• 한국컴퓨터정보학회논문지
• /
• 제24권12호
• /
• pp.1-7
• /
• 2019

머신 러닝의 심층 개발로 딥 러닝 방법은 특히 CNN(Convolution Neural Network)에서 큰 진전을 이루었다. 전통적인 텍스트 정서 분류 방법과 비교할 때 딥 러닝 기반 CNN은 복잡한 다중 레이블 및 다중 분류 실험의 텍스트 분류 및 처리에서 크게 발전하였다. 그러나 텍스트 정서 분류를 위한 신경망에도 문제가 있다. 이 논문에서는 LSTM (Long-Short Term Memory network) 및 CNN 딥 러닝 방법에 기반 한 융합 모델을 제안하고, 다중 카테고리 뉴스 데이터 세트에 적용하여 좋은 결과를 얻었다. 실험에 따르면 딥 러닝을 기반으로 한 융합 모델이 텍스트 정서 분류의 예측성과 정확성을 크게 개선하였다. 본 논문에서 제안한 방법은 모델을 최적화하고 그 모델의 성능을 개선하는 중요한 방법이 될 것이다.

• Journal of information and communication convergence engineering
• /
• 제17권1호
• /
• pp.41-48
• /
• 2019

In recent years, sentiment analysis research has become popular. The research results of sentiment analysis have achieved remarkable results in practical applications, such as in Amazon's book recommendation system and the North American movie box office evaluation system. Analyzing big data based on user preferences and evaluations and recommending hot-selling books and hot-rated movies to users in a targeted manner greatly improve book sales and attendance rate in movies [1, 2]. However, traditional machine learning-based sentiment analysis methods such as the Classification and Regression Tree (CART), Support Vector Machine (SVM), and k-nearest neighbor classification (kNN) had performed poorly in accuracy. In this paper, an improved kNN classification method is proposed. Through the improved method and normalizing of data, the purpose of improving accuracy is achieved. Subsequently, the three classification algorithms and the improved algorithm were compared based on experimental data. Experiments show that the improved method performs best in the kNN classification method, with an accuracy rate of 11.5% and a precision rate of 20.3%.

• Journal of information and communication convergence engineering
• /
• 제16권2호
• /
• pp.106-113
• /
• 2018

Although deep learning methods of convolutional neural networks (CNNs) and long-/short-term memory (LSTM) are widely used for text categorization, they still have certain shortcomings. CNNs require that the text retain some order, that the pooling lengths be identical, and that collateral analysis is impossible; In case of LSTM, it requires the unidirectional operation and the inputs/outputs are very complex. Against these problems, we thus improved these traditional deep learning methods in the following ways: We created collateral CNNs accepting disorder and variable-length pooling, and we removed the input/output gates when creating bidirectional LSTMs. We have used four benchmark datasets for topic and sentiment classification using the new methods that we propose. The best results were obtained by combining LTSM regional embeddings with data convolution. Our method is better than all previous methods (including deep learning methods) in terms of topic and sentiment classification.

• 산업경영시스템학회지
• /
• 제46권1호
• /
• pp.32-41
• /
• 2023

Recently, many studies are being conducted to extract emotion from text and verify its information power in the field of finance, along with the recent development of big data analysis technology. A number of prior studies use pre-defined sentiment dictionaries or machine learning methods to extract sentiment from the financial documents. However, both methods have the disadvantage of being labor-intensive and subjective because it requires a manual sentiment learning process. In this study, we developed a financial sentiment dictionary that automatically extracts sentiment from the body text of analyst reports by using modified Bayes rule and verified the performance of the model through a binary classification model which predicts actual stock price movements. As a result of the prediction, it was found that the proposed financial dictionary from this research has about 4% better predictive power for actual stock price movements than the representative Loughran and McDonald's (2011) financial dictionary. The sentiment extraction method proposed in this study enables efficient and objective judgment because it automatically learns the sentiment of words using both the change in target price and the cumulative abnormal returns. In addition, the dictionary can be easily updated by re-calculating conditional probabilities. The results of this study are expected to be readily expandable and applicable not only to analyst reports, but also to financial field texts such as performance reports, IR reports, press articles, and social media.

• Journal of Information Processing Systems
• /
• 제15권3호
• /
• pp.500-519
• /
• 2019

The blooming of social media has simulated interest in sentiment analysis. Sentiment analysis aims to determine from a specific piece of content the overall attitude of its author in relation to a specific item, product, brand, or service. In sentiment analysis, the focus is on the subjective sentences. Hence, in order to discover and extract the subjective information from a given text, researchers have applied various methods in computational linguistics, natural language processing, and text analysis. The aim of this paper is to provide an in-depth up-to-date study of the sentiment analysis algorithms in order to familiarize with other works done in the subject. The paper focuses on the main tasks and applications of sentiment analysis. State-of-the-art algorithms, methodologies and techniques have been categorized and summarized to facilitate future research in this field.

• 디지털융복합연구
• /
• 제18권2호
• /
• pp.249-259
• /
• 2020

본 연구는 전기자동차(EV)에 대한 소셜미디어 데이터를 기반으로 감성분석 (SA)과 속성선택 (FS)방법을 적용하여 전기자동차에 대한 일반 사람들의 의견을 보다 효과적이고 정확히 예측할 수 있는 새로운 방법론을 제안한다. 구체적인 방법은 다음과 같다. 첫째, 유튜브에 있는 전기자동차에 대한 일반 사람들의 의견을 추출하였다. 둘째, 분석의 효과성을 증대하기 위하여 카이 스퀘어, 정보획득량, 릴리프에프 등 세가지 속성선택 방법을 적용하였다. 그 결과 로지스틱 회귀분석 및 서포트 벡터 머신 분류 기법에서 가장 의미있는 결과를 얻을 수 있다는 것이 확인되었다.

