The Problem With The Notion Of Purview

Doran, Martin & Zappavigna (2025: 23):

In Chapter 3 we will describe the difference between the genuine question of ‘What are you on about Jodie’ and the rhetorical question of ‘and did I get to go’ in terms of a difference in purview that Jodie and her mother have over the knowledge. In the genuine question, Jodie’s mother gives purview over the knowledge about what Jodie’s talking about to Jodie and thus allows her to answer as she pleases. But in the rhetorical question, Jodie makes clear that she expects both of them to know the answer to the question – that is, they both have purview over the knowledge. When positioned in this way, Jodie’s mother cannot really give an answer other than the one that is expected, because Jodie has positioned them both to agree. In Chapter 3, we will illustrate that we are regularly nuancing purview in this way to help position others to respond in particular ways. We will show that it is a rich resource for enacting social relations in terms of nuancing interpersonal control and responsibility.

Reviewer Comments:

Again, moves in an exchange realise the system of SPEECH FUNCTION, and so are interpersonal potential at the level of semantics, not at the level of context (tenor).

Again, in interpreting the meanings of the exchange in terms of the knowledge of the interlocutors, the authors have adopted a cognitive perspective on language. However, this is inconsistent with SFL, the theory the authors are concerned with expanding. To be clear, in taking a 'language-based approach to cognition', SFL models 'knowledge' as meaning. Halliday & Matthiessen (1999: ix-x):

It seems to us that our dialogue is relevant to current debates in cognitive science. In one sense, we are offering it as an alternative to mainstream currents in this area, since we are saying that cognition "is" (that is, can most profitably be modelled as) not thinking but meaning: the "mental" map is in fact a semiotic map, and "cognition" is just a way of talking about language. In modelling knowledge as meaning, we are treating it as a linguistic construct: hence, as something that is construed in the lexicogrammar. Instead of explaining language by reference to cognitive processes, we explain cognition by reference to linguistic processes.

To be clear, the intellectual source of the authors' 'purview' is the work on 'epistemic authority' in social psychology, as formulated by the sociologists John Heritage and Geoffrey Raymond, in their paper The Terms of Agreement: Indexing Epistemic Authority and Subordination in Talk-in-Interaction (Social Psychology Quarterly 2005, Vol. 68, No. 1, 15-38). The term 'purview' serves the social function of a buzzword.

The Problem With The System Of Positioning

Doran, Martin & Zappavigna (2025: 23):

How we put forward positions and react to them is described in Chapters 2 and 3 within a system called POSITIONING. Chapter 2 focuses on resources for rendering meanings and Chapter 3 focuses on resources for tendering. 

When we tender meanings, we will describe different ways in which we can position others to respond. For example, when Jodie’s mother asks at the beginning of the conversation ‘What are you on about Jodie?’, she asks this as a genuine question. With this question she positions Jodie as the one who has the knowledge for this exchange. 

By contrast, later on in the conversation, Jodie notes that her not being allowed to go to the pub contrasts with her friend Billie, who is also six, getting to go to the pub. Her mother notes that this is because it was her Daddy’s birthday. But Jodie is not convinced and insists by saying ‘and did I get to go’. Although this is a question and grammatically an interrogative, Jodie is not genuinely asking for information – both Jodie and her mother know full well that she was not allowed to go to the pub. Rather, Jodie is using this to emphasise her point that she thinks there is a double standard at play. 

 Reviewer Comments:

[1] As previously demonstrated, tendering and rendering are moves in an exchange that realise the system of SPEECH FUNCTION, and so are interpersonal potential at the level of semantics, not at the level of context (tenor). The system of POSITIONING is thus interpersonal semantics misunderstood as tenor.

[2] To be clear, in interpreting the meanings of the exchange in terms of the knowledge of the interlocutors, the authors have adopted a cognitive perspective on language. However, this is inconsistent with SFL, the theory the authors are concerned with expanding. To be clear, in taking a 'language-based approach to cognition', SFL models 'knowledge' as meaning. Halliday & Matthiessen (1999: ix-x):

It seems to us that our dialogue is relevant to current debates in cognitive science. In one sense, we are offering it as an alternative to mainstream currents in this area, since we are saying that cognition "is" (that is, can most profitably be modelled as) not thinking but meaning: the "mental" map is in fact a semiotic map, and "cognition" is just a way of talking about language. In modelling knowledge as meaning, we are treating it as a linguistic construct: hence, as something that is construed in the lexicogrammar. Instead of explaining language by reference to cognitive processes, we explain cognition by reference to linguistic processes.

Rebranding Exchange Structure As Tendering And Rendering

Doran, Martin & Zappavigna (2025: 22-3):

How then can we re-model tenor as a resource for enacting social relations? We can first look at how we put forward meanings and share them with others. In this book, we will suggest a basic distinction in how we enact social relations is between resources for tendering meanings to be engaged with, and reacting to or rendering meanings that have been put forward. For example…

 

Reviewer Comments:

[1] To be clear, in SFL Theory, the resource for enacting social relations as meaning is the interpersonal metafunction of language. Tenor, on the other hand, is 'who is taking part' in the situation in cultural terms, as realised by the interpersonal metafunction of language.

[2] To be clear, putting forward meanings is language, not tenor, and the tendering and rendering of meanings is the authors' (dumbed down*) rebranding of the exchange structure that realises Halliday's interpersonal semantic system of speech function. Halliday & Matthiessen (2014: 136-7):

[3] To be clear, Jodie's 'tender' is an initiating statement and command, and the mother's 'render: reject' is the discretionary response 'refusal'.

[4] To be clear, the mother's 'tender' is an initiating statement, and Jodie's 'render' is the expected response 'acknowledgement'. Jodie's 'tender' is another initiating statement.

