logo

SCIENTIA SINICA Informationis, Volume 47, Issue 12: 1623-1645(2017) https://doi.org/10.1360/N112017-00053

A survey of information propaganda mechanism under the cross-medium

More info
  • ReceivedMar 6, 2017
  • AcceptedJun 7, 2017
  • PublishedNov 30, 2017

Abstract

With the development of mobile networking, cloud computing, and big data technology, propaganda through public opinion and sentiment on the Internet has shown some new features, such as cross-medium, cross-media, and cross-language characteristics, which indicates exciting challenges for next-generation research and application of public opinion analysis. In this paper, the information propaganda mechanism of public sentiment under social networking is explored under a cross-medium environment, which means that the information can be spread across different web sites and social networks. A multi-element information propaganda model, called the PRCMA model, is then proposed, which includes five critical elements during the entire process of information propaganda, such as the information publisher ($P$), information receiver ($R$), content ($C$), medium ($M$), and result assessment ($A$). Furthermore, the critical challenges and vital research problems are illustrated, and some up-to-date research results are analyzed and reviewed based on each dimension of the PRCMA model, particularly on how to identify and measure the influence of nodes, identify fake information in real time, measure the personal preference and group behaviors, and measure the results of propaganda in the process of information spread under a cross-medium environment. Finally, some new technologies, theoretical methods, applications, and future trends are discussed, which provide new clues and research fields for further research on public opinion and sentiment on the Internet under a cross-medium environment.


Funded by

国家国际科技合作专项(2015DFA81780)

陕西省科技厅协同创新项目(2015XT-21)

教育部“云数融合基金项目(2017B00030)

中央高校基本科研业务费(zdyf2017006)


References

[1] Borchers C. Heres why Trumps attacks on `fake news succeed. Washington Post. 2017.02. http://www.washingtonpost.com/news/the-fix/wp/2017/02/17/heres-why-trumps-attacks-on-fake-news-succeed/?utm\_term=.91 a3d6e3c8fa. Google Scholar

[2] CNN Reports. Did fake news help elect donald trump?. 2016.11.19. http://money.cnn.com/2016/11/19/technology/mark-zuckerberg-facebook-fake-news-election/index.html. Google Scholar

[3] Bessi A, Coletto M, Davidescu G A, et al. Science vs. conspiracy: collective narratives in the age of misinformation. PLOS One, 2015, 10: 1--17. Google Scholar

[4] Zhou D H, Han W B, Wang Y J. Social network information dissemination model based on node and information characteristics. Comput Res Dev, 2015, 52: 156--166. Google Scholar

[5] Lazarsfield P, Berelson B, Gaudet H. The Peoples Choice: How the Voter Makes Up His Mind in a Presidential Campaign. New York: ACM Press, 1968. Google Scholar

[6] Schifferes S. Technological transformations of news: a long term perspective. In: Proceedings of the 25th International Conference Companion on World Wide Web, Montreal, 2016. 743--744. Google Scholar

[7] Li B. Portrait sketch of micro-blog opinion leaders — an example of opinion leaders in 40 micro-blog events. Journalism Rev, 2012, 1: 19--25. Google Scholar

[8] Wang S H, Huang Q M. Research progress of heterogeneous media analysis technology. Integrat Tech, 2015, 4: 7--21. Google Scholar

[9] Watts D J, Strogatz S H. Collective dynamics of `small-world networks. Nature, 1998, 393: 440--442. Google Scholar

[10] Barabasi A L, Albert R. Emergence of scaling in random networks. Science, 1999, 286: 509--512. Google Scholar

[11] Du H F, Li S Z, Marcus W F, et al. Community structure of small world networks and scale-free networks. Acta Phys Sin, 2007, 56: 6886--6893. Google Scholar

[12] Zhang L. Research on some algorithms in network public opinion propagation. Dissertation for Ph.D. Degree. Beijing: Beijing Jiaotong University, 2009. Google Scholar

