SciELO - Scientific Electronic Library Online

vol.17 issue2A Supervised Approach for Reconstructing Thread Structure in Comments on Blogs and Online News AgenciesDetecting Salient Events in Large Corpora by a Combination of NLP and Data Mining Techniques author indexsubject indexsearch form
Home Pagealphabetic serial listing  

Services on Demand




Related links

  • Have no similar articlesSimilars in SciELO


Computación y Sistemas

Print version ISSN 1405-5546

Comp. y Sist. vol.17 n.2 México Apr./Jun. 2013




Using Stylistic Features for Social Power Modeling


El uso de características estilísticas para modelado del poder social


Rachel Cotterill


University of Sheffield, UK


Article received on 08/12/2012
Accepted on 17/01/2013.



Social Network Analysis traditionally examines the graph of a communications network to identify key individuals based on the pattern of their interactions, but there is a limit to the level of detail which can be inferred from metadata alone. Message content is a richer source of data, and can provide an indication of the relationship between a pair of communicants. An individual's language use will vary depending on their relationship to the addressee, and this paper investigates a set of stylistic features which may be used to predict the nature of a relationship within an organizational hierarchy. Experiments are conducted on the Enron corpus for the sake of comparison with earlier results, and demonstrate successful classification of upspeak vs. downspeak using a small feature set.

Keywords: Social network analysis, social power modeling, stylistics, text mining.



El análisis de redes sociales examina tradicionalmente el grafo de una red de comunicaciones, con el fin de identificar personas clave basándose en el patrón de sus interacciones, pero existe un límite respecto al nivel de detalle que se puede inferir únicamente a partir de metadatos. El contenido de mensajes es una fuente más rica de datos y puede proporcionar la indicación de una relación entre un par de comunicantes. El uso de idioma en personas varía dependiendo de sus relaciones con los destinatarios, entonces este trabajo investiga un conjunto de las características estilísticas que pueden ser utilizados para predecir la naturaleza de una relación dentro de la jerarquía de una organización. Los experimentos se realizaron sobre el corpus Enron para comparar los resultados obtenidos con los anteriores, y mostraron la clasificación exitosa de mensajes dirigidos a personas en la posición más alta en la jerarquía (upspeak) vs mensajes dirigidos hacia abajo en la jerarquía (downspeak) utilizando un pequeño conjunto de características.

Palabras clave: Análisis de redes sociales, modelado del poder social, estilística, minería de texto.





1. Bramsen, P., Escobar-Molano, M., Patel, A., & Alonso, R. (2011). Extracting Social Power Relationships from Natural Language. 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (HLT 2011), Portland, Oregon, 1, 773-782.         [ Links ]

2. Brown, P. & Levinson, S.C. (1987). Politeness: Some Universals in Language Usage. Cambridge; New York: Cambridge University Press.         [ Links ]

3. Duthler, K.W. (2006). The Politeness of Requests Made via Email and Voicemail: Support for the Hyperpersonal Model. Journal of Computer Mediated Communication, 11(2), article 6.         [ Links ]

4. Gallagher, I. (2010). Bayesian Block Modeling for Weighted Networks. Eighth Workshop on Mining and Learning with Graphs (MLG'10), Washington, DC, 55-61.         [ Links ]

5. Unicode 6.0.0. Retrieved from        [ Links ]

6. Grice, H.P. (1975). Logic and Conversation. Syntax and Semantics, Volume 3: Speech Acts (41-58). New York: Academic Press.         [ Links ]

7. Heylighen, F. & Dewaele, J.M. (2002). Variation in the Contextuality of Language: an Empirical Measure. Foundations of Science, 7(3), 293-340.         [ Links ]

8. Jabbari, S., Allison, B., Guthrie, D., & Guthrie, L. (2006). Towards the Orwellian Nightmare: Separation of business and personal emails. 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics (ACL 2006), Sydney, Australia.         [ Links ]

9. Klimt, B. & Yang, Y. (2004). Introducing the Enron Corpus. First Conference on Email and Anti-Spam (CEAS), Mountain View, California.         [ Links ]

10. Lakoff, R. (1973). Language and a Woman's Place. Language in Society, 2(1), 45-80.         [ Links ]

11. Panteli, N. (2002). Richness, Power Cues and Email Text. Information and Management, 40(2), 75-86.         [ Links ]

12. Peterson, K., Hohensee, M., & Xia, F. (2011). Email Formality in the Workplace: A Case Study on the Enron Corpus. Workshop on Languages in Social Media (LSM11), Portland, Oregon, 86-95.         [ Links ]

13. Rowe, R., Creamer, G., Hershkop, S., & Stolfo, S.J. (2007). Automated Social Hierarchy Detection through email Network Analysis. 9th WebKDD and 1st SNA-KDD 2007 workshop on Web mining and social network analysis, San Jose, California, 109-117.         [ Links ]

14. Searle, J.R. (1969). Speech Acts: An essay in the philosophy of language. London: Cambridge University Press.         [ Links ]

15. Waldvogel, J. (2007). Greetings and Closings in Workplace Email. Journal of Computer-Mediated Communication, 12(2), article 6.         [ Links ]

16. WEKA 3. (s.f.). Data Mining Software in Java. Retrieved from         [ Links ]

Creative Commons License All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License