[5] To be clear, the mother's 'tender' is an initiating statement, and Jodie's 'render: reject' is the discretionary response 'contradiction'. Its additional function of 'tender' is its function as the initiating statement of a further exchange.

* Note that speech function distinguishes between 'refusal' and 'contradiction', but the authors' "tenor" does not.

Misunderstanding Social Context As Non-Semiotic

Doran, Martin & Zappavigna (2025: 21):

As this overview shows, field, tenor, and mode as variables within the realisation hierarchy are not the be-all and end-all of our view of social context. To take seriously the integration of semiosis and society, we need a much richer model. 

Our ultimate aim in this book is to develop a model of tenor (realisation) which accounts for the contribution interpersonal meaning makes to negotiating association (instantiation) by way of membering communities in culture (individuation) – so that we can move toward comprehensively appreciating the interaction of the social and the semiotic.

Reviewer Comments:

[1] As the review of this overview demonstrates, this claim is made on the basis of the authors' misunderstandings of the architecture of language as proposed by SFL Theory. It is not a richer model that is needed, but a richer understanding of the model.

[2] This seriously misunderstands the notion of social context. In SFL Theory, context is semiotic: it is the culture modelled as a semiotic system. In Hjelmslevian terms, context is the content plane, and language the expression plane, of a connotative semiotic. The relation between context and language is symbolic identity; they two levels of abstraction of the one identity. Not only is context realised by language, but language construes — intellectually constructs — context.

[3] This further compounds the authors' misunderstanding of context as non-semiotic by misunderstanding the stratal relation between context and language as an interaction of modules — a misunderstanding that has persisted since Martin (1992: 390, 488):

Each of the presentations of linguistic text forming resources considered above adopted a modular perspective. As far as English Text is concerned this has two main dimensions: stratification, and within strata, metafunction. …

The problem addressed is a fundamental concern of modular models of semiosis — namely, once modules are distinguished, how do they interface? What is the nature of the conversation among components?

ChatGPT Comments:

Review Critique: Misunderstanding the Nature of Context and the Architecture of the System

This passage encapsulates several of the core misunderstandings that undermine the theoretical basis of the book. The claim that “field, tenor, and mode as variables within the realisation hierarchy are not the be-all and end-all of our view of social context” appears to position the authors’ model as an enrichment of the standard SFL framework. But as the review of the preceding excerpts makes clear, this claim is not based on a deeper extension of theory, but on fundamental misunderstandings of the theory’s architecture. What is needed is not a richer model, but a richer understanding of the model already in place.

First, this passage seriously misconstrues the nature of social context in SFL theory. In SFL, context is not external to semiosis; it is a semiotic system. Specifically, it is the culture modelled as a meaning potential — a higher-order stratum in the symbolic hierarchy, realised by language and construed through it. In Hjelmslevian terms (which underpin the theory’s architecture), context is the content plane, and language the expression plane, of a connotative semiotic. That is, language is the semiotic realisation of culture. To treat context as if it were non-semiotic — or as if it required an “integration” with semiosis — is to misread both levels of abstraction and the relation of symbolic identity that connects them.

This confusion is exacerbated by a deeper and longstanding theoretical error: the treatment of strata as modules which “interface” or “interact,” as if the symbolic architecture were composed of independent processing systems rather than levels of abstraction. This modular metaphor appears explicitly in Martin (1992: 390, 488), and is reproduced here in the idea that semiosis and society must be “integrated” through new interfacing mechanisms like “association” and “membering.” But in a properly stratified semiotic model, no such interface is required: context and language are distinct projections of the same meaning-making potential, realised through symbolic identity — not through interaction or modular communication.

The result is a theoretical incoherence: the authors propose a model of tenor that draws together realisation, instantiation, and individuation, but do so by treating them as separate “modules” that must somehow be coordinated, rather than as perspectival dimensions of a unified semiotic system. They offer a narrative of “integrating” the social and the semiotic, but in doing so, they detach the social from the semiotic, treating context as if it were outside the system, rather than a stratum within it.

In short, the passage illustrates a conceptual drift from SFL’s foundational principles. The so-called “integration” of semiosis and society presented here presupposes a false separation of what SFL already models as integrated through stratification, realisation, and symbolic identity. This drift not only undermines the theoretical coherence of the proposed tenor model — it also obscures the elegance and explanatory power of the existing systemic-functional framework. 

The Confusion That Invalidates The Hierarchy Of Individuation

Doran, Martin & Zappavigna (2025: 21-2):

Looking further afield this puts SFL in a stronger position to develop its third hierarchy, individuation (Martin, 2008a, 2008b, 2010, 2012; Zappavigna & Martin, 2018a, 2018b). A rough outline of the communion at stake is presented in Figure 1.11 as a scale of belonging.

This time round we are looking at the relation of a culture to the personae which member it – in terms of the way semiotic resources are allocated to personae and the way they use these resources to affiliate along a cline ranging through smaller coterie of shared values and on to large ones engendered by bonds associated with what we think of as class, generation, gender, and ethnicity. 

Here we can consider how choices in the realisation hierarchy and principles of instantiation are distributed across different communities, social fields of practice and channels of communication, as well as how they are used to create, maintain, collaborate within and struggle over these communities, social fields of practice and channels of communication.

Reviewer Comments:

To be clear, individuation is the differentiation of the meaning potential of a community ('reservoir') into the meaning potential of individuals ('repertoires'). As such, it is the elaboration of different types of meaning potential.

However, the hierarchy of individuation in Figure 1.11 confuses this elaboration of meaning potential with an extension ('affiliation') of meaners ('personae which member'); for 'association' as a type of extension, see Halliday & Matthiessen (1999: 146).

