Eun-Soon You

Emotion-based character clustering for managing story-based contents: a cinemetric analysis

Stories in digital content (e.g., movies) are usually developed using many kinds of relationships among the characters. In order to efficiently manage such contents, we want to exploit a social network (called Character-net) extracted from the stories. Since scripts are composed of several elements (i.e., scene headings, character names, dialogs, actions, etc.), we focus on analyzing interactions (e.g., dialog) among the characters to build such a social network. Most importantly, these relationships between minor and major characters can be abstracted and clustered into similar scenes. Thereby, in this paper, we propose a novel method that can cluster characters using their emotional similarity. If a minor character has a similar emotion vector tothe main character, then the minor character can be classified as a tritagonist who helps the main character. Conversely, this minor character may be clustered into another group and denoted as an antagonist. Additionally, we show the efficiency of our proposed method by experiment in this paper.

A computational model of transmedia ecosystem for story-based contents

Story-based contents (e.g., novel, movies, and computer games) have been dynamically transformed into various media. In this environment, the contents are not complete in themselves, but closely connected with each other. Also, they are not simply transformed form a medium to other media, but expanding their stories. It is called as a transmedia storytelling, and a group of contents following it is called as a transmedia ecosystem. Since the contents are highly connected in terms of the story in the transmedia ecosystem, the existing content analysis methods are hard to extract relationships between the contents. Therefore, a proper content analysis method is needed with considering expansions of the story. The aim of this work is to understand how (and why) such contents are transformed by i) defining the main features of the transmedia storytelling and ii) building the taxonomy among the transmedia patterns. More importantly, computational transmedia ecosystem is designed to process a large number of the contents, and to support high understandability of the complex transmedia patterns.

Potential Emotion Word in Movie Dialog

Word emotion analysis is the basic step that recognizes emotions. Emotion words that express emotion on dialogs are classified into two classes such as direct and potential emotion word. Direct emotion word can represent clearly emotion and potential emotion word may represent specific emotion depending on context. Potential emotion word unlike direct emotion word is hardly extracted and identified. In this paper, we propose the method that extracts and identifies potential emotion words based on WordNet as well as direct emotion words. Potential emotion word can be extracted by measuring lexical affinity. Then, we consider the sense distance in order to minimize variation of meaning. In addition, we suggest the maximum sense distance that limits searching space and can extract the best potential emotion words.

Storytelling of Collaborative Learning System on Augmented Reality

As augmented reality technologies offer superior senses of presence and immersion to learners through layers of virtual information over the physical world, much attention has been drawn to this learning medium that creates a new learning environment driven by experiences. And, existing AR-based learning content has just focused on interactions among users and on three-dimensional imaging techniques while the collaborative element has not been taken into account fully. Against the backdrop, a rule-based interactive storytelling element has been introduced to the system that offers a variety of contents at a user’s choice so as to draw attention and interests. To verify the effectiveness of such learning system, an experiment was conducted with primary school students who went through a performance assessment of ‘Growing Peach Tree’. The experiment proved the learning system effective with a high score of 80.4, which is equivalent to that of debate-based learning.

Adaptive Complex Event Processing Based on Collaborative Rule Mining Engine

Complex Event Processing (CEP) detects complex events or patterns of event sequences based on a set of rules defined by a domain expert. However, it lowers the reliability of a system as the set of rules defined by an expert changes along with dynamic changes in the domain environment. A human error made by an expert is another factor that may undermine the reliability of the system. In an effort to address such problems, this study introduces Collaborative Rule Mining Engine (CRME) designed to automatically mine rules based on the history of decisions made by a domain expert by adopting a collaborative filtering approach, which is effective in mimicking and predicting human decision-making in an environment where there are sufficient data or information to do so. Furthermore, this study suggests an adaptive CEP technique, which does not hamper the reliability since it prevents potential errors caused by mistakes of domain experts and adapts to changes in the domain environment on its own as it is linked to the system proposed by Bharagavi [10]. In a bid to verify this technique, an automated stocks trading system will be established and its performance will be measured using the rate of return.

