• 한국IT서비스학회지
• /
• 제15권3호
• /
• pp.147-155
• /
• 2016

According to rapid development of technology, web text is growing explosively and attracting many fields as substitution for survey. The user of Facebook is reaching up to 113 million people per month, Twitter is used in various institution or company as a behavioral analysis tool. However, many research has focused on meaning of the text itself. And there is a lack of study for text's creation subject. Therefore, this research consists of sex/age text classification with by using 20,187 Facebook users' posts that reveal the sex and age of the writer. This research utilized Convolution Neural Networks, a type of deep learning algorithms which came into the spotlight as a recent image classifier in web text analyzing. The following result assured with 92% of accuracy for possibility as a text classifier. Also, this research was minimizing the Korean morpheme analysis and it was conducted using a Korean web text to Authorship Attribution. Based on these feature, this study can develop users' multiple capacity such as web text management information resource for worker, non-grammatical analyzing system for researchers. Thus, this study proposes a new method for web text analysis.

• Asia pacific journal of information systems
• /
• 제12권2호
• /
• pp.179-195
• /
• 2002

In this research, we developed an efficient Hangul document classification system for text mining. We mean 'efficient' by maintaining an acceptable classification performance while taking shorter computing time. In our system, given a query document, k documents are first retrieved from the document case base using the k-nearest neighbor technique, which is the main algorithm of case-based reasoning. Then, TFIDF method, which is the traditional vector model in information retrieval technique, is applied to the query document and the k retrieved documents to classify the query document. We call this procedure 'CB_TFIDF' method. The result of our research showed that the classification accuracy of CB_TFIDF was similar to that of traditional TFIDF method. However, the average time for classifying one document decreased remarkably.

• 음성과학
• /
• 제9권3호
• /
• pp.25-34
• /
• 2002

One of the most important factor in the performance of Korean text-to-speech system is the prediction of accentual and intonational phrase boundary. The previous method of prediction shows only the 75-85% which is not proper in the practical and commercial system. Therefore, more accurate prediction must be needed in the practical system. In this study, we propose the simple and more accurate method of the prediction of AP, IP.

• 한국농공학회논문집
• /
• 제49권1호
• /
• pp.23-33
• /
• 2007

Classification results of rural villages provide useful information about rural village characteristics to select similar villages in rural development project; many researches about regional classification have been practiced. Recently rural amenity was introduced as an alternative for rural development, and rural villages have been surveyed to find potential resources for rural development by 'Rural Amenity Resources Survey Project'. Accumulated information through this survey project could be used to classify rural villages. However existing rural classification method using statistical data is not efficient method to use rural amenity resources information described with text. We introduced Information Bottleneck Method (IBM) based on information theory and implemented this method to classification with rural amenity resources information of Yanggang-myen, Yeongdong-gun in Chungbuk province.

• 인터넷정보학회논문지
• /
• 제20권1호
• /
• pp.1-10
• /
• 2019

빅 데이터에서 텍스트 마이닝은 많은 수의 데이터로부터 많은 특징 추출하기 때문에, 클러스터링 및 분류 과정의 계산 복잡도가 높고 분석결과의 신뢰성이 낮아질 수 있다. 특히 텍스트마이닝 과정을 통해 얻는 Term document matrix는 term과 문서간의 특징들을 표현하고 있지만, 희소행렬 형태를 보이게 된다. 본 논문에서는 탐지모델을 위해 텍스트마이닝에서 개선된 GA(Genetic Algorithm)을 이용한 특징 추출 방법을 설계하였다. TF-IDF는 특징 추출에서 문서와 용어간의 관계를 반영하는데 사용된다. 반복과정을 통해 사전에 미리 결정된 만큼의 특징을 선택한다. 또한 탐지모델의 성능 향상을 위해 sparsity score(희소성 점수)를 사용하였다. 스팸메일 세트의 희소성이 높으면 탐지모델의 성능이 낮아져 최적화된 탐지 모델을 찾기가 어렵다. 우리는 fitness function에서 s(F)를 사용하여 희소성이 낮고 TF-IDF 점수가 높은 탐지모델을 찾았다. 또한 제안된 알고리즘을 텍스트 분류 실험에 적용하여 성능을 검증하였다. 결과적으로, 제안한 알고리즘은 공격 메일 분류에서 좋은 성능(속도와 정확도)을 보여주었다.

• 한국전자거래학회지
• /
• 제25권1호
• /
• pp.203-214
• /
• 2020

최근 들어 기술개발 현황, 신규기술 분야 출현, 기술융합과 학제 공동연구, 기술의 트렌드 변화 등을 파악하기 위해 R&D 과제정보, 특허와 같은 기술문서의 분류정보가 많이 활용되고 있다. 이러한 기술문서를 분류하기 위해 주로 텍스트마이닝 기법들이 활용되어 왔다. 그러나 기존 텍스트마이닝 방법들로 기술문서를 분류하기 위해서는 기술문서들을 대표하는 특징들을 직접 추출해야 하는 한계점이 있다. 따라서 본 연구에서는 딥러닝 기반의 BERT모델을 활용하여 기술문서들로부터 자동적으로 문서 특징들을 추출한 후, 이를 문서 분류에 직접 활용하는 모델을 제안하고, 이에 대한 성능을 검증하고자 한다. 이를 위해 텍스트 기반의 국가 R&D 과제 정보를 활용하여 BERT 기반 국가 R&D 과제의 중분류코드 예측 모델을 생성하고 이에 대한 성능을 평가한다.