ChatGPT Comments:

Thank you, Chris — this is a precise and necessary critique. The passage from Doran, Martin & Zappavigna (2025) does indeed conflate the individuation of meaning potential with the affiliation of persons, resulting in a significant theoretical muddle. Your clarification — that individuation is an elaboration of potential, not an extension of personae — is exactly right. Below is a developed version of the critique that builds on yours and expands it in line with SFL theory:

---

Review Critique: Misrepresenting the Hierarchy of Individuation

The authors here mischaracterise individuation by confusing two distinct semiotic logics: (1) the elaboration of meaning potential, and (2) the extension of social belonging. Individuation, properly understood within the SFL tradition (Halliday & Matthiessen, 1999; Matthiessen, 2007), refers to the differentiation of the meaning potential of a community (a reservoir) into the more specific meaning potential of individuals (their repertoires). That is, it concerns the cline from collective to personal meaning potential — a relation of elaboration, not extension.

By contrast, the model offered here (and especially in Figure 1.11) reframes individuation as a matter of “personae which member [a culture]” and the “coteries of shared values” they affiliate with. This redefinition shifts the focus from semiotic potential to social identification, effectively substituting a theory of affiliation (in the sense of social alignment) for a theory of individualisation (in the sense of potential specification). The result is a conceptual slippage between:

• individuation as a semiotic process operating on meaning potential, and

• social extension or association as a process operating on personae.

This conflation overlooks a crucial distinction in SFL between:

• elaboration (where an element adds specificity within a semiotic system), and

• extension or association (where an element expands the boundaries of the system or links it to others).

As Halliday & Matthiessen (1999: 146) make clear, association — including affiliative belonging — is a kind of extension, not elaboration. When this logic is misapplied to individuation, the model shifts from describing the emergence of differentiated repertoires to describing the structuring of social groups, which is better accounted for under field, tenor, or affiliation and ideology, not individuation.

Moreover, by construing individuation as something that happens to personae who "member" a culture, rather than as a perspectival cline from collective to individual meaning potential, the model risks treating individuals as participants in social categories rather than as semiotic systems-in-development. This conflates the semiotic and the sociological — again blurring levels of abstraction and undermining the integrity of the stratified model.

In short: the authors substitute a theory of semiotic individuation with a theory of social bonding, which, while related in application, operates on a different semiotic axis. The result is a theoretically confused hierarchy that disorganises the role of individuation in the SFL architecture, and misleads the reader as to the nature of meaning potential itself.

The Problem With Field As 'A Resource For Construing Phenomena'

Doran, Martin & Zappavigna (2025: 21):

So instead of classifying fields as say horizontal or vertical, or as singulars or regions (as in Bernstein, 1996/2000) or as science, social science or humanities (e.g. Martin, 1992; Martin, 2007a, 2007b), or as ‘personal toilet’ or ‘games’ (Halliday, 1978), field can be reconstrued as a resource for construing phenomena. These resources can then be tuned in to relevant ideational systems in language (across strata) as far as realisation is concerned and the results coupled with interpersonal and/or textual meanings as required from the perspective of instantiation (i.e., mass).

Reviewer Comments:

[1] This confuses context and language. It is the ideational metafunction of language that is the resource for construing experience as meaning (phenomena). Field is the ideational dimension of the context of construing experience.

[2] To be clear, these resources already are the ideational systems of language.

[3] As previously demonstrated in the review of Rethinking Context: Realisation, Instantiation, And Individuation In Systemic Functional Linguistics (Doran et al 2024):

• 'mass' is the meaning of language misunderstood as the contextual parameter of field.
• 'technicality' is the ideational meaning of language misunderstood as the contextual parameter of field.
• 'iconisation' is the interpersonal meaning of language misunderstood as the contextual parameter of field.
• 'aggregation' is the textual meaning of language misunderstood as the contextual parameter of field.

Misunderstanding Language (Circumstance) As Field (Property)

Doran, Martin & Zappavigna (2025: 20-1):

Turning to properties, these can be qualitative (e.g., he served fast) or spatio-temporal (e.g., he served to his opponent’s backhand). There is also the option of arraying properties (e.g., he served faster in the first set) and if arrayed, then gauged (e.g., he served on average at 137 km/h). These choices are outlined in Figure 1.10.

 

Reviewer Comments:

[1] To be clear, this misconstrues language as context. The "qualitative property" fast is a Manner circumstance, and the "spatiotemporal property" to his opponent’s backhand is a Location circumstance.

[2] Again, this misconstrues language as context. The "property" faster is "arrayed" by the Location circumstance in the first set.

[3] Again, this misconstrues language as context. The "gauge" on average at 137 km/h is the Comment Adjunct on average plus the circumstantial Adjunct of Extent at 137 km/h.

Misunderstanding Language As Dynamic And Static Perspectives On Field

Doran, Martin & Zappavigna (2025: 19-20):

For both the dynamic and static perspective there are further options in play (Figure 1.9).

An activity can be presented as a single event (an ‘unmomented activity’, e.g., Alcaraz won the match) or it can be divided into moments of that activity (a ‘momented’ activity, e.g., Alcaraz won the first set, Rudd won the second, Alcaraz won the third and also won the fourth). If momented, the relationship can be one of implication where the unfolding activities are related by contingency where one necessarily follows another (e.g., Djokovic hit the line judge with the ball between points and so was automatically defaulted); alternatively they can be related by expectancy, where the unfolding is not born of necessity, but is probabilistic or expectant (as in the 2022 US Open final example above – Alcaraz won the first set, Rudd won the second, Alcaraz won the third and also won the fourth). 

