• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2004년도 추계 종합학술대회 논문집
• /
• pp.476-482
• /
• 2004

질의 응답 시스템은 사용자의 질의를 분석하여 제한된 길이의 정답을 제시해 주는 시스템이다. 질의 응답 시스템은 정확한 정답을 추출하기 위해 사용자의 질의를 분석하는 과정을 필요로 한다. 본 논문에서는 초점단어(focus-word)를 이용한 질의분석을 제안한다. 초점단어란 정답유형을 결정하는데 단서가 되는 단어로써, 추출된 초점단어에 의해 75개의 하위정답유형 중 하나가 결정된다. 실험에는 학습 데이터의 일부와 일반 Web에서 수집한 테스트 데이터가 사용되었다. 실험결과 상위범주는 97.18%, 하위범주는 95.31%의 정확도를 보였다.

• 한국콘텐츠학회논문지
• /
• 제16권7호
• /
• pp.423-430
• /
• 2016

자기보고식 설문 조사는 상황적 요인 및 개인적 특성에 따라 응답 결과가 달라질 수 있다. 본 연구는 산업 및 조직심리학 분야에서 널리 연구되고 있는 직무만족 변인을 중심으로 설문 조사 시 질문 순서 및 질문 의도가 미치는 영향을 조사하였다. 설문지는 전반적 질문과 세부적 질문의 배치 순서에 따른 질문 순서 차이 그리고 직무만족 또는 직무불만족 측정에 따른 질문 의도 차이에 따라 총 4종류를 사용하였다. 94명의 직장인을 대상으로 한 설문 조사 결과 기존 연구와 달리 전반적 질문이 먼저 제시된 경우에서 전반적 질문과 세부적 질문에 대한 응답 간 상관이 더 높은 것으로 나타났다. 통계적으로 유의한 수준은 아니었으나 직무만족 질문이 직무불만족의 질문에 비해 대부분의 영역에서 만족도가 높은 것으로 나타났다. 끝으로 연구의 의의와 한계점 및 향후 연구방향을 살펴보았다.

• 한국콘텐츠학회논문지
• /
• 제6권3호
• /
• pp.12-19
• /
• 2006

본 논문에서는 질의 응답 시스템의 성능 향상을 위한 질의문 심층 분석을 제안한다. 일반적인 질의응답 시스템들은 사용자의 자연언어 질의의 의미를 분석하지 않기 때문에 정확한 정답을 제공하는 것이 어렵다. 질의문 심층 분석은 의미자질 추출 문법과 자연언어 질의 특성을 이용하여 사용자의 질의를 의미적으로 분석하고, 의미자질들을 추출한다. 의미자질 추출 문법과 자연언어 질의 특성은 사용자 질의의 의미와 구문 구조를 반영하기 위해 의미자질과 형식형태소로 표현된다. 웹에서 추출한 세부 정답 유형이 '인물'인 100개의 질의에 대한 실험을 통해, 비교적 짧지만 사용자의 질의 의도를 충분히 표현하고 있는 자연언어 질의에 대해 질의문 심층 분석을 수행함으로써 사용자의 질의 의도를 분석하고, 의미자질들을 추출할 수 있음을 보였다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제13권2호
• /
• pp.179-186
• /
• 2021

We have been developed the smart tourism app and the Instagram and YouTube contents to provide personalized tourism information and travel product information to individual tourists. In this paper, we develop a rule-based smart tourism chatbot with the khaiii (Kakao Hangul Analyzer III) morphological analyzer and Neo4J graph database. In the proposed chatbot system, we use a morpheme analyzer, a proper noun dictionary including tourist destination names, and a general noun dictionary including containing frequently used words in tourist information search to understand the intention of the user's question. The tourism knowledge base built using the Neo4J graph database provides adequate answers to tourists' questions. In this paper, the nodes of Neo4J are Area based on tourist destination address, Contents with property of tourist information, and Service including service attribute data frequently used for search. A Neo4J query is created based on the result of analyzing the intention of a tourist's question with the property of nodes and relationships in Neo4J database. An answer to the question is made by searching in the tourism knowledge base. In this paper, we create the tourism knowledge base using more than 1300 Jeju tourism information used in the smart tourism app. We plan to develop a multilingual smart tour chatbot using the named entity recognition (NER), intention classification using conditional random field(CRF), and transfer learning using the pretrained language models.

• 한국조리학회지
• /
• 제18권5호
• /
• pp.95-112
• /
• 2012

본 연구의 목적은 전통비빔밥이 아닌 새로운 형태의 퓨전비빔밥에 대한 선호도 및 구매의도에 관한 탐색적 연구를 수행하는데 목적이 있다. 본 연구는 목적 달성을 위해 서울 지역 지하철을 이용하는 소비자들을 중심으로 표본조사를 실시하였다. 조사는 2012년 4월 3일부터 2012년 4월 10일까지 1주일동안 이루어졌고, 총 288부를 최종 분석에 사용하였다. 분석결과 비빔밥 선호에 관한 질문에서는 '좋다'와 '매우좋다' 응답이 총 190명으로 긍정적으로 나타났고, 선호하는 이유로는 '간편히 먹기 위해서'와 '맛있어서'로 나타났다. 소비자들의 퓨전비빔밥에 대한 선호도는 '매운 낙지비빔밥', '돈가스비빔밥', '회비빔밥', '치킨데리야끼비빔밥', '비빔밥 시금치 라자냐'순으로 나타났고, 구매 의도는 '매운 낙지비빔밥', '돈가스비빔밥', '회비빔밥', '게살비빔밥', '치킨데리야끼비빔밥' 순으로 나타났다. 인구통계학적 특성인 성별, 결혼유무, 연령, 학력에 따라서 퓨전비빔밥의 선호도와 구매의도 모두 유의한 차이가 있는 것으로 나타났다.

