I am working on the topic of ‘spatialised communication’ with the aim to see how computational models of grounding can be enriched with spatial information. Example: If I get a message M enriched with information that it has been posted when the emitter was located at P , this contextual information will trigger various inferences that guide my interpretation of M.

The goal of my research would be to build an algorithm that parse and meta-tag the messages of a system in which the users exchange SMS-style mess. attaching them to a 2D map/representation of the city space. This algorithm should be able to give a sense of people interaction into the system knowing the emission contextual information, kind of replicating the cognitive processes of people while exposed in the same acknowledgments of facts. These meta-tags attached should be an ontological categorisation of the message that could be re-used to enhance the message retrieval or re-aggregation for other purposes.

Particularly, my study should demonstrate how providing these automatically-generated descriptors can sustain the communication process economising in some way the content of the messages. The research question I am working on is: Does providing the message receiver with emission contextual information, i.e., the history of locations, enable the receiver to infer more effectively the meaning of the message?

The core literature I am following at this early stage is:

[1] Traum, D. R. (1999). Computational models of grounding in collaborative systems. In working notes of AAAI Fall Symposium on Psychological Models of Communication, pages 124–131.

[2] Clark, H. and Brennan, S. (1991). Perspectives on Socially Shared Cognition, chapter Grounding in Communication, pages 127–149. American Psychological Association, Washington.

[3] Dillenbourg, P., Traum, D., and Schneider, D. (1996). Grounding in multi-modal task-oriented collaboration. In Proceedings of the European Conference on AI in Education, pages 415–425, Lisbon, Portugal.

[4] Baker, M. (1994). A model for negotiation in teaching-learning dialogues. Journal of Artificial Intelligence in Education, 5(2):199–245.