Authentic chatter

Abstract

This operations research aims to derive an easy but meaningful method for practitioners to identify key influencers and uncover suppressed narratives within a Twitter topic group. This research employs a new concept called “authentic chatter” (analogous to a grass-roots discourse) in combination with influence metrics, content analysis, and commercial-off-the-shelf social media analysis software (NexaIntelligence). The mixed-method exploits the power of social network analysis to determine a small but prominent group of influencers that provides a manageable dataset for the qualitative review of the content. This paper reviews research on social influence and identifies two local influence theories, “indegree” and “retweet”, ideal for topical discussion. Next it reviews Twitter content analysis research looking at specific details on methods. Findings from this past research guide development of a new methodology. The research concludes that use of a prominent group and filtering for authentic chatter increased the signal to noise ratio highlighting important underlying themes within the topic.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3

Notes

  1. 1.

    The idea and formal definition of a prominent group is discussed in (Kardara et al. 2015). In brief she states: “the members of a topic community typically differ in the degree of influence they exert over their peers. Some users are rather passive, while others excel in some aspect of the community, affecting the behavior of other members and setting relevant trends. We call influencers or prominent users those members that have established a prominent position inside a community. Collectively, the influential users of a specific community comprise a sub-community that is called prominent group.”

  2. 2.

    In this case “local influence” means influence that is felt within a particular topic area, or # within Twitter. A person may be considered an expert in that particular domain but not so outside that topic area.

  3. 3.

    NexaIntelligence by Nexalogy was used in this research.

  4. 4.

    Note a person who creates a tweet can be referred to as a user, publisher, actor or author within this paper.

  5. 5.

    LIWC—Linguistic Inquiry and Word Count is a text analysis algorithm that exposes emotional, cognitive, and structural components present in text collections. See http://liwc.wpengine.com/wp-content/uploads/2015/11/LIWC2015_LanguageManual.pdf for more details.

  6. 6.

    Note the colours with Fig. 1 represent outliers, are produced automatically by the software, but were not used for this research.

References

  1. AlFalahi K, Atif Y, Abraham A (2014) Models of influence in online social networks. Int J Intell Syst 29(2):1–23

    Article  Google Scholar 

  2. Anger I, Kittl C (2011) Measuring influence on Twitter. Paper presented at the proceedings of the 11th international conference on knowledge management and knowledge technologies, Graz, Austria

  3. Ayers J, Leas EC, Allem J-P, Benton A, Dredze M, Althouse BM (2017) Why do people use electronic nicotine delivery systems (electronic cigarettes)? A content analysis of Twitter, 2012-2015. PLoS ONE. https://doi.org/10.1371/journal.pone.0170702

    Article  Google Scholar 

  4. Berzins J (2014) Russia’s new generation warfare in Ukraine: implications for Latvian defense policy. National Defence Academy of Latvia

  5. Bongwon S, Lichan H, Peter P, Ed HC (2010) Want to be Retweeted? Large Scale Analytics on Factors Impacting Retweet in Twitter Network. IEEE Computer Society

  6. Cha M, Haddadi H, Benevenuto F, Gummadi K (2010) Measuring user influence in Twitter: the million follower fallacy. In: ICWSM’10: proceedings of international AAAI conference on weblogs and social

  7. Chase S (2017) Latvian diplomat says NATO deployment may have to stay for 10 years to counter Russia. Ottawa

  8. Chen W, Wang Y, Yang S (2009) Efficient influence maximization in social networks. Paper presented at the proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining, Paris, France

  9. Chen W, Wang C, Wang Y (2010) Scalable influence maximization for prevalent viral marketing in large-scale social networks. Paper presented at the proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining, Washington, DC, USA

  10. Chew C, Eysenbach G (2010) Pandemics in the age of Twitter: content analysis of Tweets during the 2009 H1N1 outbreak. PLoS ONE 5:e14118

    Article  Google Scholar 

  11. Hansen LK, Arvidsson A, Nielsen FA, Colleoni E, Etter M (2010) Good friends, bad news affect and virality in Twitter. Danish Strategic Research Council

  12. Howard PN, Duffy A, Freelon D, Hussain M, Mari W, Mazaid M (2011) Opening closed regimes what was the role of social media during the Arab spring?. The Project on Information Technology and Political Islam, Washington

    Google Scholar 

  13. Jianshu W, Ee-Peng L, Jing J, Qi H (2010) TwitterRank: finding topic-sensitive influential Twitterers. ACM, New York

    Google Scholar 

  14. Jolicoeur P, Seaboyer A (2014) The evolution of Russian cyber influence activity: a comparison of Russian Cyber Ops in Georgia (2008) and Ukraine (2014). Royal Military College of Canada

