• Asia pacific journal of information systems
• /
• 제32권2호
• /
• pp.226-248
• /
• 2022

The existing model for sentiment analysis of product reviews learned from past data and new data was labeled based on training. But new data was never used by the existing system for making a decision. The proposed Aspect-based multi-agent Deep Reinforcement learning Sentiment Analysis (ADRSA) model learned from its very first data without the help of any training dataset and labeled a sentence with aspect category and sentiment polarity. It keeps on learning from the new data and updates its knowledge for improving its intelligence. The decision of the proposed system changed over time based on the new data. So, the accuracy of the sentiment analysis using deep reinforcement learning was improved over supervised learning and unsupervised learning methods. Hence, the sentiments of premium customers on a particular site can be explored to other customers effectively. A dynamic environment with a strong knowledge base can help the system to remember the sentences and usage State Action Reward State Action (SARSA) algorithm with Bidirectional Encoder Representations from Transformers (BERT) model improved the performance of the proposed system in terms of accuracy when compared to the state of art methods.

• Journal of Information Processing Systems
• /
• 제16권3호
• /
• pp.718-732
• /
• 2020

Conducting sentiment analysis and opinion mining are challenging tasks in natural language processing. Many of the sentiment analysis and opinion mining applications focus on product reviews, social media reviews, forums and microblogs whose reviews are topic-similar and opinion-rich. In this paper, we try to analyze the sentiments of sentences from online webcast reviews that scroll across the screen, which we call live barrages. Contrary to social media comments or product reviews, the topics in live barrages are more fragmented, and there are plenty of invalid comments that we must remove in the preprocessing phase. To extract evaluative sentiment sentences, we proposed a novel approach that clusters the barrages from the same commenter to solve the problem of scattering the information for each barrage. The method developed in this paper contains two subtasks: in the data preprocessing phase, we cluster the sentences from the same commenter and remove unavailable sentences; and we use a semi-supervised machine learning approach, the naïve Bayes algorithm, to analyze the sentiment of the barrage. According to our experimental results, this method shows that it performs well in analyzing the sentiment of online webcast barrages.

• Journal of Contemporary Eastern Asia
• /
• 제20권2호
• /
• pp.108-128
• /
• 2021

Research on the news coverage of North Korea has been paying less attention to social media platforms than to legacy media. An increasing number of social media users post, retweet, share, interpret, and set agendas on North Korea. The accessibility of international users and North Korea's publicity purposes make social media a venue for expression, news diversity, and framing about the nation. This study examined the sentiment of Twitter posts on North Korea from a framing perspective and the relationship between network strengths and sentiment from a social network perspective. Data were collected using two tools: Jupyter Notebook with Python 3.6 for preliminary analysis and NodeXL for main analysis. A total of 11,957 tweets, 10,000 of which were collected using Python and 1,957 tweets using NodeXL, about North Korea between June 20-21, 2020 were collected. Results demonstrated that there was more negative sentiment than positive sentiment about North Korea in the sampled Twitter posts. Some users belonging to small network sizes reached out to others on Twitter to build networks and spread positive information about North Korea. Influential users tended to be impartial to sentiment about North Korea, while some Twitter users with a small network exhibited high percentages of positive words about North Korea. Overall, marginalized populations with network bonding were more likely to express positive sentiment about North Korea than were influencers at the center of networks.

• Nuclear Engineering and Technology
• /
• 제53권3호
• /
• pp.1013-1019
• /
• 2021

This paper reviewed the temporal changes in the public opinions on nuclear energy in Korea with a big data analysis of nuclear energy-related articles and their comments posted on the portal site NAVER. All articles that included at least one of "nuclear energy," "nuclear power plant (NPP)," "nuclear power phase-out," or "anti-nuclear" in their titles or main text were extracted from those posted on NAVER in January 2010-December 2019. First, we performed annual word frequency analysis to identify what words had appeared most frequently in the articles. For that period, the most frequent words were "NPP," "nuclear energy," and "energy." In addition, "safety" has remained in the upper ranks since the Fukushima NPP accident. Then, we performed sentiment analysis of the pre-processed articles. The sentiment analysis showed that positive-tone articles have been reported more frequently than negativetone over the entire analysis period. Last, we performed sentiment analysis of the comments on the articles to examine the public's intention regarding nuclear issues. The analysis showed that the number of negative comments to articles each month-irrespective of positive or negative tone-was always larger than that of positive comments over the entire analysis period.

• 인터넷정보학회논문지
• /
• 제18권4호
• /
• pp.121-131
• /
• 2017

인터넷, 소셜미디어, 모바일 등의 등장이후 소비자들은 개인의 의견을 온라인을 통해 적극적으로 표명하기 시작했고 이의 확산 또한 실시간으로 이루어지고 있다. 인터넷 기반의 다양한 커뮤니케이션 활동들을 통해 생산되는 텍스트는 인터넷을 사용하는 사용자들이 공유하고 공감하는 자원으로서 단순한 소통의 도구를 넘어 분석의 가치가 있는 새로운 정보의 창고가 되고 있다. 세계 각국의 정부와 기업은 인터넷과 소셜미디어를 통해 생산되는 소셜 빅데이터를 활용하여 사회/경제적 문제의 해결과 정부의 정책을 효과적으로 추진하는데 적극 활용하고 있다. 특히 경제와 관련해서는 경기현황에 대한 경제주체들의 움직임을 보다 빠르고 정확하게 분석하고 예측하여 이에 알맞은 정책을 적기에 실시할 수 있도록 다각적인 활동을 펼치고 있다. 본 연구에서는 소셜 미디어에 내재된 소비자의 직적접이고 즉시성 있는 의견을 경제적 측면에서 활용할 수 있는 온라인 소비자감성지수 모형을 제시하고 구현하였다. 이를 위해 한국은행의 소비자동향조사(CSI)와 소비자심리지수(CCSI)를 온라인으로 수행할 수 있는 어휘분류체계(온톨로지)와 감성사전을 구축하고 감성분석을 실시하여 생활형편, 경제상황, 소비와 수입 4가지 영역의 소셜감성지수를 도출하였다. 또한 이들을 결합한 온라인 소비자감성지수(e-CCSI)를 개발하고 소비자심리지수와 비교를 통해 유용성을 확인하였다.

