League Table Of Visitors

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.

Misrepresenting The Metafunctions

 Doran, Martin & Zappavigna (2025: 10, 11):

The other main dimension of analysis we need to introduce here is metafunction. As developed by Halliday (e.g. 1973, 1978) this dimension refers to the different kinds of meaning that language can make — ideational resources for construing our world, interpersonal resources for enacting social relations and textual resources for composing information flow (Figure 1.4). 

More technically, metafunction refers to the tendency for linguistic systems to bundle together, with some sets of systems highly interdependent on each other, and others highly independent of each other. For grammar, this is reflected in the fact that sets of options within the ideational system of TRANSITIVITY are relatively interdependent on each other, but they are relatively independent of those within the interpersonal system of MOOD or the textual system of THEME (Martin & Matruglio, 2013/2020; Matthiessen, 1995).

Reviewer Comments:

This is misleading. To be clear, it is the principles underlying the metafunctions that "bundle" linguistic systems, not the reverse. The metafunctions give rise to the systems, not the reverse. The systems are devised according to the metafunctions, not the reverse.

ChatGPT Comments:

You're absolutely right to challenge the reversal of theoretical dependency in this excerpt. The authors misrepresent the metafunctions as emergent properties of the systems themselves, rather than as organising principles that motivate the construction of those systems. Here’s an extended critique you could add to your review, in line with your original comment but deepening the theoretical clarification:

---

Misrepresenting Metafunction as Emergent from Systemic Groupings

The authors’ characterisation of metafunction as a “tendency for linguistic systems to bundle together” misrepresents a foundational concept in Systemic Functional Linguistics. This account mistakenly presents metafunction as an emergent property of patterns within the system network — as if metafunction were something inferred from systemic interdependence, rather than the organising principle according to which those systems were constructed in the first place.

In the SFL model, metafunctions are axiomatic: they represent the fundamental types of meaning that language is evolved to enact — ideational, interpersonal, and textual. These are not discovered by observing bundles of grammatical systems; they are the theoretical starting point from which those systems are modelled and interpreted. The systems of transitivity, mood, and theme, for example, are organised according to their metafunctional roles. It is not the case that we discover the metafunctions by observing which systems “bundle”; rather, we posit metafunctional orientations and then describe systems in terms of the kinds of meaning they realise.

To say, then, that metafunction refers to "the tendency for linguistic systems to bundle together" reverses this theoretical dependency. It obscures the fact that SFL system networks are metafunctionally motivated: system organisation is guided by the distinct functions that language must serve in social life — to represent experience, enact social relations, and manage textual flow. This confusion risks eroding the explanatory power of metafunctional organisation and could easily mislead readers into thinking metafunctions are merely taxonomic or descriptive generalisations.

A more accurate formulation would be:

In SFL theory, metafunction refers to the three fundamental orientations of meaning that language is evolved to make — ideational, interpersonal, and textual — which in turn provide the organising principles for constructing grammatical systems. Each metafunction is associated with its own network of systems (e.g. transitivity, mood, theme), and the principle of metafunctional complementarity ensures that clauses simultaneously realise meanings from all three metafunctions in a stratified and integrated structure.

Until this theoretical directionality is clarified — that metafunctions give rise to systems, not the reverse — the account presented in this section risks misconstruing one of the most essential dimensions of the SFL framework.

The Models Of Discourse Semantics And Paralanguage In This Book

Doran, Martin & Zappavigna (2025: 9, 10):

For language, this book assumes a model of language comprising the strata of phonology (or graphology for written language or the embodied signing of sign languages), lexicogrammar and discourse semantics (Figure 1.3).

We call the most abstract stratum of language discourse semantics, not semantics, to emphasise its orientation to larger text patterns (Martin, 1992; Martin & Rose, 2003/2007); this distinguishes it from the clause semantics of say Halliday and Matthiessen (1999) or Hasan (e.g. Hasan, Williams, Cloran, & Lukin, 2005). For grammatical analysis of English examples we rely on Halliday (1985 and subsequent editions); for phonological analysis we draw on Halliday and Greaves (2008); and for paralanguage (i.e., body language, gesture and the like) we reference Ngo et al. (2022).

