Recent findings about language comprehension in minimal speakers with autism

(Cross-posted at FacilitatedCommunication.org).

A recent paper on language in autism has some interesting implications for facilitated communication and its variants.

But first, some context. Most studies of language skills in autistic individuals combine language production skills (mostly in spoken language) and comprehension skills (mostly of spoken language). When they examine distinctive facets of language like pronunciation, vocabulary, syntax, and pragmatics, they tend not to systematically disentangle comprehension from production. Vocabulary is often measured by comprehension: does the child point to, or look at, the picture of the “cup” when the word “cup” is spoken? Syntax tends to be measured by production: the child repeats a sentence or generates a sentence from a picture prompt, or observations are made of a child’s spoken language in real-life contexts. Pragmatics may be measured through judgments (or parent surveys) of the social appropriateness of the person’s utterances and/or the person’s judgments of the social appropriateness of hypothetical utterances by other people in different contexts.

Despite these common practices, separating comprehension from production and measuring a person’s comprehension of words, sentences, and socially embedded communications (directions, conversations, narratives) is arguably the best way to establish a person’s linguistic capabilities. That’s because comprehension precedes, and is a prerequisite for, meaningful speech. If one speaks without comprehension, that doesn’t really count as language; if one speaks hardly at all but understands a great deal, that does count as language—significant language.

Knowing a person’s language comprehension skills is crucial for making the following key determinations:

• how much they’re taking in when people talk to them
• how much information they’re able to learn through verbally presented material
• how much they understand of what they’re saying or typing when they speak or type

And here’s where the connection to FC comes in: a person’s typed-out messages cannot possibly be coming from that person if he or she doesn’t understand the words, phrases, syntax structures, and informational content that comprise those messages.

Then there’s the connection to autism: language comprehension difficulties have been found to be more essentially connected to autism than language production difficulties are. That’s because comprehension necessarily involves something that is inherently challenging in autism: turning into other people and getting inside their heads. To understand what a specific word refers to, or what an entire spoken or written message means, you need to figure out what the speaker/writer is referring to, and/or what their subtext is, and/or what their purpose is.

Few papers, as I said, have focused specifically on comprehension in autism, but a new paper has just come out that helps to fill this gap: Vyshedskiy et al. (2024).

On one hand, Vyshedskiy et al.’s language comprehension data doesn’t come from the most reliable source: they used parent surveys rather than professional assessments. On the other hand, their sample was huge and broad: 31,845 autistic individuals from 4 to 21 years of age.

To measure language comprehension, they used this:

The first nine of these questions—from “knows own name” to “understands verb tenses (i.e. I will eat an apple vs. I ate an apple”)—look straightforward and specific enough to be amenable to objective answers. So do questions 12 and 13. In some cases, the parent might not know the answer offhand, but the questions make it clear how to prompt the child to figure it out.

Only questions 10, 11, and 14 are potentially problematic, focusing on linguistic phenomena—stories and explanations—where it may be easy (and even tempting) to read in more comprehension than really is there.

To measure factors other than comprehension—including expressive language, sociability, and sensory sensitivities—the authors used something called the “ATEC questionnaire.” (They state that “Various studies confirmed validity and reliability of ATEC”).

As for the authors’ methodology, this was potentially more objective than what’s possible with smaller data sets. Rather than trying to make the data fit pre-existing assumptions, they used an automated, unsupervised cluster analysis to determine which non-linguistic factors correlated with which comprehension profiles. And their results, as it turns out, are not particularly convenient for FC proponents.

Their cluster analysis identified three distinct levels of language comprehension:

• individuals in the command-language-phenotype, who were limited to comprehension of simple commands (40% of the sample)
• individuals in the modifier-language-phenotype, who could also comprehend color, size, and number modifiers (43% of the sample)
• individuals in the syntactic language-phenotype, who could also comprehend spatial prepositions, verb tenses, flexible syntax, possessive pronouns, and complex narratives. (17% of the sample)

And here’s what the cluster analysis showed:

Participant clusters displayed statistically significant differences in properties that were not used for clustering, such as expressive language, sociability, sensory awareness, and health… demonstrating that language comprehension phenotypes are associated with symptom severity in individuals with ASD. [Boldface mine].

