• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.97-113
• /
• 2016

Due to the growth of internet data and the rapid development of internet technology, "big data" analysis is actively conducted to analyze enormous data for various purposes. Especially in recent years, a number of studies have been performed on the applications of text mining techniques in order to overcome the limitations of existing structured data analysis. Various studies on sentiment analysis, the part of text mining techniques, are actively studied to score opinions based on the distribution of polarity of words in documents. Usually, the sentiment analysis uses sentiment dictionary contains positivity and negativity of vocabularies. As a part of such studies, this study tries to construct sentiment dictionary which is customized to specific data domain. Using a common sentiment dictionary for sentiment analysis without considering data domain characteristic cannot reflect contextual expression only used in the specific data domain. So, we can expect using a modified sentiment dictionary customized to data domain can lead the improvement of sentiment analysis efficiency. Therefore, this study aims to suggest a way to construct customized dictionary to reflect characteristics of data domain. Especially, in this study, movie review data are divided by genre and construct genre-customized dictionaries. The performance of customized dictionary in sentiment analysis is compared with a common sentiment dictionary. In this study, IMDb data are chosen as the subject of analysis, and movie reviews are categorized by genre. Six genres in IMDb, 'action', 'animation', 'comedy', 'drama', 'horror', and 'sci-fi' are selected. Five highest ranking movies and five lowest ranking movies per genre are selected as training data set and two years' movie data from 2012 September 2012 to June 2014 are collected as test data set. Using SO-PMI (Semantic Orientation from Point-wise Mutual Information) technique, we build customized sentiment dictionary per genre and compare prediction accuracy on review rating. As a result of the analysis, the prediction using customized dictionaries improves prediction accuracy. The performance improvement is 2.82% in overall and is statistical significant. Especially, the customized dictionary on 'sci-fi' leads the highest accuracy improvement among six genres. Even though this study shows the usefulness of customized dictionaries in sentiment analysis, further studies are required to generalize the results. In this study, we only consider adjectives as additional terms in customized sentiment dictionary. Other part of text such as verb and adverb can be considered to improve sentiment analysis performance. Also, we need to apply customized sentiment dictionary to other domain such as product reviews.

• Electronics and Telecommunications Trends
• /
• v.32 no.5
• /
• pp.39-48
• /
• 2017

Since the world's first 3D commercial film with red-blue glasses was introduced in 1922, remarkable progress has been made in the field of 3D video. 3D video content gained enormous popularity with the movie "Avatar," which greatly increased the sale of 3D TVs. This momentum has weakened owing to lack of 3D content. However, the recent trend of virtual reality (VR) and augmented reality (AR) made 360 VR video and 3D games using a head mounted display wide spread. All these experiences mentioned above require wearing glasses to enjoy 3D content. Super multi-view content technology, on the other hand, enables viewers to enjoy 3D content without glasses on a super multi-view display. In this article, we introduce the technologies used to make super multi-view content, interact with it, and author content, which are developed by ETRI.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.75-78
• /
• 2018

감성 분석은 특정 대상에 대한 의견을 수집하고 분류하는 과정이다. 그러나 자연어에 담김 사람의 주관을 파악하는 일은 어려운 일로써, 기존의 감성 단어 사전이나 확률 모델은 이러한 문제를 해결하기 어려웠으나 딥 러닝의 발전으로 문제 해결을 시도할 수 있게 됐다. 본 논문에서는 사전 학습된 문맥 표현을 한국어 감성 분석에 활용하여 더 높은 성능을 낼 수 있음을 보인다.

• The International Journal of Costume Culture
• /
• v.13 no.1
• /
• pp.5-8
• /
• 2010

The goal of this study is to analyze the influence of the costume culture of South Korean movies and television series on the development of fashion industry. South Korean movies and television series make full use of the influence of costume culture to advocate Korea's national spirit and character as well as the confidence and vigor of the young generation. They contribute to establishing South Korea as a country with a graceful, modern appearance and great cultural heritage. The presentation and promotion of its costume culture in movie and television series stimulates its cultural competence and advances its cultural creative industry. The spread of Korean costume culture has become the pioneer and foreshadowing of clothing industries and greatly underpins its advancement overseas. In concert, the development of clothing industry helps the spread of Korean costume culture.