[13] Hu H B, Wang L. A brief history of power law distribution. Physical, 2005, 34: 889--896. Google Scholar

[14] Kou Z B, Zhang C S. Reply networks on a bulletin board system. Phys Rev E, 2003, 67: 328--335. Google Scholar

[15] Li W J, Bao H Y. Analysis of characteristics of information dissemination model in BBS. Comput Eng App, 2010, 46: 18--22. Google Scholar

[16] Lin S. Research on evaluation model of micro-blog individual information communication influence. Modn Lib Inf Tech, 2014, 243: 79--85. Google Scholar

[17] Weng J, Lim E P, Jiang J, et al. Twitterank: finding topic sensitive influential twitters. In: Proceedings of the 3rd ACM International Conference on Web Search and Data Mining (WSDM 2010), New York, 2010. 261--270. Google Scholar

[18] Pastorsatorras R, Vespignani A. Epidemic spreading in scale-free networks. Phys Rev Lett, 2001, 86: 3200--3203. Google Scholar

[19] Zhang F, Si G Y, Luo P. A survey of rumor propagation model. Complex Syst Complex Sci, 2009, 6: 1--11. Google Scholar

[20] Wu X Y, Liu Z H. How community structure influences epidemic spread in social network. Phys A Stat Mech Appl, 2008, 387: 623--630. Google Scholar

[21] Liu Z H. Signal detection and transmission in complex networks (in Chinese). Sci Sin-Phys Mech Astron, 2014, 44: 1334--1343. Google Scholar

[22] Yang J, Counts S. Predicting the speed, scale and rang of information diffusion in Twitter. In: Proceedings of the 4th International AAAI Conference on Weblogs and Social Media, Menlo Park, 2010. 355--358. Google Scholar

[23] Lagnier C, Denoyer L, Gaussier E, et al. Predicting information diffusion in social networks using content and users profiles. In: Proceedings of the 35th European Conference on Advance in Information Retrieval, Moscow, 2013. 74--85. Google Scholar

[24] Zhang Y W, Qi J Y, Ma J, et al. The interaction mechanism of online public opinion and unconventional emergencies — based on system dynamics modeling analysis. Intell Mag, 2010, 29: 1--6. Google Scholar

[25] Di G Q, Zeng H Y, Le Z J, et al. System dynamics model and simulation of network public opinion events. Intell Mag, 2012, 31: 12--19. Google Scholar

[26] Spiro E S, Irvine C A, Dubois C L, et al. Waiting for a retweet: modeling waiting time in information propagation. In: Proceedings of Workshop on Social Network and Social Media Analysis: Methods, Models and Applications, Lake Tahoe, 2013. Google Scholar

[27] Dredze M, Kambadur P, Kazantsev G, et al. How Twitter is changing the nature of financial news discovery. In: Proceedings of the 2nd International Workshop on Data Science for Macro-Modeling, San Francisco, 2016. Google Scholar

[28] Leskovec J, Backstrom L, Kleinberg J. Meme-tracking and the dynamics of the news cycle. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), Paris, 2009. Google Scholar

[29] Heimbach I, Hinz O, Schiller B, et al. Content virality on online social networks: empirical evidence from Twitter, Facebook, and Google+ on german news websites. In: Proceedings of the 26th ACM International Conference on Hypertext & Social Media, Guzelyurt, 2015. 39--47. Google Scholar

[30] Yu K, Rong L L, Guo W Q, et al. Research on public opinion communication model based on online and online network. Manag Rev, 2015, 27: 200--212. Google Scholar

[31] Du R, Yu Z W, Liu Z L, et al. Research on social impact of online and offline activities based on watercress city. Chin J Comput, 2014, 37: 238--245. Google Scholar

[32] Bauch C T, Galvani A P. Social factors in epidemiology. Science, 2013, 342: 47--49. Google Scholar

[33] Howell L. Digital wildfires in a hyperconnected world. World Economic Forum Report, 2013. http://reports.weforum.org/global-risks-2013/risk-case-1/digital-wildfires-in-a-hyperconnected-world/. Google Scholar