For all these possibilities there is also the option of construing an activity as cyclical (e.g., players play the Australian Open, then the French Open, then Wimbledon, then the US Open, before again playing the Australian Open...); or the activity can be linear, and if linear then culminative (e.g., the serve hit the back wall) or unending (e.g., Tennis is played around the world). 

Turning to a static perspective, an item can be noted individually (e.g., ace) or taxonomised, via classification (e.g., his second serve was an ace) or via composition (e.g., my first racquet was made of wood and natural gut).

Reviewer Comments:

[1] To be clear, this misconstrues language as context. An "unmomented activity" is a clause realising a figure, and a "momented activity" is a paratactically extending clause complex realising a sequence. In Martin (1992), such activity sequences are located in field, but in Martin & Rose (2007), they are located in experiential discourse semantics.

[2] This again misconstrues language as context. This is a paratactically enhancing clause complex realising a sequence. The relation between the clauses is cause, not contingency.

[3] This again misconstrues language as context. This is a paratactically enhancing clause complex realising a sequence. The paratactic and hypotactic relations between the clauses are temporal.

[4] This again misconstrues language as context. The "culminative" and "unending" linear activities are both clauses realising figures.

[5] This again misconstrues language as context. The individual item is a lexical item, the classification taxonomy is a set of hyponymically related lexical items, and the composition taxonomy is a set of meronymically related lexical items.

Misconstruing Field As Ideational Language

Doran, Martin & Zappavigna (2025: 18-9):

This latter possibility of considering register variables as resources for meaning has recently been developed in (Doran & Martin, 2021) for field. In that model, field is mapped as a resource for construing phenomena – either statically as a set of relations between items, or dynamically as sets of activities and their moments, alongside their associated properties. These general systems are outlined in Figure 1.8 below.

From a dynamic perspective, phenomena are construed as goings on (e.g. player serving^player volleying^point ends); from a static perspective, phenomena are construed as things (e.g. a point, game, match, player, umpire; ball, racquet). And either goings on or items can be propertied (e.g. serve hard, quick game).

Reviewer Comments:

[1] To be clear, this simply misconstrues context (field) as the ideational function of language: the construal of experience as meaning.

[2] To be clear, this static perspective on field is the language that realises a field: taxonomic relations of lexical items.

[3] To be clear, this dynamic perspective on field is the language that realises a field: temporally sequenced figures.

[4] To be clear, an 'associated property' in field is the language that realises a field: quality realised as Manner, Epithet etc.

The 3 Fundamental Misunderstandings That Invalidate The Model In This Book

Doran, Martin & Zappavigna (2025: 18):

Reconsidering context in this way in turn opens up the possibility 

• of reconceiving (from the perspective of instantiation) the types of field classifications pursued by previous models as syndromes of technicality, iconisation and aggregation (mass); 
• of reconceiving types of mode as syndromes of implicitness, negotiability, and iconicity (presence); and 
• of reconceiving types of tenor as syndromes of reciprocity and proliferation (association). 

And this in turn opens up the possibility of abandoning the classificatory approach to modelling field, tenor, and mode along the realisation hierarchy – and replacing it with a social semiotic perspective on register variables as resources for construing phenomena (field), enacting social relations (tenor) and composing information flow (mode). 

Developing SFL along these lines in turn opens up the possibility of re-confirming the resonance between field, tenor, and mode and metafunctions that is put at risk by research dedicated to classifying fields, tenor, and modes in relatively common-sense terms.

Reviewer Comments:

[1] To be clear, the authors' first proposal is to miscontrue context as language; specifically, to

• misconstrue contextual field as the ideational meaning of language (mass) — sub-classified as ideational meaning (technicality), interpersonal meaning (iconisation) and textual meaning (aggregation);
• misconstrue contextual mode as the textual meaning of language (presence) — sub-classified as ideational meaning (iconicity), interpersonal meaning (negotiability) and textual meaning (implicitness); and
• misconstrue contextual tenor as the interpersonal meaning of language (association).

[2] To be clear, the authors' second proposal is to misconstrue language as context; specifically, to

• misconstrue  construing experience as ideational meaning as field;
• misconstrue enacting social relations as interpersonal meaning as tenor; and
• misconstrue composing information flow as textual meaning as mode.

[3] This is misleading because it is not true. On the one hand, context-metafunction resonance is not put at risk by Halliday's characterisation of field, tenor and mode, and on the other, if it were put at risk, the authors' reconceptions could not assist in this regard, since they confuse context with language.

As previously explained, the authors misunderstand context-metafunction resonance to mean an exclusive relation between context and language on the basis of metafunction. However, what context-metafunction resonance actually means is that

• differences in field are realised by differences in ideational meaning,
• differences in tenor are realised by differences in interpersonal meaning, and
• differences in mode are realised by differences in textual meaning.

Why Mass, Presence, And Association Cannot Be Principles Of Instantiation

Doran, Martin & Zappavigna (2025: 18):

Instantiation is typically considered in terms of the coupling of choices as conditioned by varying probabilities in different texts, text types and diatypes. 

But recognising the concepts of mass, presence, and association (i.e., status/contact) as metafunctionally diversified syndromes of choice offers a perspective on instantiation that can help explain why certain choices co-occur in certain situations. That is, mass, presence and association can be considered principles of instantiation – principles underpinning the co-selection and arrangement of features across strata and metafunctions. This can help us move away from relatively ad hoc explanations as to why particular choices are taken up in particular texts or situations and move us into considering different texts and the various domains they enter into in terms of a multidimensional set of principles. 