• Management Science and Financial Engineering
• /
• v.11 no.3
• /
• pp.137-153
• /
• 2005

Collaborative filtering-based recommendation systems make personalized recommendations based on users' ratings on products. Recommender systems must collect sufficient rating information from users to provide relevant recommendations because less user rating information results in poorer performance of recommender systems. To learn about new users, recommendation systems must first present users with an initial item list. In this study, we designed and analyzed seven selection strategies including the popularity, favorite, clustering, genre, and entropy methods. We investigated how these strategies performed using MovieLens, a public dataset. While the favorite and popularity methods tended to produce the highest average score and greatest average number of ratings, respectively, a hybrid of both favorite and popularity methods or a hybrid of demographic, favorite, and popularity methods also performed within acceptable ranges for both rating scores and numbers of ratings.

• International Journal of Advanced Culture Technology
• /
• v.8 no.2
• /
• pp.231-238
• /
• 2020

Generally, sequential data refers to data having continuity. Text data, which is a representative type of unstructured data, is also sequential data in that it is necessary to know the meaning of the preceding word in order to know the meaning of the following word or context. So far, many techniques for analyzing sequential data such as text data have been proposed. In this paper, four methods of 1d-CNN, LSTM, BiLSTM, and C-LSTM are introduced, focusing on neural network techniques. In addition, by using this, IMDb movie review data was classified into two classes to compare the performance of the techniques in terms of accuracy and analysis time.

• Annual Conference on Human and Language Technology
• /
• 2011.10a
• /
• pp.37-41
• /
• 2011

본 논문에서는 최근 많은 관심을 받고 있는 Opinion Mining으로서 사용자들의 자연어 형태의 영화평 문장을 분석하여 자동으로 평점을 예측하는 시스템을 제안한다. 제안 시스템은 영화평 분석에 적합한 어휘 자질, 감정 자질, 가치 자질 및 기타 자질들을 추출하고, 10점 척도의 영화평의 평점을 10개의 범주로 가정하여, 커널모델인 다중 범주 Support Vector Machine (SVM) 모델을 이용하여 높은 성능으로 영화평의 평점을 범주 분류한다.

• Journal of Power Electronics
• /
• v.10 no.6
• /
• pp.643-646
• /
• 2010

An interactive web-based teaching tool for a power semiconductor course at the University of Central Florida is presented in this paper. A novel approach is introduced using Technology Aided Design Tools (TCAD) to generate time-lapsed 2D semiconductor device cross-section embedded in a webpage using $Adobe^{(R)}$ Flash (web design tool) platform to create interactive movies that demonstrate complex device physical phenomenon. Students can step through the interactive movies forward, backward, pausing, or looping. Each step represents a giving bias condition. Current-voltage plots are represented along with the semiconductor device and a visual point is placed on the IV curve to indicate the current bias conditions. The changes are then reflected in the 2D cross-section movie area and the IV plot. This tool was implemented in a classroom setting to augment the lectures or for discovery learning.

• International Journal of Advanced Culture Technology
• /
• v.10 no.2
• /
• pp.181-186
• /
• 2022

In this paper, we examine the shortening of the theatrical window whereby films play at theaters for 90 days as one of the most portentous issues that could reshape the Hollywood film industry. We first examine the windows system that protected the status of movie theaters and the studios' attempt to shorten the theatrical release to create a premium VOD window in response to the declining revenue of DVDs after 2007 and the rise of streaming services. We then look at some of the major disruptions in distribution COVID-19 brought about. We also explore the shortening of the theatrical release in the wake of the pandemic and shows the changes in the theatrical release, along with the expansion of streaming services, raise questions over the long-held primacy of the theatrical release and the definition of film with the theatrical release as its part. From this, we highlight Hollywood at the crossroads of major changes with its future less certain than ever before.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.563-568
• /
• 2020

본 연구에서는 블랙박스로 알려진 딥러닝 모델에 설명 근거를 제공할 수 있는 설명자 모델을 적용해 보았다. 영화평 감성 분석을 위해 MLP, CNN으로 구성된 딥러닝 모델과 결정트리의 앙상블인 Gradient Boosting 모델을 이용하여 감성 분류기를 구축하였다. 설명자 모델로는 기울기(gradient)을 기반으로 하는 IG와 레이어 사이의 가중치(weight)을 기반으로 하는 CAM, 그리고 설명가능한 대리 모델을 이용하는 LIME과 입력 속성에 대한 선형모델을 추정하는 SHAP을 사용하였다. 설명자 모델의 특성을 보기 위하여 히트맵과 관련성 높은 N개의 속성을 추출해 보았다. 설명자가 제공하는 기여도에 따라 입력 속성을 제거해 가며 분류기 성능 변화를 측정하는 정량적 평가도 수행하였다. 또한, 사람의 판단 근거와의 일치도를 살펴볼 수 있는 '설명 근거 정확도'라는 새로운 평가 방법을 제안하여 적용해 보았다.