scholarly journals Evaluation of the Optimal Topic Classification for Social Media Data Combined with Text Semantics: A Case Study of Public Opinion Analysis Related to COVID-19 with Microblogs

2021 ◽  
Vol 10 (12) ◽  
pp. 811
Author(s):  
Qin Liang ◽  
Chunchun Hu ◽  
Si Chen

Online public opinion reflects social conditions and public attitudes regarding special social events. Therefore, analyzing the temporal and spatial distributions of online public opinion topics can contribute to understanding issues of public concern, grasping and guiding the developing trend of public opinion. However, how to evaluate the validity of classification of online public opinion remains a challenging task in the topic mining field. By combining a Bidirectional Encoder Representations from Transformers (BERT) pre-training model with the Latent Dirichlet Allocation (LDA) topic model, we propose an evaluation method to determine the optimal classification number of topics from the perspective of semantic similarity. The effectiveness of the proposed method was verified based on the standard Chinese corpus THUCNews. Taking Coronavirus Disease 2019 (COVID-19)-related geotagged posts on Weibo in Wuhan city as an example, we used the proposed method to generate five categories of public opinion topics. Combining spatial and temporal information with the classification results, we analyze the spatial and temporal distribution patterns of the five optimal public opinion topics, which are found to be consistent with the epidemic development, demonstrating the feasibility of our method when applied to practical cases.

2012 ◽  
pp. 24-47
Author(s):  
V. Gimpelson ◽  
G. Monusova

Using different cross-country data sets and simple econometric techniques we study public attitudes towards the police. More positive attitudes are more likely to emerge in the countries that have better functioning democratic institutions, less prone to corruption but enjoy more transparent and accountable police activity. This has a stronger impact on the public opinion (trust and attitudes) than objective crime rates or density of policemen. Citizens tend to trust more in those (policemen) with whom they share common values and can have some control over. The latter is a function of democracy. In authoritarian countries — “police states” — this tendency may not work directly. When we move from semi-authoritarian countries to openly authoritarian ones the trust in the police measured by surveys can also rise. As a result, the trust appears to be U-shaped along the quality of government axis. This phenomenon can be explained with two simple facts. First, publicly spread information concerning police activity in authoritarian countries is strongly controlled; second, the police itself is better controlled by authoritarian regimes which are afraid of dangerous (for them) erosion of this institution.


2015 ◽  
Vol 24 (3) ◽  
pp. 266-287 ◽  
Author(s):  
Rachel Ormston ◽  
John Curtice ◽  
Stephen Hinchliffe ◽  
Anna Marcinkiewicz

Discussion of sectarianism often focuses on evidence purporting to show discriminatory behaviour directed at Catholics or Protestants in Scotland. But attitudes also matter – in sustaining (or preventing) such discriminatory behaviours, and in understanding the nature of the ‘problem of sectarianism’ from the perspective of the Scottish public. This paper uses data from the Scottish Social Attitudes survey 2014. The survey fills a gap in the evidence base by providing robust evidence on what the public actually thinks about sectarianism in modern Scotland. It assesses public beliefs about the extent and nature of sectarianism and its perceived causes. Tensions in public opinion and differences in the attitudes of different sections of Scottish society are explored.


2017 ◽  
Vol 5 (2) ◽  
pp. 379-400 ◽  
Author(s):  
Brad Blitz

The global reaction to US President Donald Trump's executive order, “Protecting the Nation from Foreign Terrorist Entry into the United States” of January 27, 2017,1 revealed great public sympathy for the fate of refugees and the principle of refugee protection. In the case of Europe, such sympathy has, however, been dismissed by politicians who have read concerns regarding security and integration as reason for introducing restrictive policies on asylum and humanitarian assistance. These policies are at odds with public sentiment. Drawing upon public opinion surveys conducted by Amnesty International, the European Social Survey (ESS), and Pew Global Attitudes Survey across the European Union and neighboring states, this article records a marked divide between public attitudes towards the treatment of refugees and asylum seekers and official policies regarding asylum and humanitarian assistance, and seeks to understand why this is the case. The article suggests that post-9/11 there has been a reconfiguration of refugee policy and a reconnecting of humanitarian and security interests which has enabled a discourse antithetical to the universal right to asylum. It offers five possible explanations for this trend: i) fears over cultural antagonism in host countries; ii) the conflation of refugees and immigrants, both those deemed economically advantageous as well as those labelled as “illegal”; iii) dominance of human capital thinking; iv) foreign policy justification; and v) the normalization of border controls. The main conclusion is that in a post-post-Cold War era characterized in part by the reconnecting of security and humanitarian policy, European governments have developed restrictive policies despite public sympathy. Support for the admission of refugees is not, however, unqualified, and most states and European populations prefer skilled populations that can be easily assimilated. In order to achieve greater protection and more open policies, this article recommends human rights actors work with the United Nations High Commissioner for Refugees (UNHCR) and its partners to challenge the above discourse through media campaigns and grassroots messaging. Further recommendations include: • Challenging efforts to normalize and drawing attention to the extreme and unprecedented activities of illegal and inhumane practices, e.g., detention, offshore processing, and the separation of families through the courts as part of a coordinated information campaign to present a counter moral argument. • Identifying how restrictive asylum policies fail to advance foreign policy interests and are contrary to international law. • Evidencing persecution by sharing information with the press and government agencies on the nature of claims by those currently considered ineligible for refugee protection as part of a wider campaign of information and inclusion. • Engaging with minority, and in particular Muslim, communities to redress public concerns regarding the possibility of cultural integration in the host country. • Clarifying the rights of refugees and migrants in line with the UNHCR and International Organization for Migration (IOM) guidelines and European and national law in order to hold governments to account and to ensure that all — irrespective of their skills, status, nationality or religion — are given the opportunity to seek asylum. • Identifying and promoting leadership among states and regional bodies to advance the rights of refugees.