Reviewer Comments:

[1] To be clear, Martin's discourse semantics arose as his rebranding of lexicogrammatical cohesion (Halliday & Hasan 1976), the non-structural system of the textual metafunction. For the myriad misunderstandings of SFL theory in this model, see here (Martin 1992) and here (Martin & Rose 2007).

[2] To be clear, Martin's ideational discourse semantics is now a rebranding of the semantics 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

[3] For evidence of the theoretical misunderstandings and plagiarism in this work, see:

Modelling Paralanguage Using Systemic Functional Semiotics

Misrepresenting Halliday On Register And Its Relation To Context

Doran, Martin & Zappavigna (2025: 9, 28n):

In the model used in this book, register is the cover term for the stratum comprising field, tenor and mode (Figure 1.2).

This contrasts with Halliday's use of the term register to refer to the skewing of probabilities in semantic systems inside language by field, tenor and mode (e.g. Halliday, 1991b, p. 48; 2006). Both concepts – field, tenor, and mode (what in this book we call register), and the language patterns that arise due to specific choices in field, tenor, and mode (what Halliday calls register) – occur within this model. The difference with Halliday in this regard is purely terminological.¹

¹ As this terminological distinction has often led to confusion, it would perhaps be useful to use Gregory’s (1967) suggestion of ‘diatype’ for the skewing of probabilities in the systems of language by choices in field, tenor and mode (i.e. Halliday’s register), and leave register as the cover term for field, tenor and mode. It is of course worth emphasising that there is a substantial difference in the model of social context presumed here and that of Halliday’s in that this model divides context into register (field/tenor/mode) and genre as distinct strata, whereas Halliday’s only has field/tenor/mode.

Reviewer Comments:

[1] This is misleading, since it misrepresents Halliday. Cf. Halliday (2005 [1991]: 60):

On the contrary; it is the probabilistic model of lexicogrammar that enables us to explain register variation. 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, the skewing of probabilities defines register variation, not register, and it is not caused by field, tenor and mode of a situation type, because the realisation of one stratum in another is not a causal relation. Less importantly, in this instance, Halliday was describing lexicogrammar, not semantics.

[2] This is very misleading, because the difference is far more than merely terminological. For example, a consequence of renaming context after a variety of language is that context is no longer culture instantiated as situations of situation types. In fact, in Martin's model, which in terms of strata, distinguishes context from language, an instance of context is deemed to be a text, an instance of language. This contradiction alone is sufficient to invalidate Martin's model.

[3] To be clear, this qualification in an endnote, nineteen pages later, flatly contradicts the authors' claim in the text that the difference between the models is 'purely terminological'.

Some Of The Problems With Genre And Register As Strata Of Social Context

Doran, Martin & Zappavigna (2025: 8):

In addition we will treat social context as involving two strata: genre and register. For practical purposes genre can be interpreted as modelling context as a system of staged, goal-oriented social processes realised through register – the latter comprising field, tenor and mode (Martin, 1992; Martin & Rose, 2008). More technically, genre is a supervenient system realised through choices in register (after Martin, 1984, 1992, 1999, 2014).

Reviewer Comments:

[1] To be clear, from the perspective of SFL Theory, Martin's contextual stratum of genre confuses mode (textual context), semantic structure (non-metafunctional language) and text type (register of language viewed from the instance pole of the cline of instantiation).

The confusion of genre with mode, the role played by language in terms of the culture, can be seen in genre systems, such as the following from Martin & Rose (2008: 7), where each feature is a role played by language:

The confusion of genre with semantic structure can be seen in genre structure, where each stage is an element of text structure. For example, Martin & Rose (2008: 52):

The confusion of genre with text type is explicit in Martin's characterisation of 'genre'. Martin & Rose (2007: 7):

We use the term genre in this book to refer to different types of texts that enact various types of social contexts.