• 한국산업정보학회논문지
• /
• 제28권5호
• /
• pp.15-30
• /
• 2023

근래에 트랜스포머(Transformer) 구조를 기초로 하는 ChatGPT와 같은 생성모델이 크게 주목받고 있다. 트랜스포머는 다양한 신경망 모델에 응용되는데, 구글의 BERT(bidirectional encoder representations from Transformers) 문장생성 모델에도 사용된다. 본 논문에서는, 한글로 작성된 영화 리뷰에 대한 댓글이 긍정적인지 부정적인지를 판단하는 텍스트 이진 분류모델을 생성하기 위해서, 사전 학습되어 공개된 BERT 다국어 문장생성 모델을 미세조정(fine tuning)한 후, 새로운 한국어 학습 데이터셋을 사용하여 전이학습(transfer learning) 시키는 방법을 제안한다. 이를 위해서 104 개 언어, 12개 레이어, 768개 hidden과 12개의 집중(attention) 헤드 수, 110M 개의 파라미터를 사용하여 사전 학습된 BERT-Base 다국어 문장생성 모델을 사용했다. 영화 댓글을 긍정 또는 부정 분류하는 모델로 변경하기 위해, 사전 학습된 BERT-Base 모델의 입력 레이어와 출력 레이어를 미세 조정한 결과, 178M개의 파라미터를 가지는 새로운 모델이 생성되었다. 미세 조정된 모델에 입력되는 단어의 최대 개수 128, batch_size 16, 학습 횟수 5회로 설정하고, 10,000건의 학습 데이터셋과 5,000건의 테스트 데이터셋을 사용하여 전이 학습시킨 결과, 정확도 0.9582, 손실 0.1177, F1 점수 0.81인 문장 감정 이진 분류모델이 생성되었다. 데이터셋을 5배 늘려서 전이 학습시킨 결과, 정확도 0.9562, 손실 0.1202, F1 점수 0.86인 모델을 얻었다.

• 대한한의정보학회지
• /
• 제15권1호
• /
• pp.1-10
• /
• 2009

In these days everyone search the information easily with the Internet as the rapid distribution and active usage of the Internet. The search engines were developed specially to accuracy of information retrieval. User search the information more quickly and variously with them. The search portal system will be embossed with representation and basic services. The Internet user needs the result of text, image and video, knowledge search. The keyword based search is used generally for getting result of the information retrieval and another method is category based search. This paper investigates the classification of knowledge search structure for oriental medicine in market leader of search portal system by ranking web site. As a result, each classification system is unified and there is a possibility of getting up a many confusion to the user who approaches with classification systematic search method. This treatise proposed the improved oriental medicine classification system of internet information retrieval in knowledge search area. if the service provider amends about the classification system, there will be able to guarantee the compatibility of data. Also the proper access path of the knowledge which seeks is secured to user.

• 한국안전학회지
• /
• 제32권5호
• /
• pp.179-185
• /
• 2017

Accident analysis is an essential process to make basic data for accident prevention. Most researches depend on survey data and accident statistics to analyze accidents, but these kinds of data are not sufficient for systematic and detailed analysis. We, in this paper, propose an accident classification model that extracts task type, original cause materials, accident type, and the number of deaths from accident reports. The classification model is a support vector machine (SVM) with word occurrence features, and these features are selected based on mutual information. Experiment shows that the proposed model can extract task type, original cause materials, accident type, and the number of deaths with almost 100% accuracy. We also develop an accident ontology to express the information extracted by the classification model. Finally, we illustrate how the proposed classification model and ontology effectively works for the accident analysis. The classification model and ontology are expected to effectively analyze various accidents.

• International Journal of Computer Science & Network Security
• /
• 제23권5호
• /
• pp.1-6
• /
• 2023

Text mining (TM) is most widely used to process the various unstructured text documents and process the data present in the various domains. The other name for text mining is text classification. This domain is most popular in many domains such as movie reviews, product reviews on various E-commerce websites, sentiment analysis, topic modeling and cyber bullying on social media messages. Cyber-bullying is the type of abusing someone with the insulting language. Personal abusing, sexual harassment, other types of abusing come under cyber-bullying. Several existing systems are developed to detect the bullying words based on their situation in the social networking sites (SNS). SNS becomes platform for bully someone. In this paper, An Enhanced text mining approach is developed by using Ensemble Algorithm (ETMA) to solve several problems in traditional algorithms and improve the accuracy, processing time and quality of the result. ETMA is the algorithm used to analyze the bullying text within the social networking sites (SNS) such as facebook, twitter etc. The ETMA is applied on synthetic dataset collected from various data a source which consists of 5k messages belongs to bullying and non-bullying. The performance is analyzed by showing Precision, Recall, F1-Score and Accuracy.