• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.3
• /
• pp.274-279
• /
• 2015

The main goal of this research is to build a sentiment analysis system which automatically determines user opinions of the Stanford Sentiment Treebank in terms of three sentiments such as positive, negative, and neutral. Firstly, sentiment sentences are POS tagged and parsed to dependency structures. All nodes of the Treebank and their polarities are automatically extracted from the Treebank. We train two Support Vector Machines models. One is for a node level classification and the other is for a sentence level. We have tried various type of features such as word lexicons, POS tags, Sentiment lexicons, head-modifier relations, and sibling relations. Though we acquired 74.2% in accuracy on the test set for 3 class node level classification and 67.0% for 3 class sentence level classification, our experimental results for 2 class classification are comparable to those of the state of art system using the same corpus.

• Korean Journal of Cognitive Science
• /
• v.19 no.4
• /
• pp.499-517
• /
• 2008

In this paper, we propose an effective emotion feature extraction method for Korean and evaluate their availability in sentiment classification. Korean emotion features are expanded from several representative emotion words and they play an important role in building in an effective sentiment classification system. Firstly, synonym information of English word thesaurus is used to extract effective emotion features and then the extracted English emotion features are translated into Korean. To evaluate the extracted Korean emotion features, we represent each document using the extracted features and classify it using SVM(Support Vector Machine). In experimental results, the sentiment classification system using the extracted Korean emotion features obtained more improved performance(14.1%) than the system using content-words based features which have generally used in common text classification systems.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.12
• /
• pp.1-7
• /
• 2019

With the in-depth development of machine learning, the deep learning method has made great progress, especially with the Convolution Neural Network(CNN). Compared with traditional text sentiment classification methods, deep learning based CNNs have made great progress in text classification and processing of complex multi-label and multi-classification experiments. However, there are also problems with the neural network for text sentiment classification. In this paper, we propose 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. This method will become an important way to optimize the model and improve the performance of the model.

• Journal of Korean Society for Quality Management
• /
• v.48 no.3
• /
• pp.421-431
• /
• 2020

Purpose: The purpose of this study is to compare and analyze the tokenizer in natural language processing for customer satisfaction in sentiment analysis. Methods: In this study, a supervised learning-based tokenizer Mecab-Ko and an unsupervised learning-based tokenizer SentencePiece were used for comparison. Three algorithms: Naïve Bayes, k-Nearest Neighbor, and Decision Tree were selected to compare the performance of each tokenizer. For performance comparison, three metrics: accuracy, precision, and recall were used in the study. Results: The results of this study are as follows; Through performance evaluation and verification, it was confirmed that SentencePiece shows better classification performance than Mecab-Ko. In order to confirm the robustness of the derived results, independent t-tests were conducted on the evaluation results for the two types of the tokenizer. As a result of the study, it was confirmed that the classification performance of the SentencePiece tokenizer was high in the k-Nearest Neighbor and Decision Tree algorithms. In addition, the Decision Tree showed slightly higher accuracy among the three classification algorithms. Conclusion: The SentencePiece tokenizer can be used to classify and interpret customer sentiment based on online reviews in Korean more accurately. In addition, it seems that it is possible to give a specific meaning to a short word or a jargon, which is often used by users when evaluating products but is not defined in advance.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.1
• /
• 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 KIISE:Databases
• /
• v.36 no.4
• /
• pp.254-262
• /
• 2009

As the trend of e-business activities develop, customers come into contact with products through on-line shopping sites and lots of customers refer product reviews before the purchasing on-line. However, as the volume of product reviews grow, it takes a great deal of time and effort for customers to read and evaluate voluminous product reviews. Lately, attention is being paid to Opinion Mining(OM) as one of the effective solutions to this problem. In this paper, we propose an efficient method for opinion sentiment classification of product reviews using product specific context information of words occurred in the reviews. We define the context information of words and propose the application of context for sentiment classification and we show the performance of our method through the experiments. Additionally, in case of word corpus construction, we propose the method to construct word corpus automatically using the review texts and review scores in order to prevent traditional manual process. In consequence, we can easily get exact sentiment polarities of opinion words in product reviews.