In short, Martin's stratum of genre, in SFL terms, is concerned with semantic structures that vary for text types (registers) that realise different modes.

[2] To be clear, in rebranding context as register, Martin confuses functional varieties of language (registers) with the contextual parameters that they realise.

[3] For evidence of the above, see the reasoned arguments in the meticulous reviews of Martin (1992) and Martin & Rose (2007).

[4] To be clear, this is a misunderstanding and misapplication of 'supervenient'. See, for example here.

[5] To be clear, this proposes that the choice between recount and narrative, for example, is realised by choices in field (what's going on in terms of the culture), tenor (who's participating, in terms of the culture) and mode (the role of language, in terms of the culture). That is, the choice between recount and narrative is realised by choices such as biology vs chemistry (field), boss vs employee (tenor), and written vs spoken (mode).

The Misunderstanding Of Stratification On Which This Work Depends

 Doran, Martin & Zappavigna (2025: 8):

In this book we will treat social context as a semiotic system realised through patterns of language (Figure 1.1).

This model conceives of context and language as being intricately related and co-developed, with each continually impacting the other (what Martin (2011), adopting a term suggested by Chris Cléirigh, calls a ‘supervenient’ perspective on social context). 

Such an approach contrasts with perspectives which either treat social context as an independent phenomenon alongside language (that is, at best, correlated with language choices but otherwise having no co-genetic relation) or alternatively as a circumvenient phenomenon in which language is in some sense embedded in context but where there is only a one-way determination – so that context determines language choice, but language has no or minimal effect on context. 

Our project, in other words, involves working towards a model in which social context is realised through recurrent patterns of meaning – where realisation involves a two-way process of mutual actualisation between language and context. Accordingly anything we say about social context is an abstraction from recurrent patterns of semantic choice (Martin, 2014) – a relationship Lemke (e.g. 1995) refers to as metaredundancy.

Reviewer Comments:

[1] To be clear, in SFL Theory, context is the culture as a semiotic system that is realised in language (inter alia). The ideational dimension of context, field, is what is going on, in terms of the culture; the interpersonal dimension of context, tenor, is who is taking part, in terms of the culture; and the textual dimension of context, mode, is the role played by language, in terms of the culture.

[2] To be clear, in SFL Theory, the stratal relation between context and language is one of intensive symbolic identity (realisation). That is, context and language form the one identity, with context as the higher level of symbolic abstraction, and language as the lower level. On the other hand, the "co-development" of context and language, is distinct from their stratal relation, and here refers to the process of logogenesis: the development of the text. That is, the authors here have confused stratification with semogenesis.

[3] To be clear, in SFL Theory, the "co-development" of context and language in logogenesis is the development of the one identity, viewed at two different levels of symbolic abstraction. Two different levels of symbolic abstraction cannot "impact" each other. For example, a pipe and a representation of a pipe cannot "impact" each other.

[4] This is misleading. On the one hand, it misrepresents Cléirigh's use of the term 'supervenient'. Cléirigh used the term to refer to the emergence of higher levels of organisation in complex systems, as in the emergence of chemical systems from physical systems, and of biological systems from chemical systems. That is, it covers similar ground to Halliday's (2002 [1996]: 388) evolutionary typology of complex systems. On the other hand, contrary to the implication, Cléirigh did not apply the term 'supervenient' to the relation between context and language. Instead, he applied it to the three strata of language, and conceived of these as embedded in context:

(This is a view that Cléirigh soon abandoned as his understanding of SFL Theory improved.)

[5] To be clear, these 'other perspectives' are the authors' own misunderstandings of work in SFL Theory, and so function here fallaciously as straw men to be attacked. See further below.

[6] To be clear, in SFL Theory, context and language are not independent, since they are two aspects of the one identity, and their "co-genetic relation" is the development of this identity in logogenesis.

[7] To be clear, 'circumvenient' was the term Cléirigh (almost facetiously) suggested to Martin when Martin rejected the term 'embedding'.