• 한국치위생학회지
• /
• 제15권4호
• /
• pp.641-648
• /
• 2015

Objectives: The purpose of the study is to investigate the relationship between emotional labor, burnout and turnover intention in the dental hygienists. Methods: A self-reported questionnaire was completed by 326 dental hygienists in Seoul and Gyeonggido from September to October, 2013. The collected data were analyzed by SPSS/WIN 15.0 program. The questionnaire consisted of nine questions of the general characteristics of the subjects, ten questions of turnover intention, and fourteen questions of burnout. Each question was measured by Likert 5 point scale. Results: There was a significant difference in workplace and monthly income which had an impact on emotional expression(p<0.05). There was a significant difference in current workplace and monthly income which had an impact on emotional dissonance(p<0.05). Burnout had a significant difference(p<0.05) in age, religion, and turnover intention current workplace, employment condition, and the number of turnover. There was a positive correlation between burnout and turnover intention. It was shown that Emotional labor had a positive correlation with burnout and turnover intention and the explanation power was 18.1%. Conclusions: The dental hygienists are one of the most vulnerable emotional labor workers and are apt to feel exhaustion from the job and turnover intention. It is necessary to prepare for the burnout and turnover intention in the dental hygienists.

• International Journal of Knowledge Content Development & Technology
• /
• 제7권1호
• /
• pp.101-120
• /
• 2017

Healthcare professionals have edited many health questions (HQs) and their answers for healthcare consumers on the Internet. The HQs provide both readable and reliable health information, and hence retrieval of those HQs that are relevant to a given question is essential for health education and promotion through the Internet. However, retrieval of relevant HQs needs to be based on the recognition of the intention of each HQ, which is difficult to be done by predefining syntactic and semantic rules. We thus model the intention recognition problem as a text classification problem, and develop two techniques to improve a learning-based text classifier for the problem. The two techniques improve the classifier by location-based and area-based feature weightings, respectively. Experimental results show that, the two techniques can work together to significantly improve a Support Vector Machine classifier in both the recognition of HQ intentions and the retrieval of relevant HQs.

• 아태비즈니스연구
• /
• 제4권1호
• /
• pp.1-14
• /
• 2013

In spite of the interest related to the entrepreneurship, the problems related to the creation of companies by the public civils servant still remain unanswered and not unanimously identified. In fact, a central question arises in this respect: "which are the factors which encourage the public civils servant to launch out in the creation of their own company?" or "how can one explain the entrepreneurial intention of the public civils servant?". For this end, and after having reviewed the principal subjacent factors of the entrepreneurial intention as well as the central assumptions of our research task, we will devote the second part to the empirical validation of the explanatory factors of the entrepreneurial intention in the specific case of the Indian public civils servant while proposing some recommendations on the matter.

• Asian Journal for Public Opinion Research
• /
• 제10권2호
• /
• pp.76-101
• /
• 2022

Despite the increasing use of digital media and their powerful impact on risk management during recent outbreaks of emerging infectious diseases, the question of how digital media exposure influences preventive behaviors has not been fully explained. Using the appraisal tendency framework and protection motivation theory as theoretical frameworks, we theorized the affective and cognitive mechanisms under which the differential roles of three negative emotions (fear, anger, worry) on two cognitive appraisals (perceived threat and perceived efficacy) were examined. Based on data collected from a survey of 1,500 South Koreans during the COVID-19 pandemic, we found that while worry and anger increased perceived efficacy, fear reduced perceived efficacy. The results also showed that although exposure to COVID-19 information via digital formats increased preventive behavioral intention in general, digital media use for COVID-19 information had a negative influence on preventive behavioral intention through the sequential mediation of fear and perceived efficacy.

• 한국보육지원학회지
• /
• 제13권1호
• /
• pp.185-200
• /
• 2017

Objective: This study was conducted to investigate the effects of early childhood teachers' teaching beliefs, mathematics teaching efficacy, and pedagogical content knowledge of mathematics on their teaching intention of mathematics. Methods: A total of 266 early child teachers in Busan participated in this study. They completed a set of question naires which consisted of questions about teaching beliefs, mathematics teaching efficacy, pedagogical content knowledge of mathematics, and the teaching intention of mathematics. The collected data were analyzed using the SPSS program. Results: First, we observed several positive correlations among the four variables. Second, we found that early childhood teachers' constructive teaching beliefs, mathematics teaching efficacy, and pedagogical content knowledge of mathematics had effects on their teaching intention of mathematics. The knowledge about teaching-learning methods for mathematics among the subcategories of pedagogical content knowledge of mathematics was observed as the strongest predictor for the teachers' teaching intention. Conclusion: We need to take more interest in the pedagogical knowledge about teaching-learning methods of mathematics in teacher training courses in order to enhance teachers' teaching intention of mathematics. As a result, this will makea contribution to high quality math education for young children.