[34] Shen Y, Yu J, Dong K, et al. Automatic fake followers detection in chinese micro-blogging system. In: Proceedings of Advances in Knowledge Discovery and Data Mining. Berlin: Springer, 2014. 596--607. Google Scholar

[35] Hardalov M, Koychev I, Nakov P. In search of credible news. In: Proceedings of International Conference on Artificial Intelligence: Methodology, Systems, and Applications. Berlin: Springer, 2016. 172--180. Google Scholar

[36] Gupta A, Kumaraguru P, Castillo C, et al. TweetCred: real time credibility assessment of content on Twitter. In: Proceedings of International Conference on Social Informatics. Berlin: Springer, 2014. 228--243. Google Scholar

[37] Papadopoulos S, Bontcheva K, Jaho E, et al. Overview of the special issue on trust and veracity of information in social media. ACM Trans Inf Syst, 2016, 34: 1--5. Google Scholar

[38] Frakes W B. Information and misinformation: an investigation of the notions of information, misinformation, informing, and misinforming. Soc Sci Inf Stud, 1985, 5: 147--149. Google Scholar

[39] Hamidian S, Diab M T. Rumor identification and belief investigation on Twitter. In: Proceedings of the 7th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, San Diego, 2016. 3--8. Google Scholar

[40] Ratkiewicz J, Conover M, Meiss M, et al. Detecting and tracking the spread of astroturf memes in microblog streams. In: Proceedings of the 20th International Conference Companion on World Wide Web, Hyderabad, 2011. 249--252. Google Scholar

[41] Qazvinian V, Rosengren E, Radev D R, et al. Rumor has it: identifying misinformation in microblogs. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, Edinburgh, 2011. 1589--1599. Google Scholar

[42] Karlova N A, Lee J H. Notes from the underground city of disinformation: a conceptual investigation. Proc Assoc Inf Sci Technol, 2011, 48: 1--9. Google Scholar

[43] Takahashi T, Igata N. Rumor detection on Twitter. In: Proceedings of the 6th International Conference on Soft Computing and Intelligent Systems, Kobe, 2012. 452--457. Google Scholar

[44] Wang A H. Dont follow me: spam detection in Twitter. In: Proceedings of the 2010 International Conference on Security and Cryptography (SECRYPT), Athens, 2010. 1--10. Google Scholar

[45] Kumar K P K, Geethakumari G. Detecting misinformation in online social networks using cognitive psychology. Human-Centric Comput Inf Sci, 2014, 4: 14--36. Google Scholar

[46] Karlova N A, Fisher K E. A social diffusion model of misinformation and disinformation for understanding human information behaviour. Inform Res, 2013, 18: 1--17. Google Scholar

[47] Kumar S, West R, Leskovec J. Disinformation on the web: impact, characteristics, and detection of wikipedia hoaxes. In: Proceedings of the 25th International Conference on World Wide Web, Montreal, 2016. 591--602. Google Scholar

[48] Zhang H L, Alim M A, Li X, et al. Misinformation in online social networks: detect them all with a limited budget. ACM Trans Inf Syst, 2016, 34: 1--24. Google Scholar

[49] Abdulla R, Garrison B, Salwen M, et al. The credibility of newspapers, television news, and online news. In: Proceedings of the Association for Education in Journalism and Mass Communication Annual Convention, Miami, 2002. 97--106. Google Scholar

[50] Li L, Sun J H. Group characteristics based on social network conflict information dissemination. Syst Eng Theory Prac, 2014, 34: 207--214. Google Scholar

[51] Schwarz J, Ringel M M. Augmenting web pages and search results to support credibility assessment. In: Proceedings of the CHI 2011 Conference on Human Factors in Computing Systems, Vancouver, 2011. 1245--1254. Google Scholar

