• Language and Information
• /
• v.17 no.2
• /
• pp.93-121
• /
• 2013

Identifying the speakers of individual utterances mentioned in textual stories is an important step towards developing applications that involve the use of unique characteristics of speakers in stories, such as robot storytelling and story-to-scene generation. Despite the usefulness, it is a challenging task because not only human entities but also animals and even inanimate objects can become speakers especially in fairytales so that the number of candidates is much more than that in other types of text. In addition, since the action of speaking is not always mentioned explicitly, it is necessary to infer the speaker from the implicitly mentioned speaking behaviors such as appearances or emotional expressions. In this paper, we investigate a method to exploit linguistic clues to identify the speakers of utterances from textual fairytale stories in Korean, especially in order to handle such challenging issues. Compared with the previous work, the present work takes into account additional linguistic features such as vocative roles and pairs of conversation participants, and proposes the use of discourse-level turn-taking behaviors between speakers to further reduce the number of possible candidate speakers. We describe a simple rule-based method to choose a speaker from candidates based on such linguistic features and turn-taking behaviors.

• Journal of Computing Science and Engineering
• /
• v.3 no.3
• /
• pp.165-180
• /
• 2009

The HKIB, or Hankookilbo, test collections are two archives of Korean newswire stories manually categorized with semi-hierarchical or hierarchical category taxonomies. The base newswire stories were made available by the Hankook Ilbo (The Korea Daily) for research purposes. At first, Chungnam National University and KISTI collaborated to manually tag 40,075 news stories with categories by semi-hierarchical and balanced three-level classification scheme, where each news story has only one level-3 category (single-labeling). We refer to this original data set as HKIB-40075 test collection. And then Yonsei University and KISTI collaborated to select 20,000 newswire stories from the HKIB-40075 test collection, to rearrange the classification scheme to be fully hierarchical but unbalanced, and to assign one or more categories to each news story (multi-labeling). We refer to this modified data set as HKIB-20000 test collection. We benchmark a k-NN categorization algorithm both on HKIB-20000 and on HKIB-40075, illustrating properties of the collections, providing baseline results for future studies, and suggesting new directions for further research on Korean text categorization problem.

• Korean Journal of Cognitive Science
• /
• v.21 no.1
• /
• pp.77-93
• /
• 2010

The aim of this study was to identify neural correlates underlying the detection of faux pas, a test of theory of mind (ToM), in Korean healthy adults. Using functional magnetic resonance imaging, we compared the brain activities associated with faux pas stories and the activities associated with control stories. Faux pas stories compared with the control stories produced activations bilaterally in the superior frontal gyrus (BA 9) and in the precuneus (BA 7). The left medial frontal gyrus (BA 9), the left superior temporal gyrus (BA 38), the left inferior temporal gyrus (BA 20) and the right inferior parietal lobule (BA 40), the right postcentral gyrus (BA 1), the right lingual gyrus (BA 18), the right transverse temporal gyrus (BA 41) were also activated. The orbitofrontal cortex and the amygdala were not found to be involved in the detection of faux pas. This result suggests that brain activations associated with ToM are dependent on the type of mental state drawn by the task.

• Journal of Science Education
• /
• v.38 no.3
• /
• pp.525-542
• /
• 2014

This study was performed to look into the difficulty of students in understanding science stories in 6th grade science textbooks and to analyze those factors. To do this, 6th grader (N=65) were selected from J Elementary School located in Gyeonggi-do Siheung-si as study subjects. 26 science stories in 6th grade science textbooks were classified by field and context (complement of knowledge, science history of scientists, science in life, cutting-edge science technology, environment issues) in which the characteristics were investigated and analyzed. Also, a survey about the difficulty in understanding science stories(26 items) was conducted(65 students) and a semi-structured interview was conducted for students to clarify the meaning of collected data from surveys(4 students). As result of analyzing surveys on science story context in science textbooks and interviews, 4 fields of 'energy,' 'matter,' 'life,' and 'earth' were evenly mentioned. Science in life and complement of science knowledge were mentions most for context and this had relation with the characteristic of science textbooks to provide many opportunities to apply learned knowledge in actual social issues. Reactions of students on science stories were mostly positive that they help studying science, but there was also difficulty in well understanding science stories. Difficulty of understanding context, problems of context suggesting methods, difficulty of science terminology, lack of interest, and etc. were analyzed as factors. Specific causes were mentioned to be description type class, unimportant context, lack of explanation on suggested context, problem of pictures by students.

• Journal of the Korean Society of Food Culture
• /
• v.24 no.2
• /
• pp.137-145
• /
• 2009

The purpose of this study is to present the scheme that can enhance the value of native local foods by analyzing the case into which storytelling is incorporated in order to revitalize native local foods. Towards this end, the cases of native local foods throughout the country were recommended through professional survey and one region among them was finally selected through the field study. The survey on the native local foods was conducted through qualitative study. The four stages of storytelling: the findings of storytelling, the production of storytelling, the experience of storytelling, and sharing of storytelling were analyzed by stage and the contents of the survey by stage were developed. In the findings of story, the origins and background of the main family's foods and food-related stories were derived. The production of stories deals with how to convey the stories of surveyed native local foods to consumers and it presented the stories about the place and food menu. In the experience of storytelling, the physical environment and non-physical environment, in which people visit native local eating houses and experience native local foods were analyzed. Finally, in the sharing of story, how the tourists who have experienced the native local foods make stories and disseminate and share them was analyzed. The significance of this study is that through the storytelling technique it presented the findings, production, experience and sharing of native local foods in the level that can apply to practical business. Although the research is in the stage of inquiry, this study is meaningful in that it presented the basic methodology that can induce the revitalization of the native local food industry through examining the tradition and significance of native local foods that can be found in all the regions of the country.

