Skip to main content
SpringerLink
Log in

Learning to lurker rank: an evaluation of learning-to-rank methods for lurking behavior analysis

  • Original Article
  • Published:
Social Network Analysis and Mining Aims and scope Submit manuscript

Abstract

While being long researched in social science and computer–human interaction, lurking behaviors in online social networks (OSNs) have been computationally studied only in recent years. Remarkably, determining lurking behaviors has been modeled as an unsupervised, eigenvector-centrality-based ranking problem, and it has been shown that lurkers can effectively be ranked according to the link structure of an OSN graph. Although this approach has enabled researchers to overcome the lack of ground-truth data at a large scale, the complexity of the problem hints at the opportunity of learning from past lurking experiences as well as of using a variety of behavioral features, including any available, possibly platform-specific information on the activity and interaction of lurkers in an OSN. In this paper, we leverage this opportunity in a principled way, by proposing a machine-learning framework which, once trained on lurking/non-lurking examples from multiple OSNs, allows us to predict the ranking of unseen lurking behaviors, ultimately enabling the prioritization of user engagement tasks. Results obtained on 23 network datasets by state-of-the-art learning-to-rank methods, using different optimization and evaluation criteria, show the significance of the proposed approach.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17

Similar content being viewed by others

Notes

  1. http://www.lemurproject.org.

References

  • Aprem A, Krishnamurthy V (2017) Utility change point detection in online social media: a revealed preference framework. IEEE Trans Signal Process 65(7):1869–1880

    Article  MathSciNet  Google Scholar 

  • Bach N, Hai N, Phuong T (2016) Personalized recommendation of stories for commenting in forum-based social media. Inf Sci 352–353:48–60

    Article  Google Scholar 

  • Bakshy E, Hofman JM, Mason WA, Watts DJ (2011) Everyone’s an influencer: quantifying influence on Twitter. In: Proc. ACM conf. on web search and web data mining (WSDM), Hong Kong, China, February 9–12, 2011, pp 65–74. https://doi.org/10.1145/1935826.1935845

  • Basile P, Caputo A, Rossiello G, Semeraro G (2016) Learning to rank entity relatedness through embedding-based features. In: Proc. int. conf. on applications of natural language to information systems (NLDB), Salford, UK, June 22–24, 2016, pp 471–477. https://doi.org/10.1007/978-3-319-41754-7_51

  • Biega AJ, Ghazimatin A, Ferhatosmanoglu H, Gummadi KP, Weikum G (2017) Learning to Un-Rank: quantifying search exposure for users in online communities. In: Proceedings of the 2017 ACM on conference on information and knowledge management—CIKM ’17, ACM Press, New York, pp 267–276

  • Breiman L (2001) Random forests. Mach Learn 45(1):5–32

    Article  MATH  Google Scholar 

  • Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadsworth, Belmont

    MATH  Google Scholar 

  • Burges CJ (2010) From ranknet to lambdarank to lambdamart: an overview. Tech. Rep. 23-581

  • Burges CJC, Ragno R, Le QV (2006) Learning to rank with nonsmooth cost functions. In: Proc. conf. on neural information processing systems (NIPS), MIT Press Cambridge, MA, USA, Canada, December 04–07, 2006, pp 193–200

  • Burges CJC, Shaked T, Renshaw E, Lazier A, Deeds M, Hamilton N, Hullender GN (2005) Learning to rank using gradient descent. In: Proc. int. conf. on machine learning (ICML), Bonn, Germany, August 7–11, 2005, pp 89–96. https://doi.org/10.1145/1102351.1102363

  • Busa-Fekete R, Szarvas G, Elteto T, Kégl B (2012) An apple-to-apple comparison of learning-to-rank algorithms in terms of normalized discounted cumulative gain. In: Proc. ECAI work. on preference learning: problems and applications in AI, vol 242, Ios Press

  • Chakrabarti S (2007) Learning to rank in vector spaces and social networks. Internet Math 4(1–3):267–298

    Article  MathSciNet  MATH  Google Scholar 

  • Chen C, Shih SY, Lee M (2016) Who should you follow? Combining learning to rank with social influence for informative friend recommendation. Decis Support Syst 90:33–45

