Abstract
We study the relationship between chatter on social media and observed actions concerning charitable donation. One hypothesis is that a fraction of those who act will also tweet about it, implying a linear relation. However, if the contagion is present, we expect a superlinear scaling. We consider two scenarios: donations in response to a natural disaster, and regular donations. We empirically validate the model using two location-paired sets of social media and donation data, corresponding to the two scenarios. Results show a quadratic relation between chatter and action in emergency response case. In case of regular donations, we observe a near-linear relation. Additionally, regular donations can be explained by demographic factors, while for a disaster response social media is a much better predictor of action. A contagion model is used to predict the near-quadratic scaling for the disaster response case. This suggests that diffusion is present in emergency response case, while regular charity does not spread via social network. Understanding the scaling behavior that relates social media chatter to physical actions is an important step in estimating the extent of a response and for determining social media strategies to affect the response.
Similar content being viewed by others
Notes
The Contact and Excitation models are similar to the threshold and independent cascade models in influence propagation. The main difference is that in our process, the propagation stops after one step.
For sparse graphs, \(q=O(\frac{1}{|V|})\) and for dense graphs, \(q=O(1).\)
References
Adali S, Sisenda F, Magdon-Ismail M (2012) Actions speak as loud as words: predicting relationships from social behavior data. In: Proceedings of WWW, pp 689–698
Anshelevich E, Hate A, Magdon-Ismail M (2013) Seeding influential nodes in non-submodular models of information diffusion. In: Proceedings of AAMAS, pp 1305–1306
Arthur WB (1989) Competing technologies, increasing returns, and lock-in by historical events. Econ J 99(394):116–131
Barabási AL, Albert R (1999) Emergence of scaling in random networks. Science 286(5439):509–512
Bekkers R, Wiepking P (2010) A literature review of empirical studies of philanthropy: eight mechanisms that drive charitable giving. Nonprofit Volunt Sect Q 40(5):924–973
Bikhchandani S, Hirshleifer D, Welch I (1998) Learning from the behavior of others: conformity, fads, and informational cascades. J Econ Perspect 12(3):151–170
Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM TIST 2(3):27.1–27.27
Cheung CK, Chan CM (2000) Social-cognitive factors of donating money to charity, with special attention to an international relief organization. Eval Program Plan 23(2):241–253
Cook S, Conrad C, Fowlkes AL, Mohebbi MH (2011) Assessing Google flu trends performance in the United States during the 2009 Influenza virus A (H1N1) pandemic. PLoS ONE 6(8):e23610
Cosley D, Huttenlocher DP, Kleinberg JM, Lan X, Suri S (2010) Sequential influence models in social networks. AAAI Int Conf Weblogs Social Media 10:26–33
Destro L, Holguín-Veras J (2011) Material convergence and its determinants. Transp Res Rec 2234(1):14–21
Domingos P, Richardson M (2001) Mining the network value of customers. In: Proceedings of KDD, pp 57–66
Doyle A, Katz G, Summers K, Ackermann C, Zavorin I, Lim Z, Muthiah S, Butler P, Self N, Zhao L, Lu CT, Khandpur RP, Fayed Y, Ramakrishnan N (2014) Forecasting significant societal events using the Embers streaming predictive analytics system. Big Data 2(4):185–195
Dredze M, Paul M, Bergsma S, Tran H (2013) Carmen: a Twitter geolocation system with applications to public health. In: HIAI Workshop (at AAAI’13), pp 20–24
Eubank S, Guclu H, Kumar VA, Marathe MV, Srinivasan A, Toroczkai Z, Wang N (2004) Modelling disease outbreaks in realistic urban social networks. Nature 429(6988):180–184
Hagar C (2013) Crisis informatics: perspectives of trust-is social media a mixed blessing? SLIS Stud Res J 2(2):2
Holguín-Veras J, Jaller M, Van Wassenhove LN, Pérez N, Wachtendorf T (2012) On the unique features of post-disaster humanitarian logistics. J Oper Manag 30(7):494–506
Kempe D, Kleinberg J, Tardos É (2003) Maximizing the spread of influence through a social network. In: Proceedings of KDD, pp 137–146
