• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.409-412
• /
• 2022

본 논문에서는 대입수시전형에서 생활기록부 입력은 대한민국 입시를 결정하는 매우 중요한 평가자료이다. 30명의 교사를 대상으로 실시한 설문조사를 통해서 교사들이 생활기록부를 작성하는데 가장 많이 참고하는 자료로는 수행평가 결과물, 발표내용, 보고서, 감상문 등의 학습 결과물(90%), 학생들이 작성한 자기평가서(73.3%), 관찰 평가지(50%)로 나타났으며, 80%(24명)의 교사들이 생활기록부를 작성하는데 고충을 겪고 있음을 확인할 수 있었다. 교사들이 느끼는 고충의 원인으로는 학생들의 개인별 특성 파악이 어려워 차별성있게 작성하는 것(76.7%)을 가장 힘들어 하였고, 작성해야 할 많은 수의 학생(60%), 문구를 만드는데 대해 부담(86.7%)을 느끼는 것으로 나타났다. 이 과정에서 교사의 전문성 뿐만 아니라 기계적이고 반복적인 작업도 많이 요구되고 있기 때문에, 생활기록부를 작성하는데에 도움을 줄 수 있는 프로그램 개발이 필요하다고 고안을 내었다. 교사들 역시 반복적이고 일률적인 생활기록부 작성에 도움을 줄 수 있는 프로그램이 있다면 유용하게 활용할 것이라는 응답이 90%였다. 따라서 본 연구에서 자연어 처리 인공지능 기술을 활용하여 교사들이 생활기록부를 작성하는데 있어 기계적이고 단순한 작업을 도와 주는 프로그램 개발에 대한 연구의 필요성을 제시하였다. 제안하는 프로그램은 학생들의 탐구보고서, 토론, 발표, 감상문 등의 생화기록부 작성 참고자료들을 텍스트로 변환하고 추상요약(Abstractive Summarization)을 통해 교사들이 효율적으로 작성하는데 활용될 수 있도록 설계하였다. 연구 결과 생활기록부 작성 참고자료를 텍스트로 변환하는 것과 추상요약을 할 수 있는 개방형 데이터셋까지는 확보하였다. 추상요약을 구현하는 방법에 대해서는 보다 심도 있는 추가연구가 필요하였다. 이를 통해 교사들이 교육 본질에 더욱 충실할 수 있는 환경을 마련하고, 내실 있는 생활기록부 작성이 공교육 신뢰 제고에 밑바탕이 되고자 한다.

• Science of Emotion and Sensibility
• /
• v.27 no.1
• /
• pp.69-80
• /
• 2024

This study aimed to gain valuable insights into the performance and user satisfaction of applications (apps) through a thorough analysis of Instagram user reviews collected from Google Play. The study utilized text mining and sentiment analysis techniques and systematically identified emotions and opinions embedded in user reviews to deeply understand the areas of improvement and user experiences of the app. It analyzes how Instagram reviews reflect the diverse experiences of users and how they reveal the strengths and weaknesses of the app. For this purpose, sentiment analysis using the naive Bayes algorithm was conducted, and the results were expected to aid in the improvement of Instagram's services. In addition, the study aimed to assist developers in better understanding and utilizing user feedback, ultimately contributing to enhanced user satisfaction. This study explored the complex relationship between social media usage patterns and user opinions by seeking ways to provide a better user experience through these insights.

• 유학연구
• /
• v.44
• /
• pp.303-333
• /
• 2018

In this paper, Peng Xiao's analysis of his Waitan Alchemy method was conducted, using Zhouyi Chantongqi Fenzhangtongzhenyi as the main text. Unlike former President Zhouyi Chantongqi, Peng Xiao's president Zhoui Chantongqi is characterized by the simultaneous appearance of Neidan and Waitan. It reveals the characteristics of the course. The study of Zhouyi Chantong qi Fenzhangtongzhenyi explains the shift in Waitan and Neitan in Taoism and the change in terms of its meaning and terminology. In this paper, we looked at the basic principles of Alchemy in Zhouyi Chantongqi Fenzhangtongzhenyi, the three main tools of Alchemy : pots, drugs, and fire control. In addition, Huangtan, Liangtan and Xuantan, which were acquired in the specific process of Alchemy, were also identified through text analysis. Finally, we looked at the effects and effects of the Waitan's Alchemy. These studies will provide easier access to the Waitan language, which is more diverse than the original Wei Boyang's Zhouyi Chantongqi and other comments. Based on this, another in-depth study of the Neitan idea of Fenzhangtongzhenyi will be possible in the future.