    Article  Google Scholar 

  • Chen W, Liu TY, Lan Y, Ma Z, Li H (2009) Ranking measures and loss functions in learning to rank. In: Proc. conf. on neural information processing systems (NIPS), Vancouver, British Columbia, Canada, pp 315–323

  • Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297

    MATH  Google Scholar 

  • Domenico MD, Lima A, Mougel P, Musolesi M (2013) The anatomy of a scientific rumor. Sci Rep 3:2980

    Article  Google Scholar 

  • Easley D, Kleinberg J (2010) Networks, crowds, and markets: reasoning about a highly connected world. Cambridge University Press, Cambridge

    Book  MATH  Google Scholar 

  • Edelmann N (2013) Reviewing the definitions of “lurkers” and some implications for online research. Cyberpsychol Behav Soc Netw 16(9):645–649

    Article  Google Scholar 

  • Farzan R, Brusilovsky P (2011) Encouraging user participation in a course recommender system: an impact on user behavior. Comput Hum Behav 27(1):276–284

    Article  Google Scholar 

  • Farzan R, DiMicco JM, Brownholtz B (2010) Mobilizing lurkers with a targeted task. In: Proc. int. conf. on weblogs and social media (ICWSM), Washington, DC, USA, May 23–26, 2010

  • Ferro N, Lucchese C, Maistro M, Perego R (2017) On including the user dynamic in learning to rank. In: Proc. ACM SIGIR conf. on research and development in information retrieval (SIGIR), Shinjuku, Tokyo, Japan, August 7–11, 2017, pp 1041–1044. https://doi.org/10.1145/3077136.3080714

  • Freund Y, Schapire RE (1995) A decision-theoretic generalization of on-line learning and an application to boosting. In: Proc. European conf. on computational learning theory (EuroCOLT), Barcelona, Spain, March 13–15, 1995, pp 23–37. https://doi.org/10.1007/3-540-59119-2_166

  • Friedman JH (2000) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232

    Article  MathSciNet  MATH  Google Scholar 

  • Hall MA (1999) Correlation-based feature selection for machine learning. PhD Thesis, University of Waikato, Hamilton

  • Hastie T, Rosset S, Zhu J, Zou H (2009) Multi-class adaboost. Stat Interface 2(3):349–360

    Article  MathSciNet  MATH  Google Scholar 

  • Hofmann K, Whiteson S, Schuth A, de Rijke M (2014) Learning to rank for information retrieval from user interactions. ACM SIGWEB Newsletter. https://doi.org/10.1145/2591453.2591458

    Article  Google Scholar 

  • Hong L, Bekkerman R, Adler J, Davison B (2012) Learning to rank social update streams. In: Proc. ACM SIGIR conf. on research and development in information retrieval (SIGIR), Portland, OR, USA, August 12–16, 2012, pp 651–660. https://doi.org/10.1145/2348283.2348371

  • Huang J, Zhang W, Zhao S, Ding S, Wang H (2017) Learning to explain entity relationships by pairwise ranking with convolutional neural networks. In: Proc. int. joint conf. on artificial intelligence (IJCAI), pp 4018–4025

  • Imlawi J, Gregg DG (2014) Engagement in online social networks: the impact of self-disclosure and humor. Int J Hum Comput Interact 30(2):106–125

    Article  Google Scholar 

  • Interdonato R, Pulice C, Tagarelli A (2015) “Got to have faith!”: The DEvOTION algorithm for delurking in social networks. In: Proc. int. conf. on advances in social networks analysis and mining (ASONAM), Paris, France, August 25–28, 2015, pp 314–319. https://doi.org/10.1145/2808797.2809394

  • Interdonato R, Tagarelli A (2016) To trust or not to trust lurkers?: evaluation of lurking and trustworthiness in ranking problems. In: Proc. int. school and conf. on network science (NetSciX), Poland, January 11–13, 2016. https://doi.org/10.1007/978-3-319-28361-6_4

  • Järvelin K, Kekäläinen J (2000) IR evaluation methods for retrieving highly relevant documents. In: Proc. ACM SIGIR conf. on research and development in information retrieval (SIGIR), pp 41–48

  • Javarone MA, Interdonato R, Tagarelli A (2016) Modeling evolutionary dynamics of lurking in social networks. In: Proc. 7th workshop on complex networks (CompleNet), Dijon, France, March 23–25, 2016, pp 227–239. https://doi.org/10.1007/978-3-319-30569-1_17

