• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.430-433
• /
• 2018

딥러닝 모델의 성능 향상을 위해 적은 데이터를 증가시킬 수 있는 연구들이 필요하다. 이미지의 경우 회전, 이동, 반전등의 연산으로 쉽게 데이터를 증가시킬 수 있지만 자연어는 그렇지 않다. 그러나 최근 딥러닝 생성 모델의 발전으로 기존 자연어 데이터를 생성 모델을 통해 양을 늘려 실험하는 연구들이 많이 시도되었다. 본 논문에서는 문장 데이터 생성을 위한 VAE, 문장 분류를 위한 CNN이 결합된 모델을 한국어 영화평 데이터에 적용하여 기존 모델보다 0.146% 높은 86.736%의 정확도를 기록하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.441-444
• /
• 2012

오늘날 스마트폰의 보급으로 SNS는 급속도로 성장하였고, 매일 엄청난 분량의 텍스트 데이터가 생성되고 있다. 본 연구에서는 다른 매체에 비해 개인의 의견이 좀 더 거침없이 올라오는 SNS의 특징에 주목해 SNS의 텍스트 데이터를 대상으로 하는 평판 분석 기법을 제안한다. 제안 방법은 분석하고자 하는 대상에 대한 SNS 데이터를 수집하여 DB에 저장한 다음, 광고 제거 과정과 자동 띄어쓰기 과정 및 형태소 분석을 거친 후 감성 포함 여부 확인 과정과 극성 분류 과정으로 구성된다. 평판 분석을 위해 본 연구에서는 감성 단어 사전의 쾌-불쾌 수치와 활성화 수치를 사용한다. 분석 결과 모든 문서에 대한 극성 분류 정확도는 55%였고, 감성 포함 여부 확인 과정이 올바르게 수행된 문서에 대한 극성 분류 정확도는 82%였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.975-977
• /
• 2020

감정 분석은 문서의 주관적인 감정, 의견, 기분을 파악하기 위한 방법으로 소셜 미디어, 온라인 리뷰 등 다양한 분야에서 활용된다. 문서 내 텍스트가 나타내는 단어와 문맥을 기반으로 감정 수치를 계산하여 긍정 또는 부정 감정을 결정한다. 2015년에 구축된 네이버 영화평 데이터 20 만개에 12 만개를 추가 구축하여 감정 분석 연구를 진행하였으며 언어 모델로는 최근 자연어처리 분야에서 높은 성능을 보여주는 BERT 모델을 이용하였다. 감정 분석 기법으로는 LSTM(Long Short-Term Memory) 등 기존의 기계학습 기법과 구글의 다국어 BERT 모델, 그리고 KoBERT 모델을 이용하여 감정 분석의 성능을 비교하였으며, KoBERT 모델이 89.90%로 가장 높은 성능을 보여주었다.

• The Journal of the Korea Contents Association
• /
• v.15 no.6
• /
• pp.179-190
• /
• 2015

The current movie world is called the era of faction hot-wind by the continuous hits of faction films. The interpretation of the missing 15 days in the Annals of the Joseon Dynasty during Gwang-hae's reign based on one sentence in the record makes 'faction' that there was another king, drives audiences to absorption and imagination in the faction film < Gwang-hae: The Man Who Became King >. Furthermore, this film redefined historical king Gwang-hae as an ambivalent image through Gwang-hae and Ha-sun who filled the role as the king in it. Also, this film was appraised by reviews of reinterpretation of the image of leader who people want and hit success when the film released before the season of the presidential election. This thesis considers 'Faction' which is marked as a new image content and analyzes the film < Gwang-hae: The Man Who Became King > which is listed as Korea's all-time sixth highest grossing film with 12,323,555 tickets sold nationwide by three sections; < Gwang-hae: The Man Who Became King > as faction film, two images of Gwang-hae, and the appropriateness of film release time. In conclusion, the film < Gwang-hae: The Man Who Became King >. succeeded since it communicated with people to satisfy their wishes and taste. It would be necessary to study and analyze the basic connection between the trend of movies and Strategic elements of the box-office results, and a significant stride for progression of the movies.

