Misunderstanding The Cultural Roles Of Language Users As Language

 Doran, Martin & Zappavigna (2025: 11):

This perspective on discourse semantics has implications for the way we characterise register variables. For example, for tenor it means that discourse roles such as ‘questioner, informer, responder, doubter, contradictor and the like’, that Halliday (1978, p. 144) locates within tenor as ‘second order social roles’, would be handled as part of language, not register – via the discourse semantic system of NEGOTIATION.

Reviewer Comments:

This confuses context with language. To be clear, discourse roles such as ‘questioner, informer, responder, doubter, contradictor and the like’ are not language, but the roles of language users ('who is taking part') in a situation, and so tenor, not semantics.

ChatGPT Comments:

This is a strong and well-justified comment, Chris — and I agree completely with your diagnosis. The excerpt reflects a category error that, if left uncorrected, undermines the register-based architecture of SFL. Here's a developed version of the critique you might add to the blog, consistent with your tone and focus, and expanding a little on the theoretical implications:

---

Misplacing Discourse Roles in the Strata

The authors’ claim that discourse roles such as ‘questioner’, ‘informer’, ‘responder’, ‘doubter’, and ‘contradictor’ should be "handled as part of language, not register" reflects a fundamental confusion between context and language. This conflation mislocates the semiotic status of such roles and destabilises the theory of stratification on which SFL is founded.

In Halliday’s model (1978: 144), these roles are explicitly situated within tenor, as part of the social configuration of the context of situation. They belong to the question of “who is taking part”, including the social identities, relationships, and role configurations enacted in a given situation type. These are not linguistic categories, but contextual ones — they represent values in the system of tenor. Their realisation in language occurs via discourse semantic systems (e.g. NEGOTIATION, APPRAISAL), which are themselves realised in lexicogrammar. To treat these roles as part of language rather than register is to collapse the stratal boundary between context and semantics, confusing what language is used to enact with what is being enacted through language.

More precisely: to say that such roles are “handled via the discourse semantic system of NEGOTIATION” is only meaningful if we preserve the theoretical distinction between:

• TENOR as the contextual system that includes these role values; and

• NEGOTIATION as a semantic system that realises (i.e. enacts) those roles in discourse.

The roles do not reside in the NEGOTIATION system; they are enacted through it, as instances of context realised in language. To assign them to semantics is to mistake the means of realisation for the meaning potential being realised.

This confusion has practical consequences for register description, genre modelling, and pedagogical practice. If discourse roles are treated as linguistic rather than contextual, then our descriptions of tenor become structurally impoverished, and the explanatory bridge between contextual configuration and linguistic realisation is weakened. A theoretically coherent register model requires that such social roles be located in context (tenor), and their realisation traced systematically through semantics and grammar.