For example, scientific writing tends to involve significant interlocking networks of activity, taxonomy and property, but relatively little evaluative language in comparison to other disciplines (e.g. Halliday & Martin, 1993). We could explain this in terms of science’s aim for very strong ideational mass (technicality) but relatively weak interpersonal mass (iconisation). We could also describe the fact that it regularly aims to link theory to data as illustrating a wide range of ideational presence (iconicity).

Reviewer Comments:

[1] Here the authors misrepresent their own misunderstanding of instantiation as the "typical" view. As a process, instantiation is the selection of features and the activation of their realisation statements in logogenesis. At the system pole of the cline of instantiation, every feature of system has a probability of instantiation relative to other features in the system, and at the instance pole, texts vary by the relative frequency of feature selection.

The midway point of variation on the cline can be viewed from the system pole as register ("diatype"), or from the instance pole as text type, with registers varying in terms of the probability of feature selection, and text types varying in terms of the frequency of feature selection.

Importantly, at ontogenetic and phylogenetic timescales, the probabilities of feature selection in the system are altered by the frequencies of feature selection in the instances.

[2] To be clear, even if mass, presence and association provided a theoretically valid model of context, they could not "be considered as principles underpinning the co-selection and arrangement of features across strata and metafunctions" simply because instantiation is not an inter-stratal relation. Instantiation is the relation between system and instance at each stratum. There is no instantiation relation between context and language. Context and language are related by realisation, elaborating identity, so there is no causal (enhancing) relation between them.

[3] This is misleading, because this is simply the imposition of terms that do not provide explanation. That is,

• it does not explain why science writing has less evaluation, it just labels it as strongly technical;
• it does not explain why science writing has less evaluation, it just labels it as weakly iconised.

[4] As demonstrated here, the authors' notion of iconicity misunderstands a congruent relation between ideational lexicogrammar and ideational semantics as an iconic relation between the ideational content of language (text) and the ideational dimension of context ("what it is talking about").

Seriously Misunderstanding Instantiation

 Doran, Martin & Zappavigna (2025: 17-8):

Realisation is a hierarchy of abstraction, with higher strata realised by patterns of meaning at lower ones. Instantiation on the other hand is a cline of generality, with higher rungs constituting a larger meaning potential than lower ones (a system to text relation). The realisation hierarchy we assume here was outlined in Figure 1.3 above (with genre as a more abstract pattern of register patterns, register as a more abstract pattern of discourse semantic patterns and so on). This can be contrasted with the version of the instantiation cline presented as Figure 1.7 (c.f. Martin, 2010, 2014). There, moving down from system, we have a cline of sub-potentialisation (system, diatype, text type, text); moving up we have a concomitant cline of generalisation (text, text type, diatype, system).

 Blogger Comments:

[1] This seriously misunderstands instantiation. To be clear, instantiation is not a cline of generality. Generality is the scale of delicacy. Halliday & Matthiessen (1999: 14, 144-5):

Note that it is important to keep delicacy and instantiation distinct. In early work on semantic networks, they were sometimes neutralised (cf. Woods', 1975, review). The difference is essentially that between being a type of x (delicacy) and being a token of x (instantiation) …

In other words, the elaboration sets up a relationship either of generality (delicacy), of abstraction (realisation), or of token to type (instantiation).

[2] To be clear, register ("diatype") and text type are not two different points of variation on the cline of instantiation, but the same point viewed from opposite poles of the cline. It is register when viewed from the system pole, and text type when viewed from the instance pole. Halliday (2005 [1995]: 254):

[3] To be clear, the cline of instantiation in Figure 1.7 only models language, not context. Martin (1992) replaced the system and instance poles of the cline of instantiation at the level of context with the strata of genre and register, respectively. In Martin's model, there are no situation types.

Seriously Misunderstanding Stratification

Doran, Martin & Zappavigna (2025: 17, 10):

Realisation is a hierarchy of abstraction, with higher strata realised by patterns of meaning at lower ones. … The realisation hierarchy we assume here was outlined in Figure 1.3 above (with genre as a more abstract pattern of register patterns, register as a more abstract pattern of discourse semantic patterns and so on).

 Blogger Comments:

This seriously misunderstands stratification. Less importantly, realisation is not a hierarchy, but the relation between levels of symbolic abstraction, as between axes or between strata. The hierarchy in this case is the hierarchy of strata: stratification.

Most importantly, higher strata are not "realised by patterns of meaning at lower ones". On the one hand, the function of the stratification hierarchy is to relate meaning, semantics, to other levels of symbolic abstraction: lexicogrammar and phonology below, and the context of language above. The authors' misunderstanding reflects Martin's mantra 'all strata make meaning' which confuses stratification (realising meaning) with semogenesis (making meaning).

On the other hand, the "patterns" of each stratum are the systems of each stratum. The term "patterns" suggests a confusion with instantiation: the patterns of instantiation that distinguish the variants on the cline of instantiation from each other.

A Misunderstanding Underlying 'Association'

Doran, Martin & Zappavigna (2025: 17):

We won't attempt a more detailed discussion of metafunctional diversification and Poynton's principles here. Suffice it to say that it is very difficult to restrict these patterns of usage to interpersonal meanings alone. So alongside mass and presence, (Doran, Martin, & Herrington, 2024) suggests the cover term association to manage the metafunctional distribution of all the status and contact (reciprocity and proliferation/contraction) patterns in play.

Reviewer Comments:

[1] This continues the authors' misunderstanding of context-metafunction resonance as requiring that variation in a contextual parameter, in this case: tenor, not be realised by variation in the language of unaligned metafunctions, in this case: ideational and textual meaning. As previously explained, it is variation in the interpersonal meaning of language that identifies variation in tenor (and vice versa).

