• 지능정보연구
• /
• 제22권3호
• /
• pp.45-69
• /
• 2016

최근에 빅 데이터를 활용하여 감성을 측정하는 시도가 활발히 이루어지고 있다. 통신 매체와 SNS의 발달로 기업은 국민의 감성을 파악하고 즉시 대응해야할 필요성이 생겼다. 우리나라의 경제는 대기업에 대한 의존도가 높기 때문에 10대 기업에 대한 감성분석은 의미가 있다고 할 수 있다. 이러한 측면에서 본 연구는 다 범주를 기준으로 구축한 감성사전을 활용하여 우리나라 10대 기업에 대한 감성을 분석하였다. 빅 데이터를 이용하여 감성을 분석한 기존의 선행연구는 감성을 차원으로 분류하는 경향이 있다. 차원적 감성으로 감성을 분류하는 것은 분류의 기준이 학술적으로 증명되었기에 감성 분석에 주로 사용되어 왔지만 전문가 정도의 지식이 있어야 분류할 수 있어 보편적인 감성을 대변하는 데 비효과적이기에 보완이 필요하다고 할 수 있다. 개별 범주적 감성은 이 점을 보완할 수 있는 분류 방식으로 일정 수준의 주관성이 개입되지만 보편적으로 느낄 수 있는 감성을 측정하는데 효과적이다. 따라서 본 연구는 보편적인 감성의 측정을 위해 감성을 차원으로 분류하지 않고 개별 범주로 분류하여 9가지 영역으로 나누었다. 선행 연구에서 추출한 9가지 범주에 해당하는 감성 단어에 기초하여 감성사전을 구축하였으며 감성 단어가 검출된 빈도를 기준으로 감성을 분석했다. 대상 데이터는 2014년 1월부터 2016년 1월까지 우리나라 10대 기업에 대하여 축적된 뉴스 데이터이다. 대상 데이터에서 검출된 감성 단어의 빈도를 기준으로 각 기업에 대한 감성 순위를 나누고 분포를 확인하였다. 기업에 따라서 감성이 다를 수 있는지, 특정 사건이 각 기업에 대한 감성에 영향을 줄 수 있는지 가설을 세우고 검정하였다. 결론적으로, 다 범주 감성 사전을 활용한 감성 분석은 기업 간 비교와 시점 간 비교에 유의한 것으로 나타났다. 본 연구는 빅 데이터에 산재해있는 감성을 국민의 시각으로 측정하는 하나의 대안으로서 의의가 있다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제31권3호
• /
• pp.67-87
• /
• 2022

Purpose This study quantified companies' views on the COVID-19 pandemic with sentiment analysis of U.S. public companies' disclosures. It aims to provide timely insights to shareholders, investors, and consumers by analyzing and visualizing sentiment changes over time as well as similarities and differences by industry. Design/methodology/approach From more than fifty thousand Form 10-K and Form 10-Q published between 2020 and 2021, we extracted over one million texts related to the COVID-19 pandemic. Using the FinBERT language model fine-tuned in the finance domain, we conducted sentiment analysis of the texts, and we quantified and classified the data into positive, negative, and neutral. In addition, we illustrated the analysis results using various visualization techniques for easy understanding of information. Findings The analysis results indicated that U.S. public companies' overall sentiment changed over time as the COVID-19 pandemic progressed. Positive sentiment gradually increased, and negative sentiment tended to decrease over time, but there was no trend in neutral sentiment. When comparing sentiment by industry, the pattern of changes in the amount of positive and negative sentiment and time-series changes were similar in all industries, but differences among industries were shown in neutral sentiment.

