Net-TF-SW: Event Popularity Quantification with Network Structure

Event popularity quantification is essential in the determination of current trends in events on social media and the internet. Particularly, it is important during a crisis to ensure appropriate information transmission and prevention of false-rumor diffusion. Here, we propose Net-TF-SW - a noise-robust and explainable topic popularity analysis method. This method is applied to tweets related to COVID-19 and the Fukushima Daiichi Nuclear Disaster, which are two significant crises that have caused significant anxiety and confusion among Japanese citizens. The proposed method is compared to existing methods, and it is verified to be more robust with respect to noise.

[1]  M. Newman.  Power laws, Pareto distributions and Zipf's law , 2005 .

[2]  Amina Adadi,et al.  Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) , 2018, IEEE Access.

[3]  E. Holmes,et al.  A new coronavirus associated with human respiratory disease in China , 2020, Nature.

[4]  J. Hageman.  The Coronavirus Disease 2019 (COVID-19). , 2020, Pediatric annals.

[5]  Guihai Chen,et al.  DancingLines: An Analytical Scheme to Depict Cross-Platform Event Popularity , 2017, DEXA.

[6]  Sergey Brin,et al.  The Anatomy of a Large-Scale Hypertextual Web Search Engine , 1998, Comput. Networks.

[7]  Guihai Chen,et al.  SENTI2POP: Sentiment-Aware Topic Popularity Prediction on Social Media , 2019, 2019 IEEE International Conference on Data Mining (ICDM).

[8]  Laks V. S. Lakshmanan,et al.  KeySee: supporting keyword search on evolving events in social streams , 2013, KDD.

[9]  Graham Smith,et al.  UNSCEAR 2013 Report. Volume I: Report to the General Assembly, Annex A: Levels and effects of radiation exposure due to the nuclear accident after the 2011 great east-Japan earthquake and tsunami , 2014, Journal of radiological protection : official journal of the Society for Radiological Protection.

[10]  Stavros T. Ponis,et al.  Twitter as an instrument for crisis response: The Typhoon Haiyan case study , 2015, ISCRAM.

[11]  Yan Tang,et al.  ESAP: A Novel Approach for Cross-Platform Event Dissemination Trend Analysis Between Social Network and Search Engine , 2016, WISE.

[12]  Yosuke Onoue,et al.  Twitter use in scientific communication revealed by visualization of information spreading by influencers within half a year after the Fukushima Daiichi nuclear power plant accident , 2018, PloS one.

[13]  Fred Pearce,et al.  An epidemic of fear , 2017 .

[14]  Rada Mihalcea,et al.  TextRank: Bringing Order into Text , 2004, EMNLP.

[15]  Satoshi Kurihara,et al.  Regional analysis of user interactions on social media in times of disaster , 2013, WWW '13 Companion.

[16]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[17]  Hong Cheng,et al.  A Model-Free Approach to Infer the Diffusion Network from Event Cascade , 2016, CIKM.

[18]  Satoshi Kurihara,et al.  Information sharing on Twitter during the 2011 catastrophic earthquake , 2013, WWW.