• (The)Study of the Eastern Classic
• /
• no.69
• /
• pp.509-530
• /
• 2017

The purpose f this thesis is to examine the reality of Min Sha-pyeong, which led to life in the end of the Koryo Dynasty. Min Sha-pyeong was able to conduct academic exchanges through active negotiations with various scholars at the time. After passing the civil service exam at the age of 21, Min Sha-pyeong acted in various positions and remained loyal to the government. Min Sha-pyeong, who frequently met with Lee Je-hyun, Baek Mun-bo and Lee-saek, exchanged opinions. Sometimes Baek Mun-bo gathered together and always joined him when drinking. Lee-saek was convinced that his poetry would continue to inspire. The time when Min Sha-pyeong was active very confusing at home and abroad. In the end of the Koryo Dynasty, the national operating system was unstable due to the poor land and the suffering of the afflicted people, who suffered from frequent in vasions of Japan. At the time, the corruption and the suffering of the people were serious. Min Sha-pyeong refers to the reality of the people who love the people, reflecting the lives of the people living in poverty. Min Sha-pyeong thinks life without loyality is not a normal life. If I had a desire, I realized that the riches of wealth would wane someday. Min Sha-pyeong hoped that he would be relieved of his sympathy and would be relieved of their position in sympathy ith the people. Here, youy can see the reality of the people in Min Sha-pyeong is clearly revealed.

• Journal of Convergence for Information Technology
• /
• v.10 no.10
• /
• pp.40-46
• /
• 2020

With the development of the Internet, users share their experiences and opinions. Since related keywords are used witho0ut considering information such as the general emotion or genre of an unstructured document such as a movie review, the sensitivity accuracy according to the appropriate emotional situation is impaired. Therefore, we propose a system that predicts emotions based on information such as the genre to which the unstructured document created by users belongs or overall emotions. First, representative keyword related to emotion sets such as Joy, Anger, Fear, and Sadness are extracted from the unstructured document, and the normalized weights of the emotional feature words and information of the unstructured document are trained in a system that combines CNN and LSTM as a training set. Finally, by testing the refined words extracted through movie information, morpheme analyzer and n-gram, emoticons, and emojis, it was shown that the accuracy of emotion prediction using emotions and F-measure were improved. The proposed prediction system can predict sentiment appropriately according to the situation by avoiding the error of judging negative due to the use of sad words in sad movies and scary words in horror movies.

• Smart Media Journal
• /
• v.9 no.4
• /
• pp.144-151
• /
• 2020

In a mobile environment, communication takes place via SMS text messages. Vocabularies used in SMS texts can be expected to use vocabularies of different classes from those used in general Korean literary style sentence. For example, in the case of a typical literary style, the sentence is correctly initiated or terminated and the sentence is well constructed, while SMS text corpus often replaces the component with an omission and a brief representation. To analyze these vocabulary usage characteristics, the existing colloquial style corpus and the literary style corpus are used. The experiment compares and analyzes the vocabulary use characteristics of the colloquial corpus SMS text corpus and the Naver Sentiment Movie Corpus, and the written Korean written corpus. For the comparison and analysis of vocabulary for each corpus, the part of speech tag adjective (VA) was used as a standard, and a distinctive collexeme analysis method was used to measure collostructural strength. As a result, it was confirmed that adjectives related to emotional expression such as'good-','sorry-', and'joy-' were preferred in the SMS text corpus, while adjectives related to evaluation expressions were preferred in the Naver Sentiment Movie Corpus. The word embedding was used to automatically construct a sentiment lexicon based on the extracted adjectives with high collostructural strength, and a total of 343,603 sentiment representations were automatically built.

