questions’. In addition, the types of texts were divided into ‘narrative texts’ and ‘expository texts’. After collecting data related to this, we developed <Automatic Reading comprehension Questions Generator> using artificial intelligence. This question generator provides four functions. The first and second functions allow artificial intelligence to automatically generates questions when the users input texts and correct answers. Through this, the user can reduce the time and effort required to create questions. In contrast, the third and fourth functions allow users to add data to create new artificial intelligence learning models. Through this, users can create new question generators suitable for their research fields and purposes. The <Automatic Reading comprehension Questions Generator> developed in this study is expected to be used not only in the field of reading in Korean subjects, but also in various fields.