Country Image in COVID-19 Pandemic: A Case Study of China

Country image has a profound influence on international relations and economic development. In the worldwide outbreak of COVID-19, countries and their people display different reactions, resulting in diverse perceived images among foreign public. Therefore, in this study, we take China as a specific and typical case and investigate its image with aspect-based sentiment analysis on a large-scale Twitter dataset. To our knowledge, this is the first study to explore country image in such a fine-grained way. To perform the analysis, we first build a manually-labeled Twitter dataset with aspect-level sentiment annotations. Afterward, we conduct the aspect-based sentiment analysis with BERT to explore the image of China. We discover an overall sentiment change from non-negative to negative in the general public, and explain it with the increasing mentions of negative ideology-related aspects and decreasing mentions of non-negative fact-based aspects. Further investigations into different groups of Twitter users, including U.S. Congress members, English media, and social bots, reveal different patterns in their attitudes toward China. This study provides a deeper understanding of the changing image of China in COVID-19 pandemic. Our research also demonstrates how aspect-based sentiment analysis can be applied in social science researches to deliver valuable insights.

[1]  M. McCombs.  Agenda setting function of mass media , 1977 .

[2]  Hyunjin Seo,et al.  Online Social Relations and Country Reputation , 2013 .

[3]  S. Ansolabehere,et al.  Primary Elections and Partisan Polarization in the U.S. Congress , 2010 .

[4]  John T. McNelly,et al.  International News Exposure and Images of Nations , 1986 .

[5]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[6]  Erving Goffman,et al.  Frame Analysis: An Essay on the Organization of Experience. , 1979 .

[7]  J. Hampton,et al.  The people's choice. , 2001, Plastic surgical nursing : official journal of the American Society of Plastic and Reconstructive Surgical Nurses.

[8]  Philip S. Yu,et al.  BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis , 2019, NAACL.

[9]  Eric Gilbert,et al.  VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text , 2014, ICWSM.

[10]  Richong Zhang,et al.  Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree , 2019, EMNLP.

[11]  Jian Wang.  Managing national reputation and international relations in the global era: Public diplomacy revisited , 2006 .

[12]  Amos Azaria,et al.  The DARPA Twitter Bot Challenge , 2016, Computer.

[13]  Jimmy J. Lin,et al.  End-to-End Open-Domain Question Answering with BERTserini , 2019, NAACL.

[14]  Sven Engesser,et al.  Populism and social media: how politicians spread a fragmented ideology , 2017 .

[15]  A. Liss.  Images of China in the American Print Media: A survey from 2000 to 2002 , 2003 .

[16]  Lei Guo,et al.  Networks, Big Data, and Intermedia Agenda Setting: An Analysis of Traditional, Partisan, and Emerging Online U.S. News , 2017 .

[17]  BIG SOCIAL DATA ANALYTICS 1 Big Social Data Analytics in Journalism and Mass Communication: Comparing Dictionary-based Text Analysis and Unsupervised Topic Modeling , 2020 .

[18]  Geir Gripsrud,et al.  Effects of hosting a mega-sport event on country image. , 2010 .

[19]  Bing Liu,et al.  Feature Projection for Improved Text Classification , 2020, ACL.

[20]  Debao Xiang,et al.  China's image on international English language social media , 2013 .

[21]  Erik Cambria,et al.  Sentic LSTM: a Hybrid Network for Targeted Aspect-Based Sentiment Analysis , 2018, Cognitive Computation.

[22]  Xinsheng Liu,et al.  The ‘China Threat’ through the Lens of US Print Media: 1992–2006 , 2012 .

[23]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[24]  Caroline Brun,et al.  XRCE: Hybrid Classification for Aspect-based Sentiment Analysis , 2014, *SEMEVAL.

[25]  L. Dodd,et al.  Congress and the Polarity Paradox: Party Polarization, Member Incivility and Enactment of Landmark Legislation, 1891–1994 , 2012 .

[26]  Keith T. Poole,et al.  on party polarization in Congress , 2007, Daedalus.

[27]  Zengjun Peng,et al.  Representation of China: An across time analysis of coverage in the New York Times and Los Angeles Times , 2004 .

[28]  Piet Schenelaars,et al.  Public opinion , 2013, BDJ.

[29]  Shimon Gadir,et al.  Agenda Setting , 1980 .

[30]  D. Shaw,et al.  Agenda setting function of mass media , 1972 .

[31]  Saif Mohammad,et al.  NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets , 2013, *SEMEVAL.

[32]  Tieyun Qian,et al.  Transfer Capsule Network for Aspect Level Sentiment Classification , 2019, ACL.

[33]  Luyao Huang,et al.  Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence , 2019, NAACL.

[34]  C. Granger.  Investigating causal relations by econometric models and cross-spectral methods , 1969 .

[35]  Li Zhang,et al.  The Rise of China: media perception and implications for international politics , 2010 .

[36]  Guillaume Bouchard,et al.  SentiHood: Targeted Aspect Based Sentiment Analysis Dataset for Urban Neighbourhoods , 2016, COLING.

[37]  Chia-ju Lin.  A Textual Analysis of the Coverage of SARS and the Image of China --- A Comparative Analysis , 2012 .

[38]  W. R. Neuman,et al.  The Dynamics of Public Attention: Agenda‐Setting Theory Meets Big Data , 2014 .

[39]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[40]  Israel D. Nebenzahl,et al.  Measuring the joint effect of brand and country image in consumer evaluation of global products , 1996 .

[41]  Michel Laroche,et al.  The influence of country image structure on consumer evaluations of foreign products , 2005 .

[42]  Kristina Lerman,et al.  Tracking Social Media Discourse About the COVID-19 Pandemic: Development of a Public Coronavirus Twitter Data Set , 2020, JMIR public health and surveillance.

[43]  Diana Ingenhoff,et al.  Advancing the country image construct from a public relations perspective , 2015 .

[44]  Timothy Baldwin,et al.  Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-Based Sentiment Analysis , 2018, NAACL.

[45]  E. Goffman.  Frame analysis: An essay on the organization of experience , 1974 .

[46]  K. Wilson,et al.  A Flu By Any Other Name: Why the World Health Organization Should Adopt the World Meteorological Association's Storm Naming System as a Model for Naming Emerging Infectious Diseases , 2012, Journal of health communication.

[47]  Dongyan Zhao,et al.  Multi-grained Attention Network for Aspect-Level Sentiment Classification , 2018, EMNLP.

[48]  Giovanni Luca Ciampaglia,et al.  The spread of low-credibility content by social bots , 2017, Nature Communications.

[49]  Filippo Menczer,et al.  BotOrNot: A System to Evaluate Social Bots , 2016, WWW.

[50]  Serena Villata,et al.  Argument Mining on Twitter: Arguments, Facts and Sources , 2017, EMNLP.

[51]  Hwee Tou Ng,et al.  An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis , 2019, ACL.