Abstract
Researchers have long been interested in the role that norms can play in governing agent actions in multi-agent systems (MAS). Much work has been done on formalising normative concepts from human society and adapting them for the government of open software systems, and on the simulation of normative processes in human and artificial societies. However, there has been comparatively little work on applying normative MAS mechanisms to learn the norms existing in human society.
This work investigates this issue in the context of international politics. Using the GDELT dataset, containing machine-encoded records of international events mentioned in news reports, we extracted bilateral sequences of inter-country events and applied a Bayesian norm mining mechanism to identify norms that best explained the observed behaviour. A statistical evaluation showed that the normative model fitted the data significantly better than a probabilistic discrete event model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
We omit conflict event types (such as Threaten, Assault and Fight) from this list, as we consider these to be events that are likely to be subject to norms, rather than reactions to norm violations.
- 2.
Some sequences contained as many as 20,000 events.
- 3.
- 4.
The priors were are initialised to 1 for all of the norms we consider. However, this choice has no significant effect as we are interested in the relative posterior odds.
- 5.
Note that this approach only reasons about single-norm hypotheses. Based on the log odds of individual norms, it would be possible to select combinations of most likely norms to form multi-norm hypotheses, but this requires a more complex model of observation likelihood than we have at present.
- 6.
The transition annotations have the format \( trigger [ guard ] / action \). Transitions from the initial state have no trigger, and guards and actions are optional.
- 7.
To simplify the model, only the first instantiation, fulfilment, violation and sanction of a norm within a sequence are tracked by the state machine.
- 8.
We perform the calculations in log space, resulting in a log likelihood, but for simplicity of presentation we do not show this.
- 9.
In the case of unconditional norms, this is once for every observation.
- 10.
Add-one smoothing involves adding one to both positive and negative counts, hence the “+2” in the denominator (the total count).
- 11.
Recall from Sect. 5 that we train sequence memoizers with two copies of each event sequences: one with its default directions (where the first event is taken to be “forwards” and a direction-reversed copy of the sequence).
- 12.
The number was constrained by the highly time-intensive process of looking up the SM’s conditional probabilities to generate and to evaluate the likelihood of these large datasets.
- 13.
Murphy discusses the relationship between sampling from the posterior and the well known bootstrap method for approximating the sampling distribution of a test statistic [22, p.192].
References
Andrighetto, G., Governatori, G., Noriega, P., van der Torre, L.W.N. (eds.) Normative Multi-Agent Systems, Dagstuhl Follow-Ups, vol. 4. Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik (2013)
Avery, D., Dam, H.K., Savarimuthu, B.T.R., Ghose, A.: Externalization of software behavior by the mining of norms. In: 13th International Conference on Mining Software Repositories, pp. 223–234. ACM (2016)
Balke, T., Novais, P., Andrade, F.C.P., Eymann, T.: From real-world regulations to concrete norms for software agents: a case-based reasoning approach. In: International Workshop on Legal and Negotiation Decision Support Systems (LDSS), pp. 14–27. CEUR Workshop Proceedings (2009)
Blei, D.M.: Build, compute, critique, repeat: data analysis with latent variable models. Ann. Revi. Stat. Appl. 1, 203–232 (2014)
de Cadenas-Santiago, G., Herrero, A.G., Vidal-Abarca, Á.O., López, T.R.: An empirical assessment of social unrest dynamics and state response in eurasian countries. Eurasian J. Soc. Sci. 3(3), 1–29 (2015)
Campos, J., López-Sánchez, M., Esteva, M.: A case-based reasoning approach for norm adaptation. In: Corchado, E., Graña Romay, M., Manhaes Savio, A. (eds.) HAIS 2010. LNCS (LNAI), vol. 6077, pp. 168–176. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-13803-4_21
Conte, R., Dellarocas, C. (eds.). Social Order in Multiagent Systems. Springer, Boston (2001). https://doi.org/10.1007/978-1-4615-1555-5
Corapi, D., Russo, A., De Vos, M., Padget, J., Satoh, K.: Normative design using inductive learning. Theor. Pract. Log. Prog. 11(4–5), 783–799 (2011)
Cranefield, S., Meneguzzi, F., Oren, N., Savarimuthu, B.T.R.: A Bayesian approach to norm identification. In: 22nd European Conference on Artificial Intelligence. Frontiers in Artificial Intelligence and Applications, vol. 285, pp. 622–629. IOS Press (2016)
Dam, H.K., Savarimuthu, B.T.R., Avery, D., Ghose, A.: Mining software repositories for social norms. In: 37th International Conference on Software Engineering, vol. 2, pp. 627–630. IEEE (2015)
Fornara, N., Colombetti, M.: A commitment-based approach to agent communication. Appl. Artif. Intell. 18(9–10), 853–866 (2004)