• Asian Journal for Public Opinion Research
• /
• 제8권3호
• /
• pp.197-221
• /
• 2020

We collected national newspaper articles on the largest Chinese investment project in Malaysia, Forest City, and examined media sentiment polarity using alternative automated sentiment analysis tools. We further checked the robustness of these results using content analysis, and consistently found that sentiment polarity for mainstream news is more volatile than independent online journalism. We also found that the sentiment polarity of Malaysian mainstream media towards Chinese investments is aligned with government interactions between the two countries. This suggests that the sentiment of Malaysian mainstream media towards Chinese investments complies with local government attitudes, while independent online media are less constrained by government control. In light of this, foreign investors looking to more effectively estimate risks should monitor both independent and mainstream media to calculate the sentiment of the host country towards their foreign direct investment projects.

• 산경연구논집
• /
• 제13권6호
• /
• pp.9-18
• /
• 2022

Purpose: The government around the world is still highlighting the effect of the new variant of Covid-19. The government continues to make efforts to restore the economy through several programs, one of them is National Economic Recovery. This program is expected to increase public and investor confidence in handling Covid-19. This study aims to capture public sentiment on the economic growth rate in Indonesia, especially during the third wave of the omicron variant of the covid-19 virus, that is at the time in the fourth quarter of 2021. Research design, data, and methodology: The approach used in this research is to collect crowdsourcing data from twitter, in the range of 1st to 10th October 2021. The analysis is done by building model using Deep Learning Neural Network method. Results: The result of the sentiment analysis is that most of the tweets have a neutral sentiment on the Economic Growth discussion. Several central figures who discussed were Minister of Coordinating for the Economy of Indonesia, Minister of State-Owned Enterprises. Conclusions: Data from social media can be used by the government to capture public responses, especially public sentiment regarding economic growth. This can be used by policy makers, for example entrepreneurs to anticipate economic movements under certain conditions.

• International Journal of Computer Science & Network Security
• /
• 제21권9호
• /
• pp.155-162
• /
• 2021

The expansion of the world wide web has led to a huge amount of user generated content over different forums and social media platforms, these rich data resources offer the opportunity to reflect, and track changing public sentiments and help to develop proactive reactions strategies for decision and policy makers. Analysis of public emotions and opinions towards events and sentimental trends can help to address unforeseen areas of public concerns. The need of developing systems to analyze these sentiments and the topics behind them has emerged tremendously. While most existing works reported in the literature have been carried out in English, this paper, in contrast, aims to review recent research works in Arabic language in the field of thematic sentiment analysis and which techniques they have utilized to accomplish this task. The findings show that the prevailing techniques in Arabic topic-based sentiment analysis are based on traditional approaches and machine learning methods. In addition, it has been found that considerably limited recent studies have utilized deep learning approaches to build high performance models.

• 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.

• 대한교통학회지
• /
• 제32권5호
• /
• pp.462-472
• /
• 2014

RPSD는 기존 PSD의 설치 운영 효율성 및 철도 이용자 안전관리 제고를 위해 개발되어 대구도시철도 2호선 문양역에서 2013년 3월부터 시범적으로 운영되어 왔다. 본 연구는 RPSD의 운영 시 비정상적인 상황에 관한 장애보고서와 로그파일을 이용하여 장애발생 내역의 분석 및 시범사업동안의 RPSD 기술 안전성에 대한 신뢰성 평가를 실시하였다. 또한 철도 이용자의 안전시설에 대한 인식과 주관적 감성을 반영하기 위해 RPSD 이용자의 감성평가 결과를 분석하여 요약하였다. 이러한 시스템 신뢰성과 감성평가를 기반으로 RPSD 시스템의 기술 안전성과 구조물 디자인 등에 대한 대중의 만족도 조사를 실시하여 기능 및 감성설계 개선점을 제시하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권7호
• /
• pp.2169-2190
• /
• 2022