[52] Odonovan J, Kang B, Meyer G, et al. Credibility in context: an analysis of feature distributions in Twitter. In: Proceedings of International Conference on Privacy, Security, Risk and Trust, Amsterdam, 2012. 293--301. Google Scholar

[53] Metzger M J, Flanagin A J. Credibility and trust of information in online environments: the use of cognitive heuristics. J Pragmatics, 2013, 59: 210--220. Google Scholar

[54] Gill A J, Nowson S, Oberlander J. What are they blogging about? personality, topic and motivation in blogs. In: Proceedings of the 3rd International ICWSM Conference, San Jose, 2009. Google Scholar

[55] Xu J, Yang X P, Liu Z. Research on web information credibility verification method based on content trust. J Beijing Ins of Tech, 2014, 34: 710--715. Google Scholar

[56] Fang B X, Guo Y C, Zhou Y. ICCON control model and evaluation of internet information content security. Sci China Ser F-Inf Sci, 2009, 39: 951--965. Google Scholar

[57] Castillo C, Mendoza M, Poblete B. Predicting information credibility in time-sensitive social media. Internet Res, 2013, 23: 560--588. Google Scholar

[58] Zubiaga A, Hoi G W S, Liakata M, et al. Analyzing how people orient to and spread rumors in social media by looking at conversational threads. PLOS One, 2016, 11: e0150989. Google Scholar

[59] Zubiaga A, Ji H. Tweet, but verify: epistemic study of information verification on Twitter. Soc Netw Anal Min, 2014, 4: 1--12. Google Scholar

[60] Ratkiewicz J, Conover M, Meiss M, et al. Truthy: mapping the spread of astroturf in microblog streams. In: Proceedings of the 20th International Conference Companion on World Wide Web, Hyderabad, 2011. 249--252. Google Scholar

[61] Castillo C, Mendoza M, Poblete B. Information credibility on Twitter. In: Proceedings of the 20th International Conference on World Wide Web, Hyderabad, 2011. 675--684. Google Scholar

[62] Xia X, Yang X, Wu C, et al. Information credibility on Twitter in emergency situation. In: Proceedings of Pacific Asia Conference on Intelligence and Security Informatics, Kuala Lumpur, 2012. 45--59. Google Scholar

[63] Zhao B, Rubinstein B I, Gemmell J, et al. A Bayesian approach to discovering truth from conflicting sources for data integration. Proc VLDB Endowment, 2012, 5: 550--561. Google Scholar

[64] Liu W J. Research on big data method and rumor. Folklore Stud, 2016, 127: 85--91. Google Scholar

[65] Liu J G, Ren S M, Guo Q, et al. Research progress of node importance ordering in complex networks. Acta Phys Sin, 2013, 62: 178901. Google Scholar

[66] Granovetter M S. The strength of weak ties. Am J Soc, 1973, 78: 1360--1380. Google Scholar

[67] Qian Y X. An empirical study on motivation of internet word of mouth in Chinas virtual brand community. Dissertation for Master Degree. Hefei: University of Science and Technology China, 2014. Google Scholar

[68] Rao Y, Feng N. Data Analysis — Forum Oriented Network Content Analysis Report (2015). Beijing: Electronic Industry Press, 2015. Google Scholar

[69] Linderholm O. 10 people you wont believe have fake followers on Twitter. 2013. https://www.yahoo.com/news/blogs/profit-minded/10-people-won-t-believe-fake-followers-twitter-215539518.html?ref=gs. Google Scholar

[70] Chen D B, Lu J Y, Shang M S, et al. Identifying influential nodes in complex networks. Phys A Stat Mech Appl, 2012, 391: 1777--1787. Google Scholar

[71] Centola D. The spread of behavior in an online social network experiment. Science, 2010, 329: 1194--1197. Google Scholar

[72] Ugander J, Backstrom L, Marlow C, et al. Structural diversity in social contagion. Proc Natl Acad Sci USA, 2012, 109: 5962--5966. Google Scholar