• The Journal of Society for e-Business Studies
• /
• v.18 no.4
• /
• pp.315-326
• /
• 2013

Users in social media post various types of opinions such as product reviews and movie reviews. It is a common trend that customers get assistance from the opinions in making their decisions. However, as opinion usage grows, distorted feedbacks also have increased. For example, exaggerated positive opinions are posted for promoting target products. So are negative opinions which are far from common evaluations. Finding these biased opinions becomes important to keep social media reliable. Techniques of opinion mining (or sentiment analysis) have been developed to determine sentiment polarity of opinionated documents. These techniques can be utilized for finding the biased opinions. However, the previous techniques have some drawback. They categorize the text into only positive and negative, and they also need a large amount of training data to build the classifier. In this paper, we propose methods for discovering the biased opinions which are skewed from the overall common opinions. The methods are based on angle based outlier detection and personalized PageRank, which can be applied without training data. We analyze the performance of the proposed techniques by presenting experimental results on a movie review dataset.

• Knowledge Management Research
• /
• v.16 no.2
• /
• pp.213-226
• /
• 2015

This study investigates the effects of the volume and valence of the movie reviews on the weekly box-office revenues. Existing literature shows that only the volume of movie reviews influences the box office results, but not valence. However, it has limitations in that it includes only the positivity or negativity ratio of the reviews, not the strength of the valence. In order to overcome such limitations, this study includes the degree of valence. This study used approximately 1.3 million reviews about 300 movies as the sample which was collected from a movie review site in an online portal, that is, movie.naver.com. SPSS was used to test the proposed model. The results of this study show different findings compared to those of the previous studies. First, the volume of movie reviews has been a consistent predictor of the box office success throughout the study periods. Second, the ratio of positive reviews has no impact on the first week's results, but shows significant effects on the box office results during the second week. Third, regarding the degree of positivity or negativity in reviews, the degree of positivity has a significant impact on the box office results only during the first week, while the degree of negativity does not have any significant effects on the results. However, from the second week, the situation is reversed; that is, only the degree of negativity has a significant impact on the box office results, but not the positivity.

• Journal of Popular Narrative
• /
• v.26 no.4
• /
• pp.77-114
• /
• 2020

This article aims to examine the Sinpa of Along With the Gods: The Two Worlds. Along with the Gods: The Two Worlds was a box office hit with a 10 million attendance mark, but it was also criticized as a 'Korean Sinpa' at the time of its release. The original version of Along with the Gods is a Webtoon called Singwahamkke in Korean. The popularity of Singwahamkke and its adaptation, Along with the Gods was enormous, which prompted a very active research to be carried about the work. However there are only a few articles which analyze the Along with the Gods: The Two Worlds focusing on the Sinpa, even though the Sinpa of the Along with the Gods: The Two Worlds was a highly controversial issue when the movie was released. In this regard, this article tries to examine the Sinpa of the Along with the Gods: The Two Worlds closely, especially by comparing it with the original webtoon Singwahamkke Jeoseung. The body part of this article is composed of three major parts: chapters 2, 3, and 4. Chapter 2 contains an in depth explanation about the notion of Sinpa, the main conceptual research tool for this study. In chapter 3, the original webtoon Singwahamkke Jeoseung is examined closely. This chapter analyzes the 'Sinpajeok moment' in Singwahamkke Jeoseung and argues that despite the presence of Sinpa elements, the webtoon cannot be considered a 'Sinpajeok text'. On the other hand the main subject of chapter 4 is discovering what effect the adaptation from webtoon to movie had on this work, with a particular focus on the gender of Sinpa and Kim Ja-hong. Chapter 5, which corresponds to the conclusion, briefly evaluates the social significance of the controversy arisen in South Korea about the Sinpa in Along with the Gods: The Two Worlds. Sinpa is one of the most repeated code in the realm of Korean popular narrative. This is why the Sinpa of contemporary text is examined continuously even though there are already plenty of studies on the Sinpa. Everyone has called Along with the Gods: The Two Worlds Sinpa but no one has properly analyzed it. It is hoped that this article which closesly examined the Sinpa in Along with the Gods: The Two Worlds contribute to the field of Sinpa. It is also expected that this article can find appropriate contextual meaning of the series of Along with the Gods.