[8] To be clear, in SFL Theory, there can be no determination between context and language because the logical relation between them is elaboration (intensive identity), not causal enhancement (circumstantial identity). What is true is that during logogenesis, previous language instantiations probabilise following language instantiations, and these potentially construe changing contextual features, as when a speaker changes the subject (second-order field).

[9] To be clear, the model that the authors are working toward in this project is therefore based on a confusion of stratification ('realisation') with instantiation ('patterns of meaning'). In SFL Theory, stratification means that the systems of context are realised by the systems of language. Patterns of meaning, on the other hand, are created in the instantiation process of logogenesis: the selection of features and the activation of their realisation statements, and constitute variation along the cline of instantiation.

[10] To be clear, the model that the authors are working toward in this project is therefore based on a fundamental misunderstanding of realisation. In SFL Theory, realisation is one-way relation: the lower level of symbolic abstraction (language) realises the higher level (context). As such, context cannot realise language. Moreover, the use of the term 'actualise' here invites confusion with instantiation as the actualisation of potential as instance. Again, the authors have confused stratification with semogenesis: the instantiation of potential in logogenesis.

[11] As will be seen, in the model that the authors are working toward in this project, their misunderstanding of stratification leads them to mistake the lower level of symbolic abstraction (semantic choice) for the higher level they plan to model (context), thereby invalidating their model and their project.

[12] This is a serious misunderstanding of metaredundancy. As the term implies, 'metaredundancy' is a redundancy on a redundancy. Applied to the stratification hierarchy, it means that semantics is redundant on the redundancy of lexicogrammar and phonology, or alternatively, that the redundancy of semantics and lexicogrammar is redundant on phonology. Applying the term to just two levels of symbolic abstraction, context and semantics, is therefore nonsensical.

Misunderstanding Tenor As The Language That Realises Tenor

Doran, Martin & Zappavigna (2025: 7):

Understanding how social relations are enacted is thus crucial to understanding how language is used and how we build our social world itself. Accordingly scholars in SFL (and related approaches) have worked hard to model tenor for upwards of half a century. However, as we will explain in this chapter, while these efforts have given us great insight into language in relation to its social context, they have often struggled to relate the internal organisation of language to parameters proposed for tenor. The model presented in this book is our reconception of tenor as a resource for negotiating social relations. It is a new approach that aims to better link options in tenor to those of language.

Reviewer Comments:

[1] To be clear, the reconception of tenor presented by the authors in this book confuses tenor (context) with the linguistic resources that realise it. This confusion renders the model theoretically invalid.

[2] To be clear, this new approach does not link options in tenor (context) to those in language. Instead, it misunderstands tenor as the language that realises tenor.

ChatGPT Comments:

Misconstruing Tenor in the SFL Architecture

The authors' stated aim — to reconceive tenor as "a resource for negotiating social relations" in order to "better link options in tenor to those of language" — misrepresents the theoretical architecture of Systemic Functional Linguistics (SFL). Specifically, it conflates the contextual variable of tenor with the linguistic resources that realise it, thereby collapsing the relation of realisation.

In the SFL model, tenor is not linguistic. It is one of the three variables of context, alongside field and mode, stratified above language. Each variable of context is realised by meaning at the level of semantics, which is realised by lexicogrammar, which is realised by phonology/graphology. Specifically, tenor — which encompasses role relationships, status, and social distance — is realised by interpersonal semantic systems such as speech function and appraisal. These systems do not constitute tenor; rather, they realise it, at a lower level of symbolic abstraction.

Misconstruing tenor as the language used to negotiate social relations reverses the realisation relation and undermines the principle of stratification that is central to the SFL model. This principle maintains a clear distinction between context and language, with realisation as the relation across strata, and instantiation as the relation between potential and instance within a stratum.

Furthermore, to conflate tenor with linguistic systems not only creates theoretical incoherence but also risks significant misapplication in domains such as discourse analysis, pedagogical grammar, and computational modelling, where clarity about stratification is crucial for making principled analytical choices.