Gao, J., Leetaru, K.H., Hu, J., Cioffi-Revilla, C., Schrodt, P.: Massive media event data analysis to assess world-wide political conflict and instability. In: Social Computing, Behavioral-Cultural Modeling and Prediction, pp. 284–292. Springer, Cham (2013). https://doi.org/10.1007/978-3-642-37210-0_31
Gao, X., Singh, M.P.: Extracting normative relationships from business contracts. In: International Conference on Autonomous Agents and Multi-Agent Systems, pp. 101–108. IFAAMAS (2014)
Gasthaus, J., Teh, Y.W.: Improvements to the sequence memoizer. In: Advances in Neural Information Processing Systems, 23, pp. 685–693. Curran Associates, Inc. (2010)
The GDELT Event Database – Data format Codebook v2.0. http://data.gdeltproject.org/documentation/GDELT-Event_Codebook-V2.0.pdf (2015)
Jiang, L., Mai, F.: Discovering Bilateral and Multilateral Causal Events in GDELT. Paper presented at the International Conference on Social Computing, Behavioral-Cultural Modeling, and Prediction. Washington D.C. (2014)
Keertipati, S., Savarimuthu, B.T.R., Purvis, M., Purvis, M.: Multi-level analysis of peace and conflict data in GDELT. In: Proceedings of the 2nd Workshop on Machine Learning for Sensory Data Analysis, pp. 33–40. ACM (2014). https://doi.org/10.1145/2689746.2689750
Kelsen, H.: General Theory of Norms. Clarendon Press (1990)
Keneshloo, Y., Cadena, J., Korkmaz, G., Ramakrishnan, N.: Detecting and forecasting domestic political crises: a graph-based approach. In: Proceedings of the 2014 ACM Conference on Web Science, pp. 192–196. WebSci 2014, ACM (2014). https://doi.org/10.1145/2615569.2615698
Leetaru, K., Schrodt, P.A.: GDELT: global data on events, location, and tone, 1979–2012. In: Proceedings of the International Studies Association Annual Convention (2013). http://data.gdeltproject.org/documentation/ISA.2013.GDELT.pdf
Murali, R., Patnaik, S., Cranefield, S.: Bilateral government event sequences extracted from the GDELT database for the period 19 June 2018 to 20 June 2019. Dataset (2021). https://doi.org/10.6084/m9.figshare.13557809
Murphy, K.P.: Machine Learning: A Probabilistic Perspective. The MIT Press, Cambridge (2012)
Qiao, F., Li, P., Deng, J., Ding, Z., Wang, H.: Graph-based method for detecting occupy protest events using GDELT dataset. In: International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, pp. 164–168. IEEE (2015)
Racette, M.P., Smith, C.T., Cunningham, M.P., Heekin, T.A., Lemley, J.P., Mathieu, R.S.: Improving situational awareness for humanitarian logistics through predictive modeling. In: Systems and Information Engineering Design Symposium (SIEDS), 2014, pp. 334–339. IEEE (2014)
Savarimuthu, B.T.R., Cranefield, S., Purvis, M.A., Purvis, M.K.: Obligation norm identification in agent societies. J. Artif. Soc. Soc. Simulat. 13(4) (2010). https://doi.org/10.18564/jasss.1659
Savarimuthu, B.T.R., Cranefield, S., Purvis, M.A., Purvis, M.K.: Identifying prohibition norms in agent societies. Artif. Intell. Law 21(1), 1–46 (2013)
Schrodt, P.A.: CAMEO: Conflict and Mediation Event Observations Event and Actor Codebook (2012). http://data.gdeltproject.org/documentation/CAMEO.Manual.1.1b3.pdf
Sen, S., Airiau, S.: Emergence of norms through social learning. In: Proceedings of the 20th International Joint Conference on Artificial Intelligence, pp. 1507–1512 (2007)
Shoham, Y., Tennenholtz, M.: On the emergence of social conventions: modeling, analysis, and simulations. Artif. Intell. 94(1), 139–166 (1997)
Tan, Z.X., Brawer, J., Scassellati, B.: That’s mine! learning ownership relations and norms for robots. In: Thirty-Third AAAI Conference on Artificial Intelligence, pp. 8058–8065. AAAI Press (2019)
Telang, P.R., Singh, M.P., Yorke-Smith, N.: A coupled operational semantics for goals and commitments. J. Artif. Intell. Res. 65, 31–85 (2019)
Ulfelder, J.: Another note on the limitations of event data (2014). https://dartthrowingchimp.wordpress.com/2014/06/06/another-note-on-the-limitations-of-event-data
Wilks, S.S.: The large-sample distribution of the likelihood ratio for testing composite hypotheses. Ann. Math. Stat. 9(1), 60–62 (1938)
Wood, F., Gasthaus, J., Archambeau, C., James, L., Teh, Y.: The sequence memoizer. Commun. ACM 54(2), 91–98 (2011)
Yonamine, J.E.: A nuanced study of political conflict using the Global Datasets of Events Location and Tone (GDELT) dataset. Ph.D. thesis, Pennsylvania State University (2013)
Acknowledgement
We thank Matt Schofield for statistical advice.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Murali, R., Patnaik, S., Cranefield, S. (2021). Mining International Political Norms from the GDELT Database. In: Aler Tubella, A., Cranefield, S., Frantz, C., Meneguzzi, F., Vasconcelos, W. (eds) Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems XIII. COIN COINE 2017 2020. Lecture Notes in Computer Science(), vol 12298. Springer, Cham. https://doi.org/10.1007/978-3-030-72376-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-72376-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-72375-0
Online ISBN: 978-3-030-72376-7
eBook Packages: Computer ScienceComputer Science (R0)