  • Lave J, Wenger E (1991) Situated learning: legitimate peripheral participation. Cambridge University Press, Cambridge

    Book  Google Scholar 

  • Lei C, Liu D, Li W (2016) Social diffusion analysis with common-interest model for image annotation. IEEE Trans Multimed 18(4):687–701

    Article  Google Scholar 

  • Liu T (2011) Learning to rank for information retrieval. Springer, Berlin

    Book  MATH  Google Scholar 

  • Lu H, Chen C, Kong M, Zhang H, Zhao Z (2016) Social recommendation via multi-view user preference learning. Neurocomputing 216:61–71

    Article  Google Scholar 

  • Luo Z, Osborne M, Wang T (2015) An effective approach to tweets opinion retrieval. World Wide Web 18(3):545–566

    Article  Google Scholar 

  • Malliaros FD, Vazirgiannis M (2013) To stay or not to stay: modeling engagement dynamics in social graphs. In: Proc. ACM conf. on information and knowledge management (CIKM), San Francisco, CA, USA, October 27–November 1, 2013, pp 469–478. https://doi.org/10.1145/2505515.2505561

  • Martin S, Brown WM, Klavans R, Boyack KW (2011) Openord: an open-source toolbox for large graph layout. In: Visualization and data analysis, San Francisco Airport, CA, USA, January 24–25, 2011, p 786806. https://doi.org/10.1117/12.871402

  • Martins F, Magalhes J, Callan J (2016) Barbara made the news: mining the behavior of crowds for time-aware learning to rank. In: Proc. ACM conf. on web search and web data mining (WSDM), San Francisco, CA, USA, February 22–25, 2016, pp 667–676. https://doi.org/10.1145/2835776.2835825

  • Metzler D, Croft WB (2007) Linear feature-based models for information retrieval. Inf Retr 10(3):257–274

    Article  Google Scholar 

  • Nonnecke B, Preece JJ (2000) Lurker demographics: counting the silent. In: Proc. ACM conf. on human factors in computing systems (CHI), pp 73–80

  • Pan Z, Lu Y, Gupta S (2014) How heterogeneous community engage newcomers? The effect of community diversity on newcomers’ perception of inclusion: an empirical study in social media service. Comput Hum Behav 39:100–111

    Article  Google Scholar 

  • Perna D, Interdonato R, Tagarelli A (2018) Identifying users with alternate behaviors of lurking and active participation in multilayer social networks. IEEE Trans Comput Soc Syst 5(1):46–63

    Article  Google Scholar 

  • Perna D, Tagarelli A (2017) An evaluation of learning-to-rank methods for lurking behavior analysis. In: Proc. int. conf. on user modeling, adaptation and personalization, UMAP, Bratislava, Slovakia, July 09–12, 2017, pp 381–382. https://doi.org/10.1145/3079628.3079650

  • Preece JJ, Nonnecke B, Andrews D (2004) The top five reasons for lurking: improving community experiences for everyone. Comput Hum Behav 20(2):201–223

    Article  Google Scholar 

  • Rowe M (2013) Mining user lifecycles from online community platforms and their application to churn prediction. In: Proc. IEEE int. conf. on data mining (ICDM), Dallas, TX, USA, December 7–10, 2013, pp 637–646. https://doi.org/10.1109/ICDM.2013.78

  • Silvestri G, Yang J, Bozzon A, Tagarelli A (2015) Linking accounts across social networks: the case of stackoverflow, github and twitter. In: Proc. int. workshop on knowledge discovery on the web, Cagliari, Italy, September 3–5, 2015, pp 41–52. http://ceur-ws.org/Vol-1489/paper-05.pdf

  • Srinivasan B, Natarajan A, Sinha R, Gupta V, Revankar S, Ravindran B (2013) Will your Facebook post be engaging? In: Proc. ACM conf. on information and knowledge management (CIKM), pp 25–28

  • Sun N, Rau PPL, Ma L (2014) Understanding lurkers in online communities: a literature review. Comput Hum Behav 38:110–117

    Article  Google Scholar 

  • Tabourier L, Libert A, Lambiotte R (2014) RankMerging: learning to rank in large-scale social networks. In: Proc. ECML PKDD workshop on dynamic networks and knowledge discovery (DyNaK), Nancy, France, September 15, 2014