The following alternative paragraph offers a theoretically consistent framing of tenor within the SFL model:

Understanding how social relations are enacted is crucial to understanding how language is used and how we build our social world. In Systemic Functional Linguistics, this is modelled through the contextual variable of tenor, which refers to the social relationships between interactants — including roles, status, and affective stance — within a situation. Over the past five decades, scholars in SFL have developed detailed accounts of how tenor is realised in language, particularly through interpersonal semantic systems such as speech function and appraisal. These linguistic resources realise (not are) the social values associated with tenor.

Until this confusion between context and language is resolved, the authors' proposed "reconception" of tenor cannot be considered a theoretically valid contribution to the SFL tradition. A principled model must maintain the distinction between tenor (as context) and the interpersonal resources that realise it in language — both in theory and in application.

Misunderstanding Tenor As Organising Social Relations

Doran, Martin & Zappavigna (2025: 7):

In this book we introduce a new model for analysing how people negotiate social relations in discourse. We do so within the general theoretical framework of Systemic Functional Linguistics (SFL), by developing its conception of social context. The particular parameter of context we focus on is what is known in SFL as tenor. In SFL, tenor has typically been considered the contextual variable that organises our social relations – the 'roles played by those taking part’ in a situation, ‘the values that the interactants imbue’ the activity with (Halliday & Matthiessen, 2014, p. 33) and the relationships between addressees or interactants (Gregory, 1967; Hasan, 2020). Or, more broadly, the ‘general dimensions of social relations’ (Poynton, 1990a, p. 70) and their negotiation (Martin, 1992, p. 523).

Reviewer Comments:

[1] To be clear, in the model being used here, negotiation is an interpersonal system located in language: on Martin's stratum of discourse semantics. It will be seen, throughout this book, that the authors repeatedly confuse interpersonal semantics with tenor, the interpersonal dimension of the cultural context that is realised by language.

[2] To be clear, this is the basic misunderstanding that undermines the authors' new model of tenor. In SFL Theory, tenor does not organise social relations. Tenor refers to the interpersonal relations between interactants, speaker and addressee, that are realised by the choices they make in language, especially interpersonal choices.

Importantly, in SFL Theory, context refers to the culture as a semiotic system. This means that it is of the semiotic order of experience, not of the material order.

ChatGPT Comments:

Further Thoughts and Implications:

1. Tenor as Interpersonal, Not Organisational: The misunderstanding of tenor as something that "organises" social relations overlooks the nuanced role that tenor plays within SFL. Tenor does not structure social relations directly but is the medium through which interpersonal dynamics are realised in discourse. It is essential to recognise that tenor operates on the level of the interaction itself rather than attempting to encapsulate all social structures.

2. Semiotic Context and Its Relationship to Language: The authors’ conflation of interpersonal semantics with the broader concept of tenor highlights a fundamental issue in how SFL views context. Context in SFL is not just a backdrop to language; it is part of the semiotic order that shapes meaning. The failure to distinguish between these layers leads to an oversimplification of how social relations are negotiated and represented in discourse.

3. The Importance of Stratal Clarity: This confusion between interpersonal semantics and tenor shows the importance of maintaining clarity across strata in SFL analysis. Tenor should be located at the level of the cultural context, not within the interpersonal semantics of discourse. Without clear distinctions, we risk misrepresenting how meaning is structured and communicated.

4. Potential for Clarification: One way to address this misunderstanding would be to revisit the relationship between tenor and the interpersonal metafunction in SFL. By emphasising that tenor is about the configuration of relationships between participants within a given discourse, rather than an organising force of those relations, a more accurate and functional interpretation could emerge.

5. Beyond the Text: Tenor in Social Interaction: While the authors focus on the linguistic realisation of tenor, it would also be valuable to consider how tenor extends beyond text into lived social contexts. By focusing on the realisation of social relations through language, rather than treating them as structural entities, we could gain a richer understanding of how people navigate power, identity, and interpersonal dynamics.