Extracting Social Meaning from Linguistic Structures in African Languages (ESCALES)

Funded by: The Army Research Lab
PIs: Lori Levin and Carolyn Rosé

The key objective of this project is to investigate the social meaning of Codeswitching (CS) and other discursive phenomena such as discourse markers, speech acts, and contexualization cues. In particular, we seek to determine what it is that bilingual speakers communicate when they engage in CS and related phenomena, and to develop language technologies to make it feasible to extract that social meaning from an electronic text. The project focuses on CS involving English (and French) with selected African languages: Swahili, Zulu, Ciluba, and Lingala. Swahili is a lingua franca in East Africa; Zulu is a lingua franca in the province of KwaZulu-Natal, South Africa; and Ciluba and Lingala are regional lingua francas in the Democratic Republic of Congo (former Zaire).

My part of this project focuses on operationalization of conversational style and social interpretation of codeswitching.

Selected Recent Publications

  1. Rosé, C. P. & Tovares, A. (in press). What Sociolinguistics and Machine Learning Have to Say to One Another about Interaction Analysis, in Resnick, L., Asterhan, C., Clarke, S. (Eds.) Socializing Intelligence Through Academic Talk and Dialogue, Washington, DC: American Educational Research Association.
  2. Gweon, G., Jain, M., Mc Donough, J., Raj, B., Rosé, C. P. (in press). Measuring Prevalence of Other-Oriented Transactive Contributions Using an Automated Measure of Speech Style Accommodation, International Journal of Computer Supported Collaborative Learning
  3. Mayfield, E., Adamson, D., Rudnicky, A., & Rosé, C. P. (2012). Computational Representation of Discourse Practices in Task-based Dialogue, ICIC 2012 Proceedings of the 4th ACM International Conference on Intercultural Collaboration, pp 67-76
  4. Gianfortoni, P., Adamson, D. & Rosé, C. P. (2011). Modeling Stylistic Variation in Social Media with Stretchy Patterns, in Proceedings of First Workshop on Algorithms and Resources for Modeling of Dialects and Language Varieties, Edinburgh, Scottland, UK, pp 49-59.
  5. Nguyen, D., Mayfield, E., & Rosé, C. P. (2010). An analysis of perspectives in interactive settings, in Proceedings of the KDD Workshop on Social Media Analytics, pp 44-52.