Journal of Computational Social Science最新文献

The Flint Water Crisis (FWC) was an avoidable public health disaster that has profoundly affected the city's residents, a majority of whom are Black. Although many scholars and journalists have called attention to the role of racism in the water crisis, little is known about the extent to which the public attributed the FWC to racism as it was unfolding. In this study, we used natural language processing to analyze nearly six million Flint-related tweets posted between April 1, 2014, and June 1, 2016. We found that key developments in the FWC corresponded to increases in the number and percentage of tweets that mentioned terms related to race and racism. Similar patterns were found for other topics hypothesized to be related to the water crisis, including water and politics. Using sentiment analysis, we found that tweets with a negative polarity score were more common in the subset of tweets that mentioned terms related to race and racism when compared to the full set of tweets. Next, we found that word pairs that included terms related to race and racism first appeared after the January 2016 state and federal emergency declarations and a corresponding increase in media coverage of the FWC. We conclude that many Twitter users connected the events of the water crisis to race and racism in real-time. Given growing evidence of negative health effects of second-hand exposure to racism, this may have implications for understanding minority health and health disparities in the US.

Vaccination has been a hot topic in the present COVID-19 context. The government, public health stakeholders and media are all concerned about how to get the people vaccinated. The study was intended to explore the perception and emotions of the Indians citizens toward COVID-19 vaccine from Twitter messages. The tweets were collected for the period of 6 months, from mid-January to June, 2021 using hash-tags and keywords specific to India. Topics and emotions from the tweets were extracted using Latent Dirichlet Allocation (LDA) method and National Research Council (NRC) Lexicon, respectively. Theme, sentiment and emotion wise engagement and reachability metrics were assessed. Hash-tag frequency of COVID-19 vaccine brands were also identified and evaluated. Information regarding 'Co-WIN app and availability of vaccine' was widely discussed and also received highest engagement and reachability among Twitter users. Among the various emotions, trust was expressed the most, which highlights the acceptance of vaccines among the Indian citizens. The hash-tags frequency of vaccine brands shows that Covishield was popular in the month of March 2021, and Covaxin in April 2021. The results from the study will help stakeholders to efficiently use social media to disseminate COVID-19 vaccine information on popular concerns. This in turn will encourage citizens to be vaccinated and achieve herd immunity. Similar methodology can be adopted in future to understand the perceptions and concerns of people in emergency situations.

Supplementary information: The online version contains supplementary material available at 10.1007/s42001-023-00203-0.

To effectively design policies and implement measures for addressing problems faced by people during these difficult times of pandemic, it is critical to have a clear vision of the problems people are freely talking about. One of the ways is to analyze social media feeds e.g., tweets, which has become one of the primary ways people express their views on various socioeconomic issues and on-ground effectiveness of measures adopted to address these issues. In this work, we attempt to uncover various socioeconomic issues, which are giving rise to negative and positive sentiments and their trends across geographies over a course of one year of the pandemic. We also try identifying similarities and differences in opinions as they vary across gender as the time passes through the crisis. Many previous works have analyzed sentiments in context of vaccines, fatalities, and lockdowns; however, socioeconomic issues did not receive full attention. We found that sentiments of people with respect to economy are negative across geographies during starting of pandemic. Thereafter, gradually sentiments lift towards positive direction reflecting a sense of improvement in situation. Females appeared to have slightly different concerns and hopes in comparison to males and especially across globe people expressed positive sentiments during new year time. Finally, this work, together with many other similar works on social media analysis gives ground for wide scale adoption of geo-temporal sentiments trend analysis of social media as a tool for uncovering key concerns and effectiveness of measures.

For a healthy society to exist, it is crucial for the media to focus on disease-related issues so that more people are widely aware of them and reduce health risks. Recently, deep neural networks have become a popular tool for textual sentiment analysis, which can provide valuable insights and real-time monitoring and analysis regarding health issues. In this paper, as part of an effort to develop an effective model that can elicit public sentiment on COVID-19 news, we propose a novel approach Cov-Att-BiLSTM for sentiment analysis of COVID-19 news headlines using deep neural networks. We integrate attention mechanisms, embedding techniques, and semantic level data labeling into the prediction process to enhance the accuracy. To evaluate the proposed approach, we compared it to several deep and machine learning classifiers using various metrics of categorization efficiency and prediction quality, and the experimental results demonstrate its superiority with 0.931 testing accuracy. Furthermore, 73,138 pandemic-related tweets posted on six global channels were analyzed by the proposed approach, which accurately reflects global coverage of COVID-19 news and vaccination.

Misinformation in the media is produced by hard-to-gauge thought mechanisms employed by individuals or collectivities. In this paper, we shed light on what the country-specific factors of falsehood production in the context of COVID-19 Pandemic might be. Collecting our evidence from the largest misinformation dataset used in the COVID-19 misinformation literature with close to 11,000 pieces of falsehood, we explore patterns of misinformation production by employing a variety of methodological tools including algorithms for text similarity, clustering, network distances, and other statistical tools. Covering news produced in a span of more than 14 months, our paper also differentiates itself by its use of carefully controlled hand-labeling of topics of falsehood. Findings suggest that country-level factors do not provide the strongest support for predicting outcomes of falsehood, except for one phenomenon: in countries with serious press freedom problems and low human development, the mostly unknown authors of misinformation tend to focus on similar content. In addition, the intensity of discussion on animals, predictions and symptoms as part of fake news is the biggest differentiator between nations; whereas news on conspiracies, medical equipment and risk factors offer the least explanation to differentiate. Based on those findings, we discuss some distinct public health and communication strategies to dispel misinformation in countries with particular characteristics. We also emphasize that a global action plan against misinformation is needed given the highly globalized nature of the online media environment.

Supplementary information: The online version contains supplementary material available at 10.1007/s42001-022-00193-5.

This study presents a framework to study quantitatively geographical visual diversities of urban neighborhood from a large collection of street-view images using an Artificial Intelligence (AI)-based image segmentation technique. A variety of diversity indices are computed from the extracted visual semantics. They are utilized to discover the relationships between urban visual appearance and socio-demographic variables. This study also validates the reliability of the method with human evaluators. The methodology and results obtained from this study can potentially be used to study urban features, locate houses, establish services, and better operate municipalities.

Since early 2020, the global coronavirus pandemic has strained economic activities and traditional lifestyles. For such emergencies, our paper proposes a social sentiment estimation model that changes in response to infection conditions and state government orders. By designing mediation keywords that do not directly evoke coronavirus, it is possible to observe sentiment waveforms that vary as confirmed cases increase or decrease and as behavioral restrictions are ordered or lifted over a long period. The model demonstrates guaranteed performance with transformer-based neural network models and has been validated in New York City, Los Angeles, and Chicago, given that coronavirus infections explode in overcrowded cities. The time-series of the extracted social sentiment reflected the infection conditions of each city during the 2-year period from pre-pandemic to the new normal and shows a concurrency of waveforms common to the three cities. The methods of this paper could be applied not only to analysis of the COVID-19 pandemic but also to analyses of a wide range of emergencies and they could be a policy support tool that complements traditional surveys in the future.