Korolov R, Peabody J, Lavoie A, Das S, Magdon-Ismail M, Wallace W (2015) Actions are louder than words in social media. In: Proceedings of the 2015 IEEE/ACM international conference on advances in social networks analysis and mining 2015. ACM, pp 292–297
Kumar S, Morstatter F, Liu H (2014) Twitter data analytics. Springer, New York
Lee YK, Chang CT (2007) Who gives what to charity? Characteristics affecting donation behavior. Soc Behav Pers 35(9):1173–1180
Leskovec J, Singh A, Kleinberg J (2006) Patterns of influence in a recommendation network. In: Advances in KDD, pp 380–389
Li N, Chen G (2009) Analysis of a location-based social network. IEEE Int Conf Comput Sci Eng 4:263–270
Morales A, Borondo J, Losada JC, Benito RM (2014) Efficiency of human activity on information spreading on twitter. Soc Netw 39:1–11
Muller A, Whiteman G (2009) Exploring the geography of corporate philanthropic disaster response: a study of Fortune Global 500 firms. J Bus Ethics 84(4):589–603
Oosterhof L, Heuvelman A, Peters O (2009) Donation to disaster relief campaigns: underlying social cognitive factors exposed. Eval Program Plan 32(2):148–157
Palen L, Liu SB (2007) Citizen communications in crisis: anticipating a future of ICT-supported public participation. In: Proceedings of SIGCHI, ACM, pp 727–736
Price DS (1976) A general theory of bibliometric and other cumulative advantage processes. JASIST 27(5):292–306
Radley A, Kennedy M (1995) Charitable giving by individuals: a study of attitudes and practice. Hum Relat 6:685–709
Romero DM, Galuba W, Asur S, Huberman BA (2011) Influence and passivity in social media. In: Proceedings of ECML/PKDD, pp 18–33
Santiago A, Benito R (2008) An extended formalism for preferential attachment in heterogeneous complex networks. EPL (Europhysics Letters) 82(5):58004
Scellato S, Mascolo C (2011) Measuring user activity on an online location-based social network. In: INFOCOM Workshops, IEEE, pp 918–923
Starbird K, Palen L (2011) Voluntweeters: self-organizing by digital volunteers in times of crisis. In: Proceedings of SIGCHI, pp 1071–1080
Starbird K, Palen L (2012) (How) will the revolution be retweeted? Information diffusion and the 2011 Egyptian uprising. In: Proceedings of ACM CSCW, ACM, pp 7–16
The Foundation Center (2014) Philanthropy and Hurricane Sandy. A report on the foundation and corporate response. http://foundationcenter.org/gainknowledge/research/pdf/sandy_philanthropy_2014.pdf. Accessed 6 Dec 2015
Torrey C, Burke M, Lee M, Dey A, Fussell S, Kiesler S (2007) Connected giving: ordinary people coordinating disaster relief on the Internet. In: Hawaii international conference on system sciences
Tyshchuk Y, Li H, Ji H, Wallace WA (2013) Evolution of communities on Twitter and the role of their leaders during emergencies. In: Proceedings of the 2013 IEEE/ACM international conference on advances in social networks analysis and mining (ASONAM2013), pp 727–733
Wang H, Hovy E, Dredze M (2015) The Hurricane Sandy Twitter Corpus. In: Workshops at the twenty-ninth AAAI conference on artificial intelligence, pp 20–24
Watts DJ (2002) A simple model of global cascades on random networks. PNAS 99(9):5766–5771
Wu S, Hofman JM, Mason WA, Watts DJ (2011) Who says what to whom on Twitter. In: Proceedings of WWW, ACM, pp 705–714
Acknowledgments
This is an extended version of the paper entitled “Actions are Louder Than Words in Social Media” presented at the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2015). The authors gratefully acknowledge support from NSF Grant 1124827. This material is also based partially upon work sponsored by the Army Research Laboratory under Cooperative Agreement Number W911NF-09-2-0053 and by Department of Homeland Security through the Command, Control, and Interoperability Center for Advanced Data Analysis Center of Excellence. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Laboratory, or the US Government.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Korolov, R., Peabody, J., Lavoie, A. et al. Predicting charitable donations using social media. Soc. Netw. Anal. Min. 6, 31 (2016). https://doi.org/10.1007/s13278-016-0341-1
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13278-016-0341-1