• Journal of Information Technology Services
• /
• v.20 no.3
• /
• pp.75-86
• /
• 2021

As artificial intelligence is actively studied, chatbot systems are being applied to various fields. In particular, many chatbot systems for psychological counseling have been studied that can comfort modern people. However, while most psychological counseling chatbots are studied as rule-base and deep learning-based chatbots, there are large limitations for each chatbot. To overcome the limitations of psychological counseling using such chatbots, we proposes a novel psychological counseling AI chatbot system. The proposed system consists of a GPT-2 model that generates output sentence for Korean input sentences and an Electra model that serves as sentiment analysis and anxiety cause classification, which can be provided with psychological tests and collective intelligence functions. At the same time as deep learning-based chatbots and conversations take place, sentiment analysis of input sentences simultaneously recognizes user's emotions and presents psychological tests and collective intelligence solutions to solve the limitations of psychological counseling that can only be done with chatbots. Since the role of sentiment analysis and anxiety cause classification, which are the links of each function, is important for the progression of the proposed system, we experiment the performance of those parts. We verify the novelty and accuracy of the proposed system. It also shows that the AI chatbot system can perform counseling excellently.

• The Journal of the Korea Contents Association
• /
• v.16 no.10
• /
• pp.393-402
• /
• 2016

To compensate for limited the satisfaction survey currently conducted by Korea Metrological Administration (KMA), a sentiment analysis via a social networking service (SNS) can be utilized. From 2011 to 2014, with the sentiment analysis, Twitter who had commented 'KMA' had collected, then, using $Na{\ddot{i}}ve$ Bayes classification, we were classified into three sentiments: positive, negative, and neutral sentiments. An additional dictionary was made with morphemes appeared only in the positive, negative, and neutral sentiments of basic $Na{\ddot{i}}ve$ Bayes classification, thus the accuracy of sentiment analysis was improved. As a result, when sentiments were classified with a basic $Na{\ddot{i}}ve$ Bayes classification, the training data were reproduced about 75% accuracy rate. Whereas, when classifying with the additional dictionary, it showed 97% accuracy rate. When using the additional dictionary, sentiments of verification data was classified with about 75% accuracy rate. Lower classification accuracy rate would be improved by not only a qualified dictionary that has increased amount of training data, including diverse keywords related to weather, but continuous update of the dictionary. Meanwhile, contrary to the sentiment analysis based on dictionary definition of individual vocabulary, if sentiments are classified into meaning of sentence, increased rate of negative sentiment and change in satisfaction could be explained. Therefore, the sentiment analysis via SNS would be considered as useful tool for complementing surveys in the future.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.34-36
• /
• 2022

In the existing text sentiment analysis models, the entire text is usually directly modeled as a whole, and the hierarchical relationship between text contents is less considered. However, in the practice of sentiment analysis, many texts are mixed with multiple emotions. If the semantic modeling of the whole is directly performed, it may increase the difficulty of the sentiment analysis model to judge the sentiment, making the model difficult to apply to the classification of mixed-sentiment sentences. Therefore, this paper proposes a sentiment analysis model BHGCN that considers the text hierarchy. In this model, the output of hidden states of each layer of BERT is used as a node, and a directed connection is made between the upper and lower layers to construct a graph network with a semantic hierarchy. The model not only pays attention to layer-by-layer semantics, but also pays attention to hierarchical relationships. Suitable for handling mixed sentiment classification tasks. The comparative experimental results show that the BHGCN model exhibits obvious competitive advantages.

• Science of Emotion and Sensibility
• /
• v.13 no.3
• /
• pp.449-458
• /
• 2010

As occasion demands to obtain efficient information from many documents and reviews on the Internet in many kinds of fields, automatic classification of opinion or thought is required. These automatic classification is called sentiment classification, which can be divided into three steps, such as subjective expression classification to extract subjective sentences from documents, sentiment classification to classify whether the polarity of documents is positive or negative, and strength classification to classify whether the documents have weak polarity or strong polarity. The latest studies in Opinion Mining have used N-gram words, lexical phrase pattern, and syntactic phrase pattern, etc. They have not used single word as feature for classification. Especially, patterns have been used frequently as feature because they are more flexible than N-gram words and are also more deterministic than single word. Theses studies are mainly concerned with English, other studies using patterns for Korean are still at an early stage. Although Korean has a slight difference in the meaning between predicates by the change of endings, which is 'Eomi' in Korean, of declinable words, the earlier studies about Korean opinion classification removed endings from predicates only to extract stems. Finally, this study introduces the earlier studies and methods using pattern for English, uses extracted sentimental patterns from Korean documents, and classifies polarities of these documents. In this paper, it also analyses the influence of the change of endings on performances of opinion classification.