[2] As previously demonstrated in the review of Rethinking Context: Realisation, Instantiation, And Individuation In Systemic Functional Linguistics (Doran et al 2024), the authors' 'association' is the meaning of language misunderstood as the contextual parameter of tenor.

Misunderstanding Context-Metafunction Resonance

Doran, Martin & Zappavigna (2025: 16):

A key motivation for this reconsideration was that many of the features typically considered as part of mode (e.g., context-dependency) and field (e.g., the specialisation and complexity of meaning) are realised across metafunctions. This clashes with the principle that there should be a link between metafunctions and register variables – field tending to be realised by ideational meaning and mode tending to be realised by textual meaning. The conceptualisation of mass and presence as transmetafunctional concepts allows for field and mode to be reconfigured in a way that maintains this register-metafunction hook-up (for what this looks like for field, see (Doran & Martin, 2021)).

Reviewer Comments:

[1] As previously explained, context-metafunction resonance ("hook-up") means

• differences in field are realised by differences in ideational meaning,
• differences in tenor are realised by differences in interpersonal meaning, and
• differences in mode are realised by differences in textual meaning.

Here, as before, the authors misunderstand context-metafunction resonance to mean an exclusive relation between context and language on the basis of metafunction.

[2] As previously explained, the notion of 'transmetafunctional concepts' derives from misunderstanding the dimension of metafunction as a scale of delicacy.

Some Misunderstandings Underlying 'Mass'

Doran, Martin & Zappavigna (2025: 16):

• For field, from the perspective of ideational meaning, the key variable is technicality – i.e., to what extent is meaning distilled as technical terms arranged as uncommon sense classification, composition, and activity (e.g., canine/feline vs dog/cat)? 
• From the perspective of interpersonal meaning the key variable is iconisation – i.e., to what extent is a phenomenon charged with values shared by members of a community (e.g., for the SFL community contrasting reactions to figures such as Halliday or Chomsky)? 
• From the perspective of textual meaning the key variable is aggregation – i.e., to what extent does a text consolidate meaning, prospectively or retrospectively, as it unfolds (e.g., the title of Table 1.2 below vs its contents)? 

Martin suggests mass as a cover term for these syndromes of usage. Table 1.2 summarises this metafunctional factoring of mass as technicality, iconisation and aggregation.

Reviewer Comments:

As previously demonstrated in the review of Rethinking Context: Realisation, Instantiation, And Individuation In Systemic Functional Linguistics (Doran et al 2024):

• 'mass' is the meaning of language misunderstood as the contextual parameter of field.
• 'technicality' is the ideational meaning of language misunderstood as the contextual parameter of field.
• 'iconisation' is the interpersonal meaning of language misunderstood as the contextual parameter of field.
• 'aggregation' is the textual meaning of language misunderstood as the contextual parameter of field.

The Misunderstandings Underlying 'Presence'

Doran, Martin & Zappavigna (2025: 15-6):

In recent years, Martin (Martin, 2017/2020; Martin & Matruglio, 2013/2020; Martin & Unsworth, 2024) has revisited the register variables classifying modes and fields from the perspective of metafunctions (i.e., ideational, interpersonal and textual meaning). Influenced by Maton's (2014) concepts of semantic gravity and semantic density he suggests that types of mode and field can in fact be associated with syndromes of choices from across all three metafunctions. 

• For mode, from the perspective of textual meaning, the key variable is implicitness – e.g., to what extent does a text depend on reference out to the physical situation?  

• From the perspective of interpersonal meaning the key variable is negotiability – e.g., to what extent does a text engage people in the 'to and fro' of dialogue, including the amount of emotion expressed?  

• From the perspective of ideational meaning the key variable is iconicity – e.g. to what extent does a text unfold by mirroring what it is talking about? 

Martin and Matruglio (2013/2020) suggest presence as a cover term for these syndromes of usage. Table 1.1 summarises this metafunctional factoring of presence in language as implicitness, negotiability, and iconicity.

Reviewer Comments:

[1] This demonstrates very serious misunderstandings of both stratification and metafunction. In terms of stratification, the relation between context and language is realisation, whereas subclassification misunderstands the relation as one of delicacy (hyponymy). Halliday & Matthiessen (1999: 145):

In terms of metafunction, the contextual parameters of field, tenor and mode are themselves categorisations of the culture as semiotic system according to metafunction. To subclassify metafunctions in terms of metafunctions is to misunderstand the dimension of metafunction as a scale of delicacy.

[2] To be clear, in SFL Theory, mode and field are realised by meanings of all three metafunctions. The different syndromes of choices of these meanings constitute different registers, which realise different subcultures/situation types, as defined by contextual configurations of field, tenor and mode variables. Here the authors have confused the dimensions of stratification and instantiation. 

[3] As previously demonstrated in the review of Rethinking Context: Realisation, Instantiation, And Individuation In Systemic Functional Linguistics (Doran et al 2024):

• 'presence' is the meaning of language misunderstood as the contextual parameter of mode.
• 'iconicity' is the ideational meaning (metaphor) of language misunderstood as the contextual parameter of mode.
• 'negotiability' is the interpersonal meaning (speech function) of language misunderstood as the contextual parameter of mode.
• 'implicitness' is the textual meaning (exophoric demonstrative reference) of language misunderstood as the contextual parameter of mode.

Misunderstanding Context As The Language That Realises It

Doran, Martin & Zappavigna (2025: 13-4):

At this point it is important to stop and ask where categories used to classify tenor relations such as this come from. It is not clear, for example, whether the categories arise from patterns in language. Neither is it clear how these categories can be clearly linked with choices in language – this is especially the case if we wish to keep some link between interpersonal systems and tenor. … 

If we want a model of social semiosis that can show how language shapes and is shaped by context (and vice versa), we need something that can show the relation between them. Accordingly in this book we will take a different tack, and think about how field, tenor and mode can be characterised as resources for construing phenomena, enacting social relations, and composing information flow. In the next section we review the work which has built up to this complementary perspective.