In particular, the authors report:

• The syntactic language phenotype had the greatest proportion of individuals characterized by parents as having mild ASD and the lowest proportion of individuals with severe ASD.
• The command language phenotype had the greatest proportion of individuals characterized by parents as having severe ASD and the lowest proportion of individuals with mild ASD.

Since those most likely to be subjected to FC are those with the most severe autism symptomology, this finding adds to the mounting evidence that those subjected to FC do not have the comprehension skills to author the linguistically sophisticated messages that are attributed to them.

In addition, the authors find the following connection to expressive language skills:

91% of children in the command language phenotype were nonverbal or minimally verbal, compared to 68% in the modifier language phenotype, and 33% in the syntactic language phenotype.

Since those most likely to be subjected to FC are minimally verbal individuals, this finding also adds to the mounting evidence against the purported authorship skills of those subjected to FC.

But what about the finding that 33% of individuals in the highest comprehension group are minimally verbal?

It’s possible that some of those individuals fell into that cluster, in part, because their parents over-estimated their comprehension of stories and explanations—a possibility I suggested earlier. Intriguingly, however, this is not the first time evidence has emerged of a subset of minimally verbal individuals with relatively intact comprehension skills. About a year ago, I wrote a blog post that reported on a study presented at the 2023 INSAR conference—a study that has since been published (Chen et al., 2024).

Like Vyshedskiy et al., Chen et al. looked at comprehension. Their sample consisted of 1579 minimally speaking autistic children, and they found that:

• minimally speaking autistic children had much lower receptive language skills (comprehension skills) compared to their neurotypical peers
• this gap widened with age
• receptive language skills correlated with social skills (and thus with one component of autism severity)

And like Vyshedskiy et al., they found that there exists a subset of minimal speakers—about 25% of their sample—in which receptive language skills are relatively high relative to expressive skills (e.g., speaking skills). However, they also found that the receptive language skills even of this unusual subgroup

• are still lower than those of same-aged, non-autistic individuals
• are positively associated with motor skills.

That is, as Chen puts it in a video describing her findings:

[I]n this subgroup, motor skills emerge as the only significant factor predicting the discrepancies between receptive and expressive language [language comprehension and language production] above and beyond all other factors. And those with better motor skills are more likely to have much better receptive language than expressive language.

And this amounts to one more piece of evidence that those who are supposedly most in need of FC—i.e., because of their purported motor difficulties—also have the worst receptive language skills.

---

References:

Chen, Y., Siles, B., & Tager-Flusberg, H. (2024). Receptive language and receptive-expressive discrepancy in minimally verbal autistic children and adolescents. Autism research : official journal of the International Society for Autism Research, 17(2), 381–394. https://doi.org/10.1002/aur.3079

Vyshedskiy, A., Venkatesh, R. & Khokhlovich, E. (2024). Are there distinct levels of language comprehension in autistic individuals – cluster analysis. npj Mental Health Res 3, 19. https://doi.org/10.1038/s44184-024-00062-1

Should Schools Dedicate Time to Grit and Growth Mindset?

 Just out in Skeptical Inquirer!

On Chalk & Talk--Math and Autism with Anna Stokke

 In which we discuss Direct Instruction, Precision Teaching and--of course!--math instruction meets facilitated communication:

https://chalkandtalkpodcast.podbean.com/

Has AI gotten any better at reading since 2019?

 …2019 being the year that Gary Marcus and Ernest Davis published Rebooting AI and discussed the inability of AI to handle passages like this one, from Laura Ingalls Wilder’s Farmer Boy:

Almanzo turned to Mr. Thompson and asked, “Did you lose a pocketbook?” 

Mr. Thompson jumped. He slapped a hand to his pocket and fairly shouted. “Yes, I have! Fifteen hundred dollars in it, too! What about it? What do you know about it?” 

“Is this it?” Alamanzo asked. 

“Yes, yes, that’s it!” Mr. Thompson said, snatching the pocketbook. 

