• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2334-2347
• /
• 2023

Metaverse services generate text data, data of ubiquitous computing, in real-time to analyze user emotions. Analysis of user emotions is an important task in metaverse services. This study aims to classify user sentiments using deep learning and pre-trained language models based on the transformer structure. Previous studies collected data from a single platform, whereas the current study incorporated the review data as "Metaverse" keyword from the YouTube and Google Play Store platforms for general utilization. As a result, the Bidirectional Encoder Representations from Transformers (BERT) and Robustly optimized BERT approach (RoBERTa) models using the soft voting mechanism achieved a highest accuracy of 88.57%. In addition, the area under the curve (AUC) score of the ensemble model comprising RoBERTa, BERT, and A Lite BERT (ALBERT) was 0.9458. The results demonstrate that the ensemble combined with the RoBERTa model exhibits good performance. Therefore, the RoBERTa model can be applied on platforms that provide metaverse services. The findings contribute to the advancement of natural language processing techniques in metaverse services, which are increasingly important in digital platforms and virtual environments. Overall, this study provides empirical evidence that sentiment analysis using deep learning and pre-trained language models is a promising approach to improving user experiences in metaverse services.

• Journal of the Korean Society for information Management
• /
• v.39 no.1
• /
• pp.91-117
• /
• 2022

The number of depressed patients in Korea and around the world is rapidly increasing every year. However, most of the mentally ill patients are not aware that they are suffering from the disease, so adequate treatment is not being performed. If depressive symptoms are neglected, it can lead to suicide, anxiety, and other psychological problems. Therefore, early detection and treatment of depression are very important in improving mental health. To improve this problem, this study presented a deep learning-based depression tendency model using Korean social media text. After collecting data from Naver KonwledgeiN, Naver Blog, Hidoc, and Twitter, DSM-5 major depressive disorder diagnosis criteria were used to classify and annotate classes according to the number of depressive symptoms. Afterwards, TF-IDF analysis and simultaneous word analysis were performed to examine the characteristics of each class of the corpus constructed. In addition, word embedding, dictionary-based sentiment analysis, and LDA topic modeling were performed to generate a depression tendency classification model using various text features. Through this, the embedded text, sentiment score, and topic number for each document were calculated and used as text features. As a result, it was confirmed that the highest accuracy rate of 83.28% was achieved when the depression tendency was classified based on the KorBERT algorithm by combining both the emotional score and the topic of the document with the embedded text. This study establishes a classification model for Korean depression trends with improved performance using various text features, and detects potential depressive patients early among Korean online community users, enabling rapid treatment and prevention, thereby enabling the mental health of Korean society. It is significant in that it can help in promotion.

• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1290-1295
• /
• 2017

Document classification, a task of classifying the category of each document based on text, is one of the fundamental areas for natural language processing. Document classification may be used in various fields such as topic classification and sentiment classification. Neural network models for document classification can be divided into two categories: word-level models and character-level models that treat words and characters as basic units respectively. In this study, we propose a neural network model that combines character-level and word-level models to improve performance of document classification. The proposed model extracts the feature vector of each word by combining information obtained from a word embedding matrix and information encoded by a character-level neural network. Based on feature vectors of words, the model classifies documents with a hierarchical structure wherein recurrent neural networks with attention mechanisms are used for both the word and the sentence levels. Experiments on real life datasets demonstrate effectiveness of our proposed model.

• Journal of Advanced Marine Engineering and Technology
• /
• v.34 no.6
• /
• pp.871-879
• /
• 2010

In this paper, we present a system that classifies comments on a news article into a user opinion called a polarity (positive or negative). The system is a kind of document classification system for comments and is based on machine learning techniques like support vector machine. Unlike normal documents, comments have their body that can influence classifying their opinions as polarities. In this paper, we propose a feature weighting scheme using such characteristics of comments and several resources for opinion classification. Through our experiments, the weighting scheme have turned out to be useful for opinion classification in comments on Korean news articles. Also Korean character n-grams (bigram or trigram) have been revealed to be helpful for opinion classification in comments including lots of Internet words or typos. In the future, we will apply this scheme to opinion analysis of comments of product reviews as well as news articles.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.5
• /
• pp.11-17
• /
• 2009

It's a trend that the proportion of using an internet messenger among on-line communication methods is getting increased. However, there are not many applications which efficiently utilize these messenger communication data. Messenger communication data have specific characteristics that reflect the user's linguistic habits. The linguistic habits are revealed through frequently used words and emoticons, and user's emotions can be grasped by these. This paper proposes the method that efficiently classifies the emotions of a messenger user using frequently used words or symbols. The emotion classifier from repeated experiments achieves high accuracy of more than 95%.