• International Journal of Computer Science & Network Security
• /
• 제23권9호
• /
• pp.120-128
• /
• 2023

In this work, we have presented ATSA, a hierarchical attention deep learning model for Arabic sentiment analysis. ATSA was proposed by addressing several challenges and limitations that arise when applying the classical models to perform opinion mining in Arabic. Arabic-specific challenges including the morphological complexity and language sparsity were addressed by modeling semantic composition at the Arabic morphological analysis after performing tokenization. ATSA proposed to perform phrase-chunks sentiment embedding to provide a broader set of features that cover syntactic, semantic, and sentiment information. We used phrase structure parser to generate syntactic parse trees that are used as a reference for ATSA. This allowed modeling semantic and sentiment composition following the natural order in which words and phrase-chunks are combined in a sentence. The proposed model was evaluated on three Arabic corpora that correspond to different genres (newswire, online comments, and tweets) and different writing styles (MSA and dialectal Arabic). Experiments showed that each of the proposed contributions in ATSA was able to achieve significant improvement. The combination of all contributions, which makes up for the complete ATSA model, was able to improve the classification accuracy by 3% and 2% on Tweets and Hotel reviews datasets, respectively, compared to the existing models.

• 한국IT서비스학회지
• /
• 제20권5호
• /
• pp.159-176
• /
• 2021

In this study, we performed a comparative analysis of the sentiment value for the tourists in USA, China, and Korea on the COVID19 pandemic era to explore and find out the features of the tourists by using online reviews. We collected a total of 243,826 online hotel reviews for metropolitan city and vacation spot in the three countries to compare the features between the business and the vacation trips. We collected the online reviews into the tow groups from Jan. 1, 2019 to Nov. 31, 2019 for before COVID19 pandemic and from Apr. 1, 2020 to Deb 28, 2021 for during COVID19. Online reviews were categorized into 6 dimensions using LDA model. Sentiment analysis were presented for 6 dimensions by utilizing a lexicon base. We proposed an approach to analyzing the importance of each attribute by applying 6-dimensional sentiment values to conjoint analysis. Our empirical analysis showed that the proposed approach could explore and find out the changed features of travelers during the COVID19 pandemic.

• Journal of Platform Technology
• /
• 제11권2호
• /
• pp.3-14
• /
• 2023

This paper proposes a big data sentiment analysis method and deep learning implementation method to provide a webtoon comment analysis web page for convenient comment confirmation and feedback of webtoon writers for the development of the cartoon industry in the video animation field. In order to solve the difficulty of automatic analysis due to the nature of Internet comments and provide various sentiment analysis information, LSTM(Long Short-Term Memory) algorithm, ranking algorithm, and word2vec algorithm are applied in parallel, and actual popular works are used to verify the validity. If the analysis method of this paper is used, it is easy to expand to other domestic and overseas platforms, and it is expected that it can be used in various video animation content fields, not limited to the webtoon field

• 산업경영시스템학회지
• /
• 제43권4호
• /
• pp.33-40
• /
• 2020

In order to satisfy customers, it is important to identify the quality elements that affect customers' satisfaction. The Kano model has been widely used in identifying multi-dimensional quality attributes in this purpose. However, the model suffers from various shortcomings and limitations, especially those related to survey practices such as the data amount, reply attitude and cost. In this research, a model based on the text sentiment analysis is proposed, which aims to substitute the survey-based data gathering process of Kano models with sentiment analysis. In this model, from the set of opinion text, quality elements for the research are extracted using the morpheme analysis. The opinions' polarity attributes are evaluated using text sentiment analysis, and those polarity text items are transformed into equivalent Kano survey questions. Replies for the transformed survey questions are generated based on the total score of the original data. Then, the question-reply set is analyzed using both the original Kano evaluation method and the satisfaction index method. The proposed research model has been tested using a large amount of data of public IT service project evaluations. The result shows that it can replace the existing practice and it promises advantages in terms of quality and cost of data gathering. The authors hope that the proposed model of this research may serve as a new quality analysis model for a wide range of areas.

• 디지털융복합연구
• /
• 제17권9호
• /
• pp.47-54
• /
• 2019

본 연구는 빅데이터 분석 방법인 오피니언 마이닝을 사용하여 아파트 가격 관련 뉴스 기사의 극성을 확인하는 연구로 자료는 2012년, 2018년 2년간 네이버에 게시된 인터넷 뉴스 기사를 사용하였다. 감성분석 모형을 모델링하고 주제 지향형 감성사전 구축 방법을 제안하였다. 제안한 감성분석 모형을 통해 분석한 결과, 아파트 가격이 상승하는 시기에는 사회적 이슈 선정에 있어서 언론사의 성향에 따라 차이가 있는 것을 확인하였고 정부와 동일한 성향의 언론사에서 긍정 기사가 많은 것을 확인하였다. 부동산 분야에서 사용할 수 있는 감성분석 모형을 제시하고 부동산 관련 비정형 데이터의 극성을 분석하였다는 것에 의의가 있다. 향후 다양한 분야에 접목하기 위해서는 주제별 감성사전을 구축해야 하며 다양한 비정형 데이터를 수집하고 수집 기간을 확장하는 것이 필요하다.