The COVID-19 pandemic has affected many aspects of human life. The pandemic not only caused millions of fatalities and problems but also changed public sentiment and behavior. Owing to the magnitude of this pandemic, governments worldwide adopted full lockdown measures that attracted much discussion on social media platforms. To investigate the effects of these lockdown measures, this study performed sentiment analysis and latent Dirichlet allocation topic modeling on textual data from Twitter published during the three lockdown waves in Malaysia between 2020 and 2021. Three lockdown measures were identified, the related data for the first two weeks of each lockdown were collected and analysed to understand the public sentiment. The changes between these lockdowns were identified, and the latent topics were highlighted. Most of the public sentiment focused on the first lockdown as reflected in the large number of latent topics generated during this period. The overall sentiment for each lockdown was mostly positive, followed by neutral and then negative. Topic modelling results identified staying at home, quarantine and lockdown as the main aspects of discussion for the first lockdown, whilst importance of health measures and government efforts were the main aspects for the second and third lockdowns. Governments may utilise these findings to understand public sentiment and to formulate precautionary measures that can assure the safety of their citizens and tend to their most pressing problems. These results also highlight the importance of positive messaging during difficult times, establishing digital interventions and formulating new policies to improve the reaction of the public to emergency situations.

• 한국습지학회지
• /
• 제23권4호
• /
• pp.364-371
• /
• 2021

담수 외래종에 대한 대중의 인식은 시대나 외래종과 관련된 특정 사건에 따라 달라진다. 인식차이는 관리계획을 수립하고 이해하는데 영향을 미쳐 외래종을 관리하는데 대중들의 인식을 이해하는 것이 중요하다. 본 연구에서는 보전문화체학 (Conservation culturomics)에서 사용하는 소셜 네트워크 플렛폼의 디지털 텍스트, 언론보도, 인터넷 검색량을 분석하여 담수 외래종에 대한 대중의 관심도와 감성을 파악하고자 하였다. 11종의 담수 외래종을 대상으로 트위터 게시글 수와, 언론보도량, 검색량을 추출하여 대중의 관심도를 파악하였다. 또한 이 자료들의 시간에 따른 추세와 계절 변동성여부, 자료의 반복 주기를 확인하였다. 수집된 자료를 텍스트마이닝 기법 기반의 감성분석을 통해 감성지수(sentiment score)로 산출해 각 종에 대한 대중들의 감성을 분석하였다. 연구결과 황소개구리와 뉴트리아, 파랑볼우럭, 큰입우럭은 다른 종들보다 상대적으로 많은 대중의 관심을 받는 것으로 확인되었다. 일부 종에서는 특정 시기에 따라 반복되고 변화하는 트윗량과, 언론보도량, 검색량을 나타냈다. 한편 텍스트마이닝 분석 결과, 대부분의 사람들이 담수 외래종에 대해 부정적인 감성을 가지고 있었다. 특히 생태계교란 생물이 지정된 이후 연도가 갈수록 부정적인 감성은 증가하였다. 하지만 과학적 근거가 없는 정보가 확산되거나 혐오를 증대시켜 담수 외래종을 관리하는 것은 한계가 있다. 따라서 외래종에 대한 대중들의 인식을 과학적으로 파악하여 관리방안이 수립되어야 한다.

• International Journal of Computer Science & Network Security
• /
• 제24권9호
• /
• pp.12-20
• /
• 2024

Sentiment analysis has become a pivotal component in understanding public opinion, market trends, and user experiences across various domains. The advent of GPT (Generative Pre-trained Transformer) models has revolutionized the landscape of natural language processing, introducing a new dimension to sentiment analysis. This comprehensive roadmap delves into the transformative impact of GPT models on sentiment analysis tasks, contrasting them with conventional methodologies. With an increasing need for nuanced and context-aware sentiment analysis, this study explores how GPT models, known for their ability to understand and generate human-like text, outperform traditional methods in capturing subtleties of sentiment expression. We scrutinize various case studies and benchmarks, highlighting GPT models' prowess in handling context, sarcasm, and idiomatic expressions. This roadmap not only underscores the superior performance of GPT models but also discusses challenges and future directions in this dynamic field, offering valuable insights for researchers, practitioners, and AI enthusiasts. The in-depth analysis provided in this paper serves as a testament to the transformational potential of GPT models in the realm of sentiment analysis.