• Journal of Internet Computing and Services
• /
• v.17 no.3
• /
• pp.107-113
• /
• 2016

Following the recent advancement in the use of social networks, a vast amount of different online reviews is created. These variable online reviews which provide feedback data of contents' are being used as sources of valuable information to both contents' users and providers. With the increasing importance of online reviews, studies on opinion mining which analyzes online reviews to extract opinions or evaluations, attitudes and emotions of the writer have been on the increase. However, previous sentiment analysis techniques of opinion-mining focus only on the classification of reviews into positive or negative classes but does not include detailed information analysis of the user's satisfaction or sentiment grounds. Also, previous designs of the sentiment analysis technique only applied to one content domain that is, either product or movie, and could not be applied to other contents from a different domain. This paper suggests a sentiment analysis technique that can analyze detailed satisfaction of online reviews and extract detailed information of the satisfaction level. The proposed technique can analyze not only one domain of contents but also a variety of contents that are not from the same domain. In addition, we design a system based on Hadoop to process vast amounts of data quickly and efficiently. Through our proposed system, both users and contents' providers will be able to receive feedback information more clearly and in detail. Consequently, potential users who will use the content can make effective decisions and contents' providers can quickly apply the users' responses when developing marketing strategy as opposed to the old methods of using surveys. Moreover, the system is expected to be used practically in various fields that require user comments.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.5
• /
• pp.243-253
• /
• 2012

An opinion mining technique which was developed from document classification in area of data mining now becomes a common interest in domestic as well as international industries. The core of opinion mining is to decide precisely whether an opinion document is a positive or negative one. Although many related approaches have been previously proposed, a classification accuracy was not satisfiable enough to applying them in practical applications. A opinion documents written in Korean are not easy to determine a polarity automatically because they often include various and ungrammatical words in expressing subjective opinions. Proposed in this paper is a new approach of classification of opinion documents, which considers only a frequency of word patterns and excludes the grammatical factors as much as possible. In proposed method, we express a document into a bag of words and then apply a learning algorithm using a frequency of word patterns, and finally decide the polarity of the document using a score function. Additionally, we also present the experiment results for evaluating the accuracy of the proposed method.

• Journal of Korea Trade
• /
• v.24 no.8
• /
• pp.39-62
• /
• 2020

Purpose - Korean exports account for a vast proportion of Korean GDP, and large volumes of Korean products are sold in the United States. Identifying and characterizing actual and potential product hazards related to Korean products is critical to safeguard Korean export trade, as severe quality issues can impair Korea's reputation and reduce global consumer confidence in Korean products. In this study, we develop country-of-origin-based product risk analysis methods for social media with a specific focus on Korean-labeled products, for the purpose of safeguarding Korean export trade. Design/methodology - We employed two social media datasets containing consumer-generated product reviews. Sentiment analysis is a popular text mining technique used to quantify the type and amount of emotion that is expressed in the text. It is a useful tool for gathering customer opinions regarding products. Findings - We document and discuss the specific potential risks found in Korean-labeled products and explain their implications for safeguarding Korean export trade. Finally, we analyze the false positive matches that arise from the established dictionaries that were used for risk discovery and utilize these classification errors to suggest opportunities for the future refinement of the associated automated text analytic methods. Originality/value - Various studies have used online feedback from social media to analyze product defects. However, none of them links their findings to trade promotion and the protection of a specific country's exports. Therefore, it is important to fill this research gap, which could help to safeguard export trade in Korea.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.79-80
• /
• 2022

본 논문에서는 데이터 증강 기법 중 하나인 EDA를 적용하여 BERT 기반의 감성 분류 언어 모델을 만들고, 성능 개선 방법을 제안한다. EDA(Easy Data Augmentation) 기법은 테이터가 한정되어 있는 환경에서 SR(Synonym Replacement), RI(Random Insertion), RS(Random Swap), RD(Random Deletion) 총 4가지 세부 기법을 통해서 학습 데이터를 증강 시킬 수 있다. 이렇게 증강된 데이터를 학습 데이터로 이용해 구글의 BERT를 기본 모델로 한 전이학습을 진행하게 되면 감성 분류 모델을 생성해 낼 수 있다. 데이터 증강 기법 적용 후 전이 학습을 통해 생성한 감성 분류 모델의 성능을 증강 이전의 전이 학습 모델과 비교해 보면 정확도 측면에서 향상을 기대해 볼 수 있다.

• Journal of the Korean Data Analysis Society
• /
• v.20 no.6
• /
• pp.2917-2932
• /
• 2018

Many researches are accomplished as a result of the efforts of developing the production predicting model to solve the supply imbalance of onions which are vegetables very closely related to Korean food. But considering the possibility of storing onions, it is very difficult to solve the supply imbalance of onions only with predicting the production. So, this paper's purpose is trying to build a sentiment dictionary to predict the price of onions by using the internet articles which include the informations about the production of onions and various factors of the price, and these articles are very easy to access on our daily lives. Articles about onions are from 2012 to 2016, using TF-IDF for comparing with four kinds of TF-IDFs through the documents classification of wholesale prices of onions. As a result of classifying the positive/negative words for price by k-means clustering, DBSCAN (density based spatial cluster application with noise) clustering, GMM (Gaussian mixture model) clustering which are partitional clustering, GMM clustering is composed with three meaningful dictionaries. To compare the reasonability of these built dictionary, applying classified articles about the rise and drop of the price on logistic regression, and it shows 85.7% accuracy.