He opened it and hurriedly counted the money. He counted the bills over twice… 

Then he breathed a long sigh of relief and said, “Well this durn boy didn’t steal any of it.”

They find that AI fails to answer questions like:

• Why did Mr. Thompson slap his pocket with his hand?
• Before Almanzo spoke, did Mr. Thompson realize that he had lost his wallet?
• What is Almanzo referring to when he asks “Is this it?”
• Who almost lost $15,00?
• Was all of the money still in the wallet?

So I fed Gemini the same passage and asked it the same questions.

Gemini did well on the first question:

The passage describes Mr. Thompson being worried about his lost pocketbook. After Almanzo asked him if he had lost a pocketbook, the text says that “Mr. Thompson jumped. He slapped a hand to his pocket and fairly shouted.” This suggests that Mr. Thompson slapped his pocket to check if his pocketbook was still there. In other words, he was likely worried that he had lost it.

It didn’t do so well on the second: 

The passage doesn’t explicitly tell us if Mr. Thompson realized his wallet was missing before Almanzo spoke. Here’s why: The passage starts with Almanzo asking about a lost “pocketbook,” not mentioning Mr. Thompson’s awareness. Mr. Thompson’s reaction (jumping and slapping his pocket) could be due to either suddenly realizing it’s missing or simply confirming a nagging suspicion. There isn’t enough information to definitively say whether Mr. Thompson knew beforehand.

In its answer to the third question, it’s slightly off, identifying “it,” rather than “this,” as the item that refers to the wallet in Almanzo’s hand (as opposed to the wallet that was lost):

In the passage, when Almanzo asks “Is this it?”, he’s most likely referring to the pocketbook he holds (or possibly points to) that belongs to Mr. Thompson. 

Here’s why: 

The conversation revolves around a lost “pocketbook” that Almanzo mentions first. Mr. Thompson reacts strongly to the question, suggesting he recognizes the object as his missing belonging. He then snatches the “it” in question and confirms it’s his lost pocketbook. Therefore, “it” refers to the physical pocketbook Almanzo has presented to Mr. Thompson.

In its answer to the fourth and fifth questions, Gemini gets back on track:

From the passage, it was Mr. Thompson who almost lost $1,500. The text says he had that amount in the “pocketbook” and reacted with relief upon finding it.

...

The passage suggests that all the money was still in the wallet. Here’s why: Mr. Thompson snatches the wallet back and hurriedly counts the money. He counts the bills “over twice,” implying a thorough check. Finally, he breathes a sigh of relief and says, “Well this durn boy didn’t steal any of it.” This sequence suggests Mr. Thompson found all the money he was expecting to find, leading to his relief. There’s no mention of missing money.

But when I asked it a fifth question that doesn’t appear in Rebooting AI, things fell apart:

Unfortunately, the passage doesn’t give us a clear answer about who Mr. Thompson refers to as “this durn boy.” 

Here’s why: 

A general statement of relief without a specific boy in mind. There’s no mention of any other boys in the scene. 

It’s unclear if Mr. Thompson suspected someone (possibly a boy) of stealing the wallet before Almanzo found it. His relieved statement, “Well this durn boy didn’t steal any of it,” could be: 

• Directed at himself for possibly misplacing the wallet and fearing a boy might have found it.
• A general statement of relief without a specific boy.

Some possible revelations on what goes on in facilitators’ heads when they facilitate big projects

(Cross-posted at FacilitatedCommunication.org.)

In this post, I return to one of the news stories I included in my FC news roundup from two weeks ago: a story on KQED’s California Report Magazine about a non-speaking 19-year-old who, after a breakthrough at age 16, defied impressions that, as reporter Sasha Khokha puts it, “he didn’t have the motor skills to point to the right answers in school.” The boy, who now goes by Jacob, was, purportedly, suddenly able to slowly type out full sentences with everything spelled correctly.

