HeadTalk was a 12 month interdisciplinary demonstrator project (2005-2006, ESRC grant No. RES-149-25-1016) involving Applied Linguists and Computer Vision experts based at the University of Nottingham. This project, funded by the ESRC’s National Centre for e-Social Science, focused upon the development and exploitation of computer vision techniques that are able to annotate video streams and mark-up gesture-in-talk, allowing for detailed empirical explorations of markers of active listenership (backchannels) in discourse. It focused specifically upon exploring the existence, functions and roles of a sub-group of backchannels; head nods, in dyadic conversation.
Explorations of an initial one-hour recording of an academic supervision session provided the data for exploring the fundamentals of verbal and non-verbal backchanneling, i.e. for exploring both similarities and differences in the basic forms and linguistic functions of non-verbal and verbal backchannels, and for identifying relationships between the two groups. The findings from these explorations were used to define approximate parameters for the linguistic characteristics of gesture-in-talk, which were then cross compared with the analyses of various characteristics of non-verbal behaviour (such as the intensity, frequency and length of backchanneling head nods), conducted by the image experts.
The results from this iterative process allowed us to start to identify relationships across, between and within the different communicative 'modes', and has provided the foundations for a coding scheme that integrates information concerning the characteristics of both non-verbal and verbal aspects of talk. As part of the, associated, Digital Record project (refer to project page), this scheme will be extended to include other features of gesture-in-talk, making the scheme invaluable to linguistic and gesture research as although coding schemes and systems of mark-up for dealing with both verbal and non-verbal behaviour have long existed, until now no standardized scheme for combining the two has been developed.
This project was completed in 2006, although the research carried out as part of HeadTalk was used to lay the foundations of research for the Digital Record Project. In addition to this, HeadTalk has been extended as the basis for an ESRC funded PhD thesis by Dawn Knight.
Reports, Conference Papers and Publications
- Carter, R., Knight, D. & Adolphs, S. (2006). Head-Talk: Towards a multi-modal corpus. Paper delivered at Joint Annual Meeting of the British Association for Applied Linguistics and the Irish Association for Applied Linguistics Conference, Cork, Ireland, 7 - 9 September 2006.
- Knight, D., Adolphs, S. & Carter, R. (2006). The linguistic coding of verbal and non-verbal backchannels: a preliminary approach. Node meeting presentation and report, Nottingham, July 2006.
- Knight, D., Bayoumi, S., Mills, S., Crabtree, A., Adolphs, A., Pridmore, T. & Carter, C. (2006). Beyond the Text: Construction and Analysis of Multi-Modal Linguistic Corpora. Published in the Proceedings of the 2nd International Conference on e-Social Science, Manchester, 28 - 30 June 2006.
- Knight, D., Bayoumi, S., Mills, S., Crabtree, A., Adolphs, A., Pridmore, T. & Carter, C. Beyond the Text: Construction and Analysis of Multi-Modal Linguistic Corpora. (2006). Paper delivered at 2nd International Conference on e-Social Science, Manchester, 28 – 30 June 2006.
- Knight, D., Carter, R. & Adolphs, S. (2006). The Multi-Modal Corpus: Coding and representing data- the issues. Paper delivered at 3rd IVACS conference, Nottingham, 23 – 24 June 2006.
- Adolphs, S. & Knight, D. Analysing spoken corpora: Methodological issues and technical challenges. (2006). Paper delivered at BAAL SIG Seminar (Special Interest Group: Corpus Linguistics), Milton Keynes, 28 April 2006.
- Knight, D. (2006). Developing a Multi-Modal Corpus: Data Coding Issues. Paper delivered at IVACS Annual Research Symposium, University of Limerick, Ireland, 4 February 2006.
- Knight, D., Carter, R. & Adolphs, D. (2006). The linguistic coding of backchannels: A proposed methodological approach. Node meeting presentation and report, Nottingham, December 2005.
- Knight, D., Carter, R. & Adolphs, S. (2005). HeadTalk: Issues in multi-modal communication analysis. Node meeting presentation and report, Nottingham, October 2005.
CRAL Project Staff
If you would like more information on any aspect of this research, do not hesitate to contact a member of the CRAL staff involved, as detailed below:
Back to top