On the multilingual and genre robustness of EmoGraphs for author profiling in social media

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-24027-5_28Author profiling aims at identifying different traits such as age and gender of an author on the basis of her writings. We propose the novel EmoGraph graph-based approach where morphosyntactic categories are enriched with semantic and affective information. In this work we focus on testing the robustness of EmoGraphs when applied to age and gender identification. Results with PAN-AP-14 corpus show the competitiveness of the representation over genres and languages. Finally, some interesting insights are shown, for example with topic and emotion bounded genres such as hotel reviews.The research has been carried out in the framework of the European Commission WIQ-EI IRSES (no. 269180) and DIANA - Finding Hidden Knowledge in Texts (TIN2012-38603-C02) projects. The work of the first author was partially funded by Autoritas Consulting SA and by Spanish Ministry of Economics under grant ECOPORTUNITY IPT-2012-1220-430000.Rangel, F.; Rosso, P. (2015). On the multilingual and genre robustness of EmoGraphs for author profiling in social media. En Experimental IR Meets Multilinguality, Multimodality, and Interaction: 6th International Conference of the CLEF Association, CLEF'15, Toulouse, France, September 8-11, 2015, Proceedings. Springer International Publishing. 274-280. https://doi.org/10.1007/978-3-319-24027-5_28274280Argamon, S., Koppel, M., Fine, J., Shimoni, A.: Gender, genre, and writing style informal written texts. TEXT 23, 321–346 (2003)Levin, B.: English Verb Classes and Alternations. University of Chicago Press, Chicago (1993)Mohammad, S.M., Yang, T.: Tracking sentiment in mail: how gender differ on emotional axes. In: Proceedings of the 2nd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis (2011)Pennebaker, J.W.: The Secret Life of Pronouns: What Our Words Say About Us. Bloomsbury Press (2011)Rangel, F., Rosso, P.: On the impact of emotions on author profiling. Information Processing & Management, Special Issue on Emotion and Sentiment in Social and Expressive Media (in press, 2015)Rangel, F., Rosso, P., Chugur, I., Potthast, M., Trenkmann, M., Stein, B., Verhoeven, B., Daelemans, W.: Overview of the 2nd author profiling task at pan 2014. In: Cappellato L., Ferro N., Halvey M., Kraaij, W. (eds.) CLEF 2014 Labs and Workshops, Notebook Papers. CEUR-WS.org, vol. 1180 (2014)Rangel, F., Rosso, P., Koppel, M., Stamatatos, E., Inches, G.: Overview of the author profiling task at pan 2013. In: Forner, P., Navigli, R., Tufis, D. (eds.) Notebook Papers of CLEF 2013 LABs and Workshops. CEUR-WS.org, vol. 1179 (2013)Sidorov, G., Miranda-Jimnez, S., Viveros-Jimnez, F., Gelbukh, F., Castro-Snchez, N., Velsquez, F., Daz-Rangel, I., Surez-Guerra, S., Trevio, A., Gordon-Miranda, J.: Empirical study of opinion mining in spanish tweets. In: 11th Mexican International Conference on Artificial Intelligence, MICAI, pp. 1–4 (2012)Strapparava, C., Valitutti, A.: Wordnet-affect: an affective extension of wordnet. In: Proceedings of the 4th International Conference on Language Resources and Evaluation, Lisbon (2004