[73] Kitsak M, Gallos L K, Havlin S, et al. Identification of influential spreaders in complex networks. Nat Phys, 2010, 6: 888--893. Google Scholar

[74] Zeng A, Zhang C J. Ranking spreaders by decomposing complex networks. Phys Lett A, 2012, 377: 1031--1035. Google Scholar

[75] Fang B X, Jia Y, Han Y. Social networking analysis, core scientific issues, current research and future perspectives. Bull Chin Acad Sci, 2015, 30: 187--199. Google Scholar

[76] Ren Z M, Shao F, Liu J G, et al. Research on network node importance measurement method based on degree and aggregation coefficient. Acta Phys Sin, 2013, 62: 128901. Google Scholar

[77] Tan Y J, Wu J, Deng H Z, et al. Review of invulnerability research on complex networks. Syst Eng, 2006, 24: 1--5. Google Scholar

[78] Li P X, Ren Y Q, Xi Y M. A measure of the importance of a network node (set). Syst Eng, 2004, 22: 13--20. Google Scholar

[79] Yu X, Li Y H, Zheng X P, et al. Evaluation method of node importance in communication networks based on network performance gradient. J Tsinghua Univ (NAT SCI EDIT), 2008, 48: 541--544. Google Scholar

[80] Huang X, Vodenska I, Wang F, et al. Identifying influential directors in the United States corporate governance network. Phys Rev E Stat Nonlinear Soft Matter Phys, 2011, 84: 046101. Google Scholar

[81] Goyal A, Bonchi F, Lakshmanan L V. Learning influence probabilities in social networks. In: Proceedings of the 3rd ACM International Conference on Web Search and Data Mining, New York, 2010. 241--250. Google Scholar

[82] Zhang Y L, Li C P, Chen H. An efficient link based similarity measure in information networks. J Softw, 2014, 25: 2602--2615. Google Scholar

[83] Song J, Guo C P, Zhang Y C, et al. Research and implementation of incremental iterative computation model. Chin J Comput, 2016, 39: 109--125. Google Scholar

[84] Xu W T, Liu F, Zhu E Z. Research on new micro-blog user influence ranking algorithm based on MapReduce. Comput Sci, 2016, 43: 66--70. Google Scholar

[85] Qi X M, Sun W X. A PageRank algorithm for fusing multiple feature factors. Comput Eng Appl, 2015, 53: 97--103. Google Scholar

[86] Lu L, Zhang Y C, Chi H Y, et al. Leaders in social networks, the delicious case. PLOS One, 2011, 6: e21202. Google Scholar

[87] Li Q, Zhou T, Lu L, et al. Identifying influential spreaders by weighted LeaderRank. Phys A Stat Mech Appl, 2014, 404: 47--55. Google Scholar

[88] Xu J M, Zhu F X, Liu S C, et al. Improved LeaderRank algorithm for opinion leader mining. Comput Eng Appl, 2015, 51: 110--114. Google Scholar

[89] Guo C, Shen Q, Yang Y, et al. User rank: a user influence-based data distribution optimization method for privacy protection in cloud storage system. In: Proceedings of the 39th Annual Computer Software and Applications Conference, Taichung, 2015. 104--109. Google Scholar

[90] Huang J M, Shen H W, Chen X Q. Explore the spread of information using the backbone of social networking. J Chin Inf Process, 2016, 30: 74--82. Google Scholar

[91] Wang C X, Guan X H, Qin T, et al. Research on influence modeling of opinion leaders in micro-blog news communication. J Softw, 2015, 26: 1473--1485. Google Scholar

[92] Bakshy E, Hofman J M, Watts D J, et al. Identifying “influencers on Twitter. In: Proceeding of the 4th International Conference on Web Search and Data Mining. New York: ACM Press, 2011. 1--10. Google Scholar

[93] Wang Z J, Wang S H, Zhang W G, et al. Potential influence propagation model based on social content. Chin J Comput, 2016, 39: 1528--1540. Google Scholar