• 지능정보연구
• /
• 제20권1호
• /
• pp.133-148
• /
• 2014

최근 다양한 정보채널들의 등장으로 인해 빅데이터에 대한 관심이 높아지고 있다. 이와 같은 현상의 가장 큰 원인은, 스마트기기의 사용이 활성화 됨에 따라 사용자가 생성하는 텍스트, 사진, 동영상과 같은 비정형 데이터의 양이 크게 증가하고 있는 것에서 찾을 수 있다. 특히 비정형 데이터 중에서도 텍스트 데이터의 경우, 사용자들의 의견 및 다양한 정보를 명확하게 표현하고 있다는 특징이 있다. 따라서 이러한 텍스트에 대한 분석을 통해 새로운 가치를 창출하고자 하는 시도가 활발히 이루어지고 있다. 텍스트 분석을 위해 필요한 기술은 대표적으로 텍스트 마이닝과 오피니언 마이닝이 있다. 텍스트 마이닝과 오피니언 마이닝은 모두 텍스트 데이터를 입력 데이터로 사용할 뿐 아니라 파싱, 필터링 등 자연어 처리기술을 사용한다는 측면에서 많은 공통점을 갖고 있다. 특히 문서의 분류 및 예측에 있어서 목적 변수가 긍정 또는 부정의 감성을 나타내는 경우에는, 전통적 텍스트 마이닝, 또는 감성사전 기반의 오피니언 마이닝의 두 가지 방법론에 의해 오피니언 분류를 수행할 수 있다. 따라서 텍스트 마이닝과 오피니언 마이닝의 특징을 구분하는 가장 명확한 기준은 입력 데이터의 형태, 분석의 목적, 분석의 결과물이 아닌 감성사전의 사용 여부라고 할 수 있다. 따라서 본 연구에서는 오피니언 분류라는 동일한 목적에 대해 텍스트 마이닝과 오피니언 마이닝을 각각 사용하여 예측 모델을 수립하는 과정을 비교하고, 결과로 도출된 모델의 예측 정확도를 비교하였다. 오피니언 분류 실험을 위해 영화 리뷰 2,000건에 대한 실험을 수행하였으며, 실험 결과 오피니언 마이닝을 통해 수립된 모델이 텍스트 마이닝 모델에 비해 전체 구간의 예측 정확도 평균이 높게 나타나고, 예측의 확실성이 강한 문서일수록 예측 정확성이 높게 나타나는 일관적인 성향을 나타내는 등 더욱 바람직한 특성을 보였다.

• 한국IT서비스학회지
• /
• 제18권1호
• /
• pp.187-200
• /
• 2019

Bankruptcy prediction model is an issue that has consistently interested in various fields. Recently, as technology for dealing with unstructured data has been developed, researches applied to business model prediction through text mining have been activated, and studies using this method are also increasing in bankruptcy prediction. Especially, it is actively trying to improve bankruptcy prediction by analyzing news data dealing with the external environment of the corporation. However, there has been a lack of study on which news is effective in bankruptcy prediction in real-time mass-produced news. The purpose of this study was to evaluate the high impact news on bankruptcy prediction. Therefore, we classify news according to type, collection period, and analyzed the impact on bankruptcy prediction based on sentiment analysis. As a result, artificial neural network was most effective among the algorithms used, and commentary news type was most effective in bankruptcy prediction. Column and straight type news were also significant, but photo type news was not significant. In the news by collection period, news for 4 months before the bankruptcy was most effective in bankruptcy prediction. In this study, we propose a news classification methods for sentiment analysis that is effective for bankruptcy prediction model.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.818-833
• /
• 2021

To address the problems of low precision rate, insufficient feature extraction, and poor contextual ability in existing text sentiment analysis methods, a mixed model account of a CNN-BiLSTM-TE (convolutional neural network, bidirectional long short-term memory, and topic extraction) model was proposed. First, Chinese text data was converted into vectors through the method of transfer learning by Word2Vec. Second, local features were extracted by the CNN model. Then, contextual information was extracted by the BiLSTM neural network and the emotional tendency was obtained using softmax. Finally, topics were extracted by the term frequency-inverse document frequency and K-means. Compared with the CNN, BiLSTM, and gate recurrent unit (GRU) models, the CNN-BiLSTM-TE model's F1-score was higher than other models by 0.0147, 0.006, and 0.0052, respectively. Then compared with CNN-LSTM, LSTM-CNN, and BiLSTM-CNN models, the F1-score was higher by 0.0071, 0.0038, and 0.0049, respectively. Experimental results showed that the CNN-BiLSTM-TE model can effectively improve various indicators in application. Lastly, performed scalability verification through a takeaway dataset, which has great value in practical applications.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2019년도 제60차 하계학술대회논문집 27권2호
• /
• pp.385-386
• /
• 2019

This paper proposes a fusion model based on Long-Short Term Memory networks (LSTM) and CNN deep learning methods, and applied to multi-category news datasets, and achieved good results. Experiments show that the fusion model based on deep learning has greatly improved the precision and accuracy of text sentiment classification.