Movie browsing system based on character and emotion

A variety of research is in progress to detect wanted scenes from videos. A method of detecting scenes wanted by a user through scene rearrangement based on calculated visual similarity is limited in that such a method does not reflect elements along the storyline through which a user remembers a movie. A movie’s story is built up by characters, and such build-up is closely related with emotions of characters in a film. A movie browsing system based on storyline is executable by applying characters and those characters’ emotions. Thus, methods of extracting key characters in each scene and of clustering scenes through extraction of emotion vectors from dialogues in each scene are hereby suggested. This paper also proposes to develop a movie browsing method and a system based on emotions of characters.

Improved Performance of Emotion Extraction Through Banned Words

With the increased interests in annotation of multimedia contents in a bid to improve information retrieval performance, the importance of information on emotions in the contents is being highlighted. This research improves the previous emotion extraction method using WordNet. Since it required too much time for search emotional category and had wrong many results, we propose an advanced emotion extraction method added banned words. This improved method and the banned words will be described in this paper. Also, we will show the efficiency of our proposal through experiment.

Design of Narrative Text Visualization Through Character-net

인터넷 발전과 스마트 혁명을 거치며 사용자가 생산하는 데이터양이 중가하고 그 유형도 다양해졌다. 이 렇게 방대한 양의 데이터를 분석하고 새로운 가치로 활용한다는 개념의 빅데이터가 새로운 이슈로 부상하 였다. 더욱이 빅데이터 속의 콘텐츠들을 검색하기 위해서는 동영상이 포함하고 있는 스토리에 대한 분석과 시각화에 대한 연구가 필요하다. 따라서 본 연구에서는 등장인물들 간의 대화를 분석하여 스토리를 모델링 하는 캐릭터 넷(Character-net)이라는 인터페이스를 개발하였다. 캐릭터 넷은 스토리가 있는 동영상을 분 석해서 인물들을 자동으로 추출할 수 있고, 등장인물들 간의 관계를 자동으로 모형화 할 수 있다. 이로써 기존 연구와는 다른 방법으로 스토리를 가시화하는 툴의 가능성을 발견할 수 있었다. 하지만 아직 활용하기 어렵고 한 눈에 스토리 특징을 파악하기 어렵다는 단점이 발견되었다. 이러한 캐릭터 넷을 개선하기 위해서 는 정보 디자인을 접목하여 해결할 수 있을 것이라 가정하였다. 따라서 본고에서는 먼저 데이터 정보디자인 분야에서의 시각화 디자인들을 간략하게 소개하였다. 나아가 동영상 스토리를 시각화하는 연구 사례들을 살펴보았다. 그리고 캐릭터 넷의 핵심 아이디어와 기존 연구와의 기술적 차이점에 대해 소개한 뒤, 추가적 으로 이를 디자인적 솔루션을 접목하여 개선할 수 있는 방법들을 모색하였다.

Story Modeling for Green Light Decision Making

The content business is an important field that regulates national competitiveness in the culture industry. Particularly, the size of the movie industry is 1.1 billion dollars in Korea and 85 billion dollars worldwide. It is steadily increasing. However, few movies are successful and the production of a new movie has a high risk. Thus, it is necessary to analyze the scenarios that are made before filming. This is needed to forecast if a movie will be hit. We propose a new method that analyzes and forecasts the movie based on its story, since the plot most influences a box office hit.

Collaborative Digital Storytelling based on Collective Intelligence through Contest

Web development and digital technology enable users not only to consume contents but also to produce and share it through using various media. Thus, since personal needs for contents are increased, the interest in environment and technology for creating digital contents is growing. Because of existing digital contents technology such as writing tool or digital storyboard have focused on the individual creation, it is hard to induce participation and collaboration of other users and sharing and reusing contents. Therefore, we suggest a new form of collaborate digital storytelling using the concept of the collective intelligence through contest. Most of all, we develop writing tool and storyboard tool in order to facilitate participants to produce online contents. Also, distinguished from previous contest, this contest considers not only content output but also collaborative process for making it.