[94] Zhao Z Y, Yu H, Wang X F, et al. Influence analysis of node propagation based on network community structure. Chin J Comput, 2014, 37: 753--766. Google Scholar

[95] Zhao L J, Xie W L, Gao H O, et al. A rumor spreading model with variable forgetting rate. Phys A: Stat Mech Appl, 2013, 392: 6146--6154. Google Scholar

[96] Wang X C, Lin Z Y, Sun J. 10 judgments about the regularity of group events — based on the analysis of participants behavioral characteristics. J Nation Sch Admin, 2011, 1: 13--16. Google Scholar

[97] Zhu G H, Jiang G P, Xia L L. The influence of bandwagon phenomenon on rumor propagation in social networks. Comput Sci, 2016, 43: 135--139. Google Scholar

[98] Asur S, Huberman B A, Szabo G, et al. Trends in social media: persistence and decay. In: Proceedings of the 5th International AAAI Conference on Weblogs and Social Media. Menlo Park: The AAAI Press, 2011. 434--437. Google Scholar

[99] Berger J, Milkman K L. What makes online content viral? J Marketing Res, 2012, 49: 192--205. Google Scholar

[100] Yuan Q, Gao Q. The analysis of online news information credibility assessment on weibo based on analyzing content. In: Proceedings of International Conference on Engineering Psychology and Cognitive Ergonomics. Berlin: Springer, 2016. 125--135. Google Scholar

[101] Wang Y Z, Yu J Y, Qiu W, et al. Evolutionary game model and analysis method of network group behavior. Chin J Comput, 2015, 38: 282--300. Google Scholar

[102] Zhang Y F, Xiao R B. The emergence mechanism of network group event public opinion synchronization based on cellular automata. Syst Eng Theor Pract, 2014, 34: 2600--2608. Google Scholar

[103] Niu P Y. Research on performance evaluation of network information dissemination. Dissertation for Ph.D. Degree. Wuhan: Wuhan University, 2009. Google Scholar

[104] Wang J Y, Zhang P, Liu L W, et al. Research on traffic evaluation of network rumor propagation. Intell Mag, 2016, 35: 105--109. Google Scholar

[105] Meng X F, Du Z J. Big data integration research: problems and challenges. Comput Res Dev, 2016, 53: 231--246. Google Scholar

[106] Gao J, Buldyrev S V, Stanley H E, et al. Networks formed from interdependent networks. Nat Phys, 2012, 8: 40--48. Google Scholar

[107] Chen C, Chen F, Cao D, et al. A cross-media sentiment analytics platform for microblog. In: Proceedings of the 23rd ACM International Conference on Multimedia, Brisbane, 2015. 767--769. Google Scholar

[108] hspace-0.8 mmCao D, Ji R, Lin D, et al. A cross-media public sentiment analysis system for microblog. Multim Syst, 2016, 22: 479--486. Google Scholar

[109] Zhou H W, Chen L, Shi F L, et al. Learning bilingual sentiment word embeddings for cross-language sentiment classification. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics, Beijing, 2015. 430--440. Google Scholar

[110] Zhou G, Zeng Z, Huang J X, et al. Transfer learning for cross-lingual sentiment classification with weakly shared deep neural networks. In: Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, Pisa, 2016. 245--254. Google Scholar