• Knowledge Management Research
• /
• v.25 no.3
• /
• pp.201-230
• /
• 2024

This study aimed to identify the factors contributing to perceived healthiness by analyzing consumer reviews of healthy restaurants. While previous studies have primarily focused on the healthiness of food products, comprehensive research from the perspective of restaurants through online review analysis is limited. To achieve this, co-occurrence network analysis and LDA topic modeling, methods of text mining, were used to investigate consumers' health-related perceptions and preferences for healthy restaurants based on a large dataset of online reviews. The analysis revealed that consumers emphasize various health-related factors such as taste, ingredient categories, freshness, price, nutritional content, healthy options, and menu diversity when choosing healthy restaurants. These factors significantly influence the evaluation and selection of restaurants. Notably, it was found that the taste of food offered in healthy restaurants is closely linked to the perception of healthiness, highlighting the importance of a healthy taste derived from ingredients. In conclusion, this study provides practical insights into how healthy restaurants can reflect and meet consumers' health perceptions and suggests strategic directions for the food and dining industry to respond to health trends.

• The Journal of the Korea Contents Association
• /
• v.12 no.8
• /
• pp.13-19
• /
• 2012

This paper introduces a test-bed toolkit for evaluating and enhancing text analysis engines which extract technological knowledge from articles, patents, reports and so forth. The toolkit consists of two test-beds for technical entity recognition and relation extraction engines, which are capable of identifying technical entities and predicting semantic relation types between the entities. With using the introduced toolkits, users and developers can efficiently perform the execution monitoring and error analysis of the technical text analysis engines.

• Journal of Digital Contents Society
• /
• v.12 no.2
• /
• pp.225-232
• /
• 2011

is an innovative creation, accommodating characteristics of various genres and media, ranging from elements of media aesthetics to visual aesthetics and games. Although it takes a form of a book, it exceeds stereotypes seen in paperbacks or eBooks. Because of such differentiated characteristics of this appBook (which is provided in the form of app), it induce users(readers) to conduct interactional activity. This study will mainly discuss about the formation of discourse of app based digital novel in a media aesthetic point of view. Considering the mutual relation between property of media and contents of stories, it is desirable to accommodate the mutuality of understanding between the digital media and formation discourse in creating stories.

• Journal of Internet Computing and Services
• /
• v.13 no.2
• /
• pp.99-108
• /
• 2012

Many methods had been developed to improve the accuracy of extracting information from a vast amount of data. This paper combined a number of natural language processing methods such as NER (named entity recognition), sentence extraction, and part of speech tagging to carry out text analysis. The data source is comprised of texts obtained from the web using a domain-specific data extraction agent. A framework for the extraction of information from unstructured data was developed using the aforementioned natural language processing methods. We simulated the performance of our work in the extraction and analysis of texts for the detection of organizational structures. Simulation shows that our study outperformed other NER classifiers such as MUC and CoNLL on information extraction.

• Journal of KIISE
• /
• v.43 no.5
• /
• pp.509-515
• /
• 2016

Given a text T and a pattern P, the order-preserving pattern matching problem is to find all substrings in T which have the same relative orders as P. The order-preserving pattern matching problem has been studied in terms of finding some patterns affected by relative orders, not by their absolute values. Given a text T and a pattern set $\mathbb{P}$, the order-preserving multiple pattern matching problem is to find all substrings in T which have the same relative orders as any pattern in $\mathbb{P}$. In this paper, we present a hashing-based algorithm for the order-preserving multiple pattern matching problem.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.1
• /
• pp.329-332
• /
• 2014

The Korean High Speed Electric Multiple Unit (HEMU) train system is soon being applicable to practical use. This new technology is expected not only to reshape the domestic market but also to be exported to overseas markets for high-speed train system. This study aims to prospect demands on the HEMU train technology and to formulate marketing strategies using a text-mining technique, therefore, providing a foundation for successful commercialization of the HEMU train system.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.123-124
• /
• 2011

반도체 기술의 비약적 발전에 힘입어 현재의 개인용 컴퓨터는 고성능 CPU를 탑재하고 1990대의 텍스트 기반의 운영체제에서 벗어나 그래픽 기반의 운영체제에서 다양한 멀티미디어 기능을 제공 한다. 이를 위한 입력장치로 텍스트 기반 운영체제에서 주로 사용된 키보드뿐 아니라 마우스, 카메라, 터치스크린 등의 다양한 장치들이 사용되고 있다. 그러나 빔 프로젝터를 이용한 프레젠테이션의 경우 아직도 레이저포인터를 이용한 발표가 일반적이며 발표자와 빔 프로젝트용 PC와의 인터랙션이 없기 때문에 다양한 멀티미디어 기능 구현이 제한적이다. 본 논문에서는 USB 웹 카메라를 이용하여 프로젝터 화면을 촬영한 후 영상처리 라이브러리인 OpenCV를 기반으로 레이저 포인터의 위치와 동작을 검출하여 원거리에서도 사용자가 레이저 포인터를 이용하여 마우스 동작을 재현할 수 있는 시스템을 개발하고자 한다. 이를 활용하면 레이저 포인터를 사용하여 발표자가 별도의 입력장치 없이 PC와의 인터랙션이 가능해져서 다양한 멀티미디어 기반의 프레젠테이션이 가능해진다.