  15. Kardara M, Papadakis G, Papaoikonomou A, Tserpes K, Varvarigou T (2015) Large-scale evaluation framework for local influence theories in Twitter. Inf Process Manage 51:226–252. https://doi.org/10.1016/j.ipm.2014.06.002

    Article  Google Scholar 

  16. Lachlan KA, Spence PR, Lin X, Najarian K, Del Greco M (2016) Social media and crisis management: CERC, search strategies, and Twitter content. Comput Hum Behav 54:647–652. https://doi.org/10.1016/j.chb.2015.05.027

    Article  Google Scholar 

  17. LIWC (2018) Home page. https://liwc.wpengine.com/. Accessed 12 Jan 2018

  18. Neuendorf KA (2017) The content analysis guidebook. SAGE, Thousand Oaks

    Google Scholar 

  19. Pal A, Counts S (2011) Identifying topical authorities in microblogs. Paper presented at the proceedings of the fourth ACM international conference on Web search and data mining, Hong Kong, China

  20. Paul C, Matthews M (2016) The Russian “Firehose of Falsehood” Propaganda Model. Rand Corporation, Santa Monica

    Google Scholar 

  21. Pomerantsev P, Weiss M (2014) The menace of unreality: how the Kremlin weaponizes information, culture and money

  22. Quercia D, Ellis J, Capra L, Crowcroft J (2011) In the mood for being influential on Twitter. In: 2011 IEEE third international conference on privacy, security, risk and trust and 2011. IEEE third international conference on social computing, 9-11 Oct. 2011 2011. pp 307-314. https://doi.org/10.1109/passat/socialcom.2011.27

  23. Räbiger S, Spiliopoulou M (2015) A framework for validating the merit of properties that predict the influence of a Twitter user. Expert Syst Appl 42:2824–2834. https://doi.org/10.1016/j.eswa.2014.11.006

    Article  Google Scholar 

  24. Riddell J, Brown A, Kovic I, Jauregui J (2017) Who are the most influential emergency physicians on Twitter? West J Emerg Med 18:281

    Article  Google Scholar 

  25. Riquelme F, González-Cantergiani P (2016) Measuring user influence on Twitter: a survey. Inf Process Manage 52:949–975. https://doi.org/10.1016/j.ipm.2016.04.003

    Article  Google Scholar 

  26. Romero DM, Galuba W, Asur S, Huberman BA (2011) Influence and passivity in social media. Paper presented at the proceedings of the 20th international conference companion on world wide web, Hyderabad, India

  27. Schenk CB, Sicker DC (2011) Finding event-specific influencers in dynamic social networks. In: 2011 IEEE third international conference on privacy, security, risk and trust and 2011. IEEE third international conference on social computing, 9-11 Oct. 2011. pp 501–504. https://doi.org/10.1109/passat/socialcom.2011.100

  28. Scripps J, Tan P-N, Esfahanian A-H (2009) Measuring the effects of preprocessing decisions and network forces in dynamic network analysis. Paper presented at the proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, Paris, France

  29. Shane S (2017) The fake Americans Russia created to influence the election. New York

  30. Small TA (2011) What the hashtag? Inform Commun Soc 14:872–895. https://doi.org/10.1080/1369118X.2011.554572

    Article  Google Scholar 

  31. Starbird K (2017) Examining the alternative media ecosystem through the production of alternative narratives of mass shooting events on Twitter. Paper presented at the ICWSM 2017

  32. Sun J, Tang J (2011) A survey of models and algorithms for social influence analysis. Social network data analysis. Springer, New York, pp 177–214

    Google Scholar 

  33. Sun J, Tang J (2013) Models and algorithms for social influence analysis. Paper presented at the proceedings of the sixth ACM international conference on web search and data mining, Rome, Italy

  34. Timberg C (2016) Russian propaganda effort helped spread ‘fake news’ during election, experts say

  35. Wikipedia (2018) Social influence. https://en.wikipedia.org/wiki/Social_influence. Accessed 28 Feb 2018

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Bruce Forrester.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Forrester, B. Authentic chatter. Comput Math Organ Theory 26, 382–411 (2020). https://doi.org/10.1007/s10588-019-09299-0

Download citation

Keywords

  • Authentic chatter
  • Social network analysis
  • Content analysis
  • Mixed-method
  • Twitter analysis