  • Figure 1

    Sentiment propaganda model with PRCMA multi-factors

  • Figure 2

    The analysis and evaluation framework for network group behavior

  • Table 1   The evolution clue and index for content reliability in social media network
    Class Index and clue
    Information source Basic features: visit num/prize num/rank/official ownership/domain types/topic/is ICP/is well-known/ is authenticity.
    Structure features: simpility navigation/website structure/editable reply advise/readable strength/is public aesthetic/source advertisement num/advertisement quantity/credibility other data credibility in website.
    Interactive ability: user search/information validation/timeliness of user response.
    Information content Basic features: the length of content/is spelling error/is syntax error/the reference of content and data/contain URLs/contain label/timeless of content.
    Participant degree: focus num/resport num/popularity.
    Syntax features: is true/text case/punctuation/personal pronoun/the length of content/URLs num.
    Semantic features: the professional of content/understandability/rationality/valuability/usefulness/łinebreak reliability/orientation.
    Topic The content of topic features: topic tags/topic content segmentation extraction/topic semantic features/positive scoring/negative scoring/topic sentiments.
    Topic total features: content num in topic/the average length of content/the field of topic/expression num in content in topic.
    Topic user features: average age of user/user num/validation user num/the nun of topic is referred by users/the sex of users in topic.
    Information disseminator Basic attribute features: sex/location/liveness/social platform/portrait/identity validation/level/types of user/frequenty of post/focus num/follow num/browser num of user home page.
    Preference features: the motivation writing and spreads/reputation/similarity degree.
    User behaviour features: report comment symtax/semantic/comment sentiment/supported.
    Propaganda Propaganda quantity features: propaganda degree num/max num/audience num.
    The network of content propagation: propagation subtree structure/average depth of propagation/max depth/propagation path/content dispersed structure/content delivery structure/strongly connected component/network dentisity/average clustering sparse/average path length/the distribution of degree/power law distribution/match pattern.
    A single user attribute in a network of content propagation: content dissemination form a network penetration/degree/clustering coefficient/betweenness/closeness/interest rate/the degree and the degree of correlation/weak star nodes and star effect/homogeneity.
  • Table 2   Information propaganda model evaluation index in social network
    Criterion Related definitions
    The distribution characteristics of media Information media Communication node node interaction is strong, the power index will be higher, the node of heavy tailed phenomenon is more significant, which rely on information in interactive media communication is more strong in the “opinion leaders" is more significant.
    The community of propaganda nodes The higher the clustering coefficient, the more obvious the characteristics of the network structure community, namely, the lower the speed of information transmission on the medium, but the higher the credibility of the information dissemination.
    Authority The weaker interaction between media nodes, the more stringent information dissemination channels, the higher the authority, such as: government media
    Network propagation speed and delay The speed and influence of information in different media: the propagation delay of information in the media network.
    Ability to interact online and offline The degree of network user participation and the influence of network on offline activities.
    Information content perspective Accuracy Information provides a true description; information provides a true result of subsequent events; information can accurately describe reality.
    Authority Information source authority; information based on scientific discovery.
    Goal The presentation of information presents a description of real goals; information provides an inseparable and unbiased description of reality.
    Real-time The information is timely; the information provides multiple sides of the real-time state; the information remains sufficiently fresh.
    Coverage Information covers a set of facts and perspectives; information can meet the needs of individuals or groups; information is beneficial to individuals or groups.
    The spread of motivation and influence Preference characteristics Communicators (forwarding comments and browsing frequency); forwarding (comments and browsing) topic types; spread interest tags; user type propagation researchers and fans of user types.
    Emotional characteristics Positive features: share happiness, enhance influence, reward motivation, help companies and help others motivation.
    Negative characteristics: negative emotional venting, psychological comfort, warning others, seeking compensation and revenge.
    Neutral characteristics: participation, interaction, support, community development, habitual motivation, etc.
    Reciprocal exchange capability The purpose of sharing and disseminating information is to better access to equal information resources, to reflect the influence and value of communicators, and to value the equivalence of the content of communication.
    Influence characteristics The physical attributes of network nodes, network topology attributes and network link characteristics.
    Receiver preference User perception feature Semantic content category and emotional tag of information content.
    Characteristics of interest preferences Receiver forwarding (comments and browsing), topic classification and interest tags; receiver focuses on user type and fan user type.
    Comment/Forwarding features Forwarding (comments) content syntax and semantic features; comments and content information and negative comparison; whether or not the comment supports content.

Copyright 2020 Science China Press Co., Ltd. 《中国科学》杂志社有限责任公司 版权所有

京ICP备18024590号-1       京公网安备11010102003388号