• Journal of the Korean Society for information Management
• /
• v.24 no.2
• /
• pp.123-141
• /
• 2007

It has been known that predicting stock price is very difficult due to a large number of known and unknown factors and their interactions, which could influence the stock price. However, we started with a simple assumption that good news about a particular company will likely to influence its stock price to go up and vice versa. This assumption was verified to be correct by manually analyzing how the stock prices change after the relevant news stories were released. This means that we will be able to predict the stock price change to a certain degree if there is a reliable method to classify news stories as either favorable or unfavorable toward the company mentioned in the news. To classify a large number of news stories consistently and rapidly, we developed and evaluated a natural language processing based multi-stage news classification system, which categorizes news stories into either good or bad. The evaluation result was promising as the automatic classification led to better than chance prediction of the stock price change.

• Journal of Environmental Impact Assessment
• /
• v.17 no.4
• /
• pp.213-224
• /
• 2008

Since 1970's rapid urbanization and economic growth, the population was highly increased and residential type was changed from single detached house to high density and high-rise apartment. Recently more high-rise residential building generates more traffic volumes and it makes spatial concentration. The highly traffic volumed road and high residential building was constructed nearby, it occurs noise problem. The purpose of this study is comparing the performance of three type noise barrier between noise source and receiver using a noise map simulation. Three types were composed as road side planting trees, building side planting trees and noise barrier wall. Planting trees is less effective than noise barrier wall as a noise barrier. And they are all effective under 3 stories than over 5 stories, especially noise barrier function can't work over 5 stories.

• Journal of Korean Academy of Nursing
• /
• v.39 no.2
• /
• pp.237-248
• /
• 2009

Purpose: The purpose of this study was to investigate the experience of urinary incontinence (UI) for elderly Korean women using a narrative approach. Methods: The data were collected using individual in-depth interviews with 15 communitydwelling elderly women who had UI for at least 1 yr. The narratives of the life stories of these women were analyzed from the actor’s perspective, motivation and purpose of actions, and action toward goal achievement. Also the narratives on UI were analyzed according to cognition, behavior, and evaluation of UI. Results: Three major types of the life stories emerged from the analysis. First, the conquest narrative type reflects active characteristics of narrators within the circumstances of the sociocultural context. Second, the patience narrative is characterized as having flexibility between self determination for goal achievement and the boundary of the sociocultural context. Lastly, the compliance narrative reflected characteristics of narrators who easily adapt their way of life to circumstances. In terms of UI, the narrators in all three types lacked awareness of UI as an illness condition. Three different reasons are specifically identified according to the narrative types. Conclusion: The results of this study indicate that the concept and the illness behaviors related to UI in elderly Korean women with UI were closely related to the way of women's lives within the sociocultural and historical context.

• The Journal of Korean Academy of Sensory Integration
• /
• v.21 no.2
• /
• pp.69-83
• /
• 2023

Objective : This study sought to systematically examine the intervention effect of social stories when applied in relation to children with sleep disorders. Methods : Studies available in the SCOPUS, ScienceDirect, PsycArticles, and PubMed databases that were published from 2001 to 2022 were searched. The keywords used for the search were as follows: ("social story" OR "social stories") AND ("sleep" OR "sleep disorders" OR "sleep wake disorder bedtimes" OR "sleep initiation and maintenance disorders" OR "sleep wake disorder" OR "sleep arousal disorders"). Based on the selection criteria, six experimental studies were selected and analyzed. Results : The selected studies were two randomized controlled trials, three individual trials, and one case study. The subjects were mostly children diagnosed with autism spectrum disorder who were school-aged or adolescent. The intervention types were often complex interventions, including social stories and other interventions, while the durations of the interventions varied from one day to more than 40 days. The interventions had a positive effect on the subjects' sleep quality, with night wakings, sleep onset delay, and sleep anxiety all being improved. As standardized assessment tools to evaluate the effectiveness of social stories, the Child Sleep Habits Questionnaire and the Child Behavior Checklist were used in two papers each, and were the most commonly used. As non-standardized assessment tools, each of the four papers used turbulence and sleep diaries as assessment tools. Conclusion : The effect of social story mediation can be divided into sleep quality and sleep-related behavior. In terms of sleep quality, studies showing improvements in night wakings, sleep onset delay, and sleep anxiety accounted for a large proportion of the sample. The detailed effect area of sleep quality showed a significant improvement after the interventions in most studies, and in all six studies analyzed in the present study, the continuation of the effect after the intervention was confirmed via follow-up tests. Thus, the findings of this study are expected to be helpful when applying social stories in children with sleep disorders in clinical practice due to presenting the intervention effects, outcome evaluation tools, and intervention periods in children with sleep disorders in prior investigations involving social stories.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.931-934
• /
• 2019

Research using artificial intelligence to generate captions for an image has been studied extensively. However, these systems are unable to create creative stories that include more than one sentence based on image content. A story is a better way that humans use to foster social cooperation and develop social norms. This paper proposes a framework that can generate a relatively short story to describe based on the context of an image. The main contributions of this paper are (1) An unsupervised framework which uses recurrent neural network structure and encoder-decoder model to construct a short story for an image. (2) A huge English novel dataset, including horror and romantic themes that are manually collected and validated. By investigating the short stories, the proposed model proves that it can generate more creative contents compared to existing intelligent systems which can produce only one concise sentence. Therefore, the framework demonstrated in this work will trigger the research of a more robust AI story writer and encourages the application of the proposed model in helping story writer find a new idea.