Hydrology ◽  
2021 ◽  
Vol 8 (2) ◽  
pp. 57
Author(s):  
Konstantinos Vantas ◽  
Epaminondas Sidiropoulos

The identification and recognition of temporal rainfall patterns is important and useful not only for climatological studies, but mainly for supporting rainfall–runoff modeling and water resources management. Clustering techniques applied to rainfall data provide meaningful ways for producing concise and inclusive pattern classifications. In this paper, a timeseries of rainfall data coming from the Greek National Bank of Hydrological and Meteorological Information are delineated to independent rainstorms and subjected to cluster analysis, in order to identify and extract representative patterns. The computational process is a custom-developed, domain-specific algorithm that produces temporal rainfall patterns using common characteristics from the data via fuzzy clustering in which (a) every storm may belong to more than one cluster, allowing for some equivocation in the data, (b) the number of the clusters is not assumed known a priori but is determined solely from the data and, finally, (c) intra-storm and seasonal temporal distribution patterns are produced. Traditional classification methods include prior empirical knowledge, while the proposed method is fully unsupervised, not presupposing any external elements and giving results superior to the former.


Author(s):  
Xi Liu ◽  
Yongfeng Yin ◽  
Haifeng Li ◽  
Jiabin Chen ◽  
Chang Liu ◽  
...  

AbstractExisting software intelligent defect classification approaches do not consider radar characters and prior statistics information. Thus, when applying these appaoraches into radar software testing and validation, the precision rate and recall rate of defect classification are poor and have effect on the reuse effectiveness of software defects. To solve this problem, a new intelligent defect classification approach based on the latent Dirichlet allocation (LDA) topic model is proposed for radar software in this paper. The proposed approach includes the defect text segmentation algorithm based on the dictionary of radar domain, the modified LDA model combining radar software requirement, and the top acquisition and classification approach of radar software defect based on the modified LDA model. The proposed approach is applied on the typical radar software defects to validate the effectiveness and applicability. The application results illustrate that the prediction precison rate and recall rate of the poposed approach are improved up to 15 ~ 20% compared with the other defect classification approaches. Thus, the proposed approach can be applied in the segmentation and classification of radar software defects effectively to improve the identifying adequacy of the defects in radar software.


Symmetry ◽  
2021 ◽  
Vol 13 (3) ◽  
pp. 415
Author(s):  
Jinli Wang ◽  
Yong Fan ◽  
Hui Zhang ◽  
Libo Feng

Tracking scientific and technological (S&T) research hotspots can help scholars to grasp the status of current research and develop regular patterns in the field over time. It contributes to the generation of new ideas and plays an important role in promoting the writing of scientific research projects and scientific papers. Patents are important S&T resources, which can reflect the development status of the field. In this paper, we use topic modeling, topic intensity, and evolutionary computing models to discover research hotspots and development trends in the field of blockchain patents. First, we propose a time-based dynamic latent Dirichlet allocation (TDLDA) modeling method based on a probabilistic graph model and knowledge representation learning for patent text mining. Second, we present a computational model, topic intensity (TI), that expresses the topic strength and evolution. Finally, the point-wise mutual information (PMI) value is used to evaluate topic quality. We obtain 20 hot topics through TDLDA experiments and rank them according to the strength calculation model. The topic evolution model is used to analyze the topic evolution trend from the perspectives of rising, falling, and stable. From the experiments we found that 8 topics showed an upward trend, 6 topics showed a downward trend, and 6 topics became stable or fluctuated. Compared with the baseline method, TDLDA can have the best effect when K is 40 or less. TDLDA is an effective topic model that can extract hot topics and evolution trends of blockchain patent texts, which helps researchers to more accurately grasp the research direction and improves the quality of project application and paper writing in the blockchain technology domain.


1987 ◽  
Vol 81 (4) ◽  
pp. 1139-1153 ◽  
Author(s):  
Gregory A. Caldeira

I show the intimate connection between the actions of the justices and support for the Supreme Court during one of the most critical periods of U.S. political history, the four months of 1937 during which Franklin D. Roosevelt sought legislation to “pack” the high bench with friendly personnel. Over the period from 3 February through 10 June 1937, the Gallup Poll queried national samples on 18 separate occasions about FDR's plan. These observations constitute the core of my analyses. I demonstrate the crucial influence of judicial behavior and the mass media in shaping public opinion toward the Supreme Court. This research illuminates the dynamics of public support for the justices, contributes to a clearer understanding of an important historical episode, shows the considerable impact of the mass media on public attitudes toward the Court, and adds more evidence on the role of political events in the making of public opinion.


Sign in / Sign up

Export Citation Format

Share Document