Reviewer Comments:

[1] To be clear, in SFL Theory, the categories of tenor (Value) are realised by patterns in language (Token). The authors' inability to understand the relation between two levels of symbolic abstraction is the source of all the theoretical inconsistencies in this work.

[2] To be clear, this model already exists. It is called Systemic Functional Linguistic Theory, and the relation between context and language is one of symbolic identity. Together context and language constitute a connotative semiotic, with context as its content plane (Value) and language as its expression plane (Token). Context is realised by language and language realises context, and in doing so, language construes (intellectually constructs) context.

[3] To be clear, the 'different tack' taken by the authors in this book is to reinterpret context as the language that realises it. Again, the authors' inability to understand the relation between two levels of symbolic abstraction is the source of all the theoretical inconsistencies in this work.

Problems With The Notion Of Context Skewing Language System Probabilities

Doran, Martin & Zappavigna (2025: 11-12):

The resonance between discourse semantic systems and register variables is annotated in Figure 1.5 – with field skewing probabilities in IDEATION and CONNEXION systems, mode skewing probabilities in PERIODICITY and IDENTIFICATION systems and tenor skewing probabilities in NEGOTIATION and APPRAISAL systems.

Reviewer Comments:

[1] As previously explained, context-metafunction resonance means

• differences in field are realised by differences in ideational meaning,
• differences in tenor are realised by differences in interpersonal meaning, and
• differences in mode are realised by differences in textual meaning.

As previously demonstrated, the authors misunderstand context-metafunction resonance as an exclusive relation between context and language on the basis of metafunction. 

[2] As previously explained, this misunderstands the relation between context and registers of language in SFL Theory. Halliday (2005 [1991]: 60):

Register variation can be defined as the skewing of (some of) these overall probabilities, in the environment of some specific configuration of field, tenor and mode. It is variation in the tendency to select certain meanings rather than others, realising variation in the situation type.

That is, different registers are defined by having different probabilities of selection of semantic and lexicogrammatical features, with each register realising a different configuration of field, tenor and mode variables, and each of these defining a different situation type. Importantly, the skewing of probabilities is not caused by the contextual variables of field, tenor and mode, if only because the relation between context and language is not causal (enhancement), but one of intensive identity (elaboration).

Misunderstanding Tenor And The Architecture Of Language

Doran, Martin & Zappavigna (2025: 11):

Through the history of SFL, a range of scholars have tried to make tenor do a very wide range of things. But with a more elaborated model of language and context that includes discourse semantics, genre and, as we will discuss below, instantiation and individuation, the division of semiotic labour can be more comfortably distributed across the model.

Reviewer Comments:

[1] This is the logical fallacy known as ipse dixit: a bare assertion unsupported by evidence. Here it also serves as an instance of the straw man fallacy, since it sets up an imaginary position to be argued against in the work of the authors; cf. tilting at windmills. 

To be clear, tenor merely concerns who is taking part in a speech situation. It is simply the theoretical projection of the interpersonal metafunction onto context. It will be seen in this review that it is the authors themselves who try "to make tenor do a very wide range of things", by extending it to include interpersonal semantics and to serve as a 'principle of instantiation' for language.

[2] This misunderstands the architecture of language proposed by SFL Theory. The "semiotic labour" is already distributed along all the dimensions proposed. For example, Halliday & Matthiessen (2014: 32):

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.

Problems With The Discourse Semantics Framework

Doran, Martin & Zappavigna (2025: 11):

The model of discourse semantics we assume here is also organised by metafunction (Hao, 2020; Martin, 1992; Martin & Rose, 2003/2007; Martin & White, 2005). As outlined in Figure 1.5, its systems comprise: 

• the ideational systems of IDEATION, which map how we construe our experience in terms of the occurrences, states, entities and qualities of language, and CONNEXION, which articulates how we connect these ideational meanings and stretches of text together into larger sequences of experience or rhetoric; 
• the textual systems of PERIODICITY, which are concerned with how we foreground and background information as waves of prominence, and IDENTIFICATION, which map how we introduce and track people, places and things; and most significantly for this book, 
• the interpersonal systems of NEGOTIATION, which present the resources we have for dialogue, and APPRAISAL, which map the resources we have for evaluating, amplifying and arranging interpersonal meanings.

Reviewer Comments:

[1] To be clear, the experiential discourse semantic system of IDEATION in Martin (1992) is Martin's rebranding of his misunderstandings of (textual) LEXICAL COHESION in Halliday & Hasan (1976). However, it has more recently become a rebranding of the ideational semantics — both experiential and logical — of Halliday & Matthiessen (1999) by Martin's former student Hao. See, for example:

Misrepresenting Halliday & Matthiessen's Semantics As Martin And Hao's Discourse Semantics 

[2] To be clear, the logical discourse semantic system of CONJUNCTION in Martin (1992), renamed CONNEXION by Martin's former student, Hao, is Martin's rebranding of his misunderstandings of (textual) grammatical cohesive CONJUNCTION in Halliday & Hasan (1976), confused with (logical) grammatical CLAUSE COMPLEXING in Halliday (1985).

[3] To be clear, the textual discourse semantic system of PERIODICITY in Martin & Rose (2007) is Martin's rebranding of writing pedagogy. No system networks have ever been devised, and the structures each consist of only one functional element (e.g. hyper-Theme). Moreover, in Martin (1992: 393), these rebrandings were modelled as interstratal interaction patterns, rather than discourse semantic systems.