  • Tagarelli A, Interdonato R (2013) “Who’s out there?”: identifying and ranking lurkers in social networks. In: Proc. int. conf. on advances in social networks analysis and mining (ASONAM), Niagara, ON, Canada, August 25–29, 2013, pp 215–222. https://doi.org/10.1145/2492517.2492542

  • Tagarelli A, Interdonato R (2014) Lurking in social networks: topology-based analysis and ranking methods. Soc Netw Anal Min 4(230):27

    Google Scholar 

  • Tagarelli A, Interdonato R (2015) Time-aware analysis and ranking of lurkers in social networks. Soc Netw Anal Min 5(1):23

    Article  Google Scholar 

  • Tian Q, Li B (2016) Weakly hierarchical lasso based learning to rank in best answer prediction. In: Proc. int. conf. on advances in social networks analysis and mining (ASONAM), San Francisco, CA, USA, August 18–21, 2016, pp 307–314. https://doi.org/10.1109/ASONAM.2016.7752250

  • Tsai CH, Lou JK, Lu WC, Lin SD (2014) Exploiting rank-learning models to predict the diffusion of preferences on social networks. In: Proc. int. conf. on advances in social networks analysis and mining (ASONAM), Beijing, China, August 17–20, 2014, pp 265–272. https://doi.org/10.1109/ASONAM.2014.6921595

  • Tsai H, Pai P (2014) Why do newcomers participate in virtual communities? An integration of self-determination and relationship management theories. Decis Support Syst 57:178–187. https://doi.org/10.1016/j.dss.2013.09.001

    Article  Google Scholar 

  • Wang Y, Wang L, Li Y, He D, Liu T (2013) A theoretical analysis of NDCG type ranking measures. In: Proc. annual conf. on learning theory (COLT), Princeton University, NJ, USA, June 12–14, 2013, pp 25–54

  • Wu Q, Burges CJC, Svore KM, Gao J (2010) Adapting boosting for information retrieval measures. Inf Retr 13(3):254–270

    Article  Google Scholar 

  • Xu J, Li H (2007) Adarank: a boosting algorithm for information retrieval. In: Proc. ACM SIGIR conf. on research and development in information retrieval (SIGIR), Amsterdam, The Netherlands, July 23–27, 2007, pp 391–398. https://doi.org/10.1145/1277741.1277809

  • Xu T, Zhu H, Chen E, Huai B, Xiong H, Tian J (2014) Learning to annotate via social interaction analytics. Knowl Inf Syst 41(2):251–276

    Article  Google Scholar 

  • Zamani H, Shakery A, Moradi P (2014) Regression and learning to rank aggregation for user engagement evaluation. In: Proc. ACM recommender systems challenge (RecSysChallenge), ACM, p 29

  • Zhao W, Li S, He Y, Wang L, Wen JR, Li X (2016) Exploring demographic information in social media for product recommendation. Knowl Inf Syst 49(1):61–89

    Article  Google Scholar 

  • Zhuang J, Mei T, Hoi S, Hua XS, Li S (2011) Modeling social strength in social media community via kernel-based learning. In: Proc. ACM multimedia conf. and co-located workshops, Scottsdale, AZ, USA, November 28–December 1, 2011, pp 113–122. https://doi.org/10.1145/2072298.2072315

  • Zin T, Tin P, Hama H (2017) Deep learning model for integration of clustering with ranking in social networks. Adv Intell Syst Comput 536:247–254

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. DIMES, University of Calabria, Rende, Italy

    Diego Perna & Andrea Tagarelli

  2. Cirad, UMR Tetis, Montpellier, France

    Roberto Interdonato

Authors
  1. Diego Perna
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Roberto Interdonato
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Andrea Tagarelli
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Andrea Tagarelli.

Additional information

An abridged version of this paper appeared in Perna and Tagarelli (2017).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Perna, D., Interdonato, R. & Tagarelli, A. Learning to lurker rank: an evaluation of learning-to-rank methods for lurking behavior analysis. Soc. Netw. Anal. Min. 8, 39 (2018). https://doi.org/10.1007/s13278-018-0516-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13278-018-0516-z

Keywords

Search

Navigation