Journal of Computational Social Science最新文献

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.

One of the first steps in many text-based social science studies is to retrieve documents that are relevant for an analysis from large corpora of otherwise irrelevant documents. The conventional approach in social science to address this retrieval task is to apply a set of keywords and to consider those documents to be relevant that contain at least one of the keywords. But the application of incomplete keyword lists has a high risk of drawing biased inferences. More complex and costly methods such as query expansion techniques, topic model-based classification rules, and active as well as passive supervised learning could have the potential to more accurately separate relevant from irrelevant documents and thereby reduce the potential size of bias. Yet, whether applying these more expensive approaches increases retrieval performance compared to keyword lists at all, and if so, by how much, is unclear as a comparison of these approaches is lacking. This study closes this gap by comparing these methods across three retrieval tasks associated with a data set of German tweets (Linder in SSRN, 2017. 10.2139/ssrn.3026393), the Social Bias Inference Corpus (SBIC) (Sap et al. in Social bias frames: reasoning about social and power implications of language. In: Jurafsky et al. (eds) Proceedings of the 58th annual meeting of the association for computational linguistics. Association for Computational Linguistics, p 5477-5490, 2020. 10.18653/v1/2020.aclmain.486), and the Reuters-21578 corpus (Lewis in Reuters-21578 (Distribution 1.0). [Data set], 1997. http://www.daviddlewis.com/resources/testcollections/reuters21578/). Results show that query expansion techniques and topic model-based classification rules in most studied settings tend to decrease rather than increase retrieval performance. Active supervised learning, however, if applied on a not too small set of labeled training instances (e.g. 1000 documents), reaches a substantially higher retrieval performance than keyword lists.

As part of the "text-as-data" movement, Natural Language Processing (NLP) provides a computational way to examine political polarization. We conducted a methodological scoping review of studies published since 2010 (n = 154) to clarify how NLP research has conceptualized and measured political polarization, and to characterize the degree of integration of the two different research paradigms that meet in this research area. We identified biases toward US context (59%), Twitter data (43%) and machine learning approach (33%). Research covers different layers of the political public sphere (politicians, experts, media, or the lay public), however, very few studies involved more than one layer. Results indicate that only a few studies made use of domain knowledge and a high proportion of the studies were not interdisciplinary. Those studies that made efforts to interpret the results demonstrated that the characteristics of political texts depend not only on the political position of their authors, but also on other often-overlooked factors. Ignoring these factors may lead to overly optimistic performance measures. Also, spurious results may be obtained when causal relations are inferred from textual data. Our paper provides arguments for the integration of explanatory and predictive modeling paradigms, and for a more interdisciplinary approach to polarization research.

Supplementary information: The online version contains supplementary material available at 10.1007/s42001-022-00196-2.