[4] To be clear, the textual discourse semantic system of IDENTIFICATION in Martin (1992) is Martin's rebranding of his misunderstandings of grammatical REFERENCE in Halliday & Hasan (1976). 

[5] To be clear, the interpersonal discourse semantic system of NEGOTIATION in Martin (1992) is Martin's rebranding of his misunderstandings of SPEECH FUNCTION in Halliday (1985). 

[6] To be clear, for Halliday, APPRAISAL is a system between grammar and lexis, in which attitudinal assessments are realised by lexical items.

∞

For detailed evidence of the myriad misunderstandings of SFL theory in the 'discourse semantic' framework, see here (Martin 1992) and here (Martin & Rose 2007).

Problems With The Key Motivation For The Model Of Tenor In This Book

Doran, Martin & Zappavigna (2025: 10):

The significance of metafunctionality for this book and for the model of context in SFL in general, has to do with their relation with field, tenor and mode. As explored in Halliday (1978), the metafunctions of language (that we can describe as the ‘intrinsic’ functionality of language) are said to resonate with the field, tenor and mode variables of context (what we can describe as the ‘extrinsic’ functionality of context) – with ideational meaning by and large responsible for construing field, interpersonal meaning by and large responsible for enacting tenor and textual meaning by and large responsible for composing mode. 

This is a powerful claim, which suggests that language is not randomly correlated with context but in fact has evolved in a very definite relation with context, such that its overarching internal organisation connects closely with the organisation of context. It puts forward a model that suggests the organisation of language and our social system are intimately connected, with each dependent on the other – rather than being just superficially coordinated. 

Sustaining this resonance between language’s intrinsic functionality conceptualised through metafunction and extrinsic functionality conceptualised through register (field, tenor, and mode) is a key motivation for the model of tenor offered in this book.

Reviewer Comments:

[1] This seriously misunderstands what Hasan calls 'context-metafunction resonance'. Halliday (1978: 143):

Each of the components of the situation tends to determine the selection of options in a corresponding component of the semantics. In the typical instance, the field determines the selection of experiential meanings, the tenor determines the selection of interpersonal meanings, and the mode determines the selection of textual meanings.

That is, it is not that

• ideational meaning is by and large responsible for construing field, 
• interpersonal meaning is by and large responsible for enacting tenor and 
• textual meaning is by and large responsible for composing mode

but that

• different fields are realised by different ideational meanings,
• different tenors are realised by different interpersonal meanings, and
• different modes are realised by different textual meanings.

To be clear, all metafunctions — necessarily — realise each of the three parameters of context.

[2] This seriously misunderstands the relation between language and context. The relation between any two levels of symbolic abstraction is symbolic identity. The process 'realise' expresses an intensive (elaborating) identifying relation between language (Token) and context (Value), such that each can be used to identify the other. The identity can decode language (Identified) by reference to context (Identifier), or it can encode context (Identified) by reference to language (Identifier).

[3] As can be seen from the above, the key motivation for the model of tenor offered in this book derives from two critical misunderstandings of the relation between language and context — misunderstandings that invalidate the model.

ChatGPT Comments:

This is an excellent and precise critique, Chris — and I think your three points already strike at the heart of the problem with conceptual clarity and theoretical rigour. I can suggest a few possible expansions and refinements to deepen the review’s critical edge, while staying fully within the tone and aims you've already established:

---

Misunderstanding Context-Metafunction Resonance

1. Reversal of the Realisation Relation

The authors misrepresent the principle of context–metafunction resonance by implying that each metafunction is responsible for construing a corresponding context variable. This misconstrues the relation between strata: language does not organise context, and metafunctions are not assigned to contextual variables. Rather, contextual variation (in field, tenor, and mode) motivates variation in the semantic systems that realise them.

The correct formulation — as in Halliday (1978: 143) and further clarified by Hasan (e.g. 1992) — is that:

• field is realised through variation in ideational meaning,

• tenor is realised through variation in interpersonal meaning,

• mode is realised through variation in textual meaning.

This preserves the theoretical directionality of realisation: context → semantics → lexicogrammar, with each stratum functioning as the Value to be realised, and the stratum below as its Token (as your second comment clearly notes). The wording in the excerpt reverses this dependency and treats metafunction as if it encodes context directly, rather than realising it through systems of semantic potential.

---

2. Mischaracterising Intrinsic and Extrinsic Functionality

The terms intrinsic (language) and extrinsic (context) functionality are introduced without proper grounding in the SFL framework, and this weakens the clarity of the resonance relation. While it is true that metafunction represents the intrinsic functionality of language (its evolved semiotic orientations), it is incorrect to infer that this maps directly onto context variables in a one-to-one functional dependency.

Context and language are not interlocked systems of mutual determination. Context does not have metafunctions. Rather, the metafunctions provide a lens through which context is construed by language, via semantic systems. The framing offered in the excerpt slides toward a kind of functional parallelism that blurs the line between language and context — both semiotic systems, but distinct in the stratified model — threatening to collapse the symbolic hierarchy that organises meaning-making in SFL.

---

3. Misplaced Theoretical Motivation for the Tenor Model

The claim that “sustaining this resonance” is the key motivation for the new tenor model is particularly problematic given that the authors have misunderstood what the resonance is. If the foundation is theoretically flawed — reversing the realisation relation, and mislocating responsibility for functional alignment — then the model of tenor they propose is motivated by a category error.

This again casts doubt on the validity of the entire reconception, as noted in your third reviewer point. A sound model of tenor must begin from a consistent theory of stratification and realisation — in which:

• context is realised by language,

• tenor is a variable of context,

• and interpersonal meaning is the stratal means through which tenor is realised.