In one of the accompanying photographs, we can see Jacob engaging in the typical RPM/S2C-style of letter-selection, with someone else holding up a device to his extended index finger. We can also see a reference in the caption to a neurologist who “confirms that even though his father holds the device for him, Jacob types independently.” That neurologist, later identified as Dr. Margaret Bauman, has a history of defending FC, and it’s unclear on what basis she confirmed Jacob’s independence. In fact, the only way to establish independence is through a rigorous message-passing test in which the facilitator is reliably blinded. Bauman has been involved in only one published message-passing test, back in 1996. As we discuss here, that test was very far from rigorous.

Here comes the part I didn’t get to in my earlier post. According to the article, which is titled “Non-Verbal Teen to 'Take on the World' With a Symphony Written in His Head”:

Six months after learning to type, Jacob surprised his parents again. He told them he had a 70-minute symphony in his head… It’s called Unforgettable Sunrise.

Since Jacob can neither sing nor play an instrument (nor, apparently, read music), one of Jacob’s father’s collaborators, composer Rob Laufer, was brought in to translate Jacob’s verbal descriptions of the 6-movement, 70-minute symphony into a musical score on paper. Laufer, purportedly, “was amazed at the precision of Jacob’s vision for the symphony.”

But what, exactly, did it take for Laufer to translate Jacob’s vision onto paper? In the next dozen paragraphs I’m going to embark on what might seem like an off-topic excursion into symphonic composition and the translation of mental music into musical scores. But my objective here is to explore a broader question:

What is going on in the minds of parents and other facilitators when they assist minimally verbal individuals with nonverbal tasks and large projects that go beyond a few pages worth of typed output?

And my goal, once I emerge from this musical excursion towards the end of this post, is to formulate some possible answers that came to me only as I read and listened to this fascinating—if irresponsible—KQED report.

An excursion into classical music composition and translating mental music into notes on paper

People who attend classical music concerts regularly see multi-paragraph-long descriptions of the pieces being performed. Here’s an excerpt from the program notes of a recent Philadelphia Orchestra concert describing the first movement of Bruckner’s 4th symphony:

After a nocturnal string tremolo that opens the first movement (Bewegt, nicht zu schnell), the horn announces the sunrise and the dawn of a new day for hunting. The theme is eventually taken up by the rest of the orchestra and developed using Bruckner’s favorite rhythm of two beats followed by a triplet. A lighthearted second theme appears first in the strings, evoking the gentle folk-dance flavor that Mahler would later allude to in the Ländler movements of some of his symphonies. The main “horn call” motif then opens the development section, which ebbs and flows around a brief treatment of the second theme and further development of the “Bruckner rhythm,” culminating in a majestic brass chorale garlanded with string tremolos. This sets up the recapitulation, where the first theme is embroidered with an added flute solo, and the second theme is harmonically enriched with unusual modulations. An extended coda prepares for a triumphant return to E-flat at the conclusion.

—Luke Howard

Imagine, first, how long it would take someone extending an index finger to a held-up keyboard to type all this out.

Imagine, second, whether anyone reading this passage who had never heard Bruckner’s 4th symphony before, even if he is a skilled composer, could possibly translate it into the actual melodies, chords, rhythm, and orchestration of Bruckner’s 4th symphony. As pianist and conductor Daniel Barenboim writes in a recent New York Times Op-Ed, “when we try to describe music with words, all we can do is articulate our reactions to it, and not grasp music itself.”

Perhaps a better way to grok what it takes for Person B to transcribe music from Person A’s head into notes on paper, with little other than Person A’s words to guide them, is to watch this scene from the movie Amadeus. Here Salieri sits at the foot of Mozart’s deathbed and attempts to transcribe, from Mozart’s verbal directions and humming, a short passage of the requiem that Mozart has inside his pillow-propped head. While this scene gives us some idea of what’s involved, though, even it strains credulity. Amadeus takes many liberties not just with Mozart’s life, but also with what Salieri can realistically glean from what comes out of Mozart’s mouth.

What’s crucial here, however, is that the Mozart character uses not just ordinary words, but musical terms, and, in addition, that he frequently illustrates melodies by humming them. Finally, since he can read music, he can check Salieri’s transcription. Here’s an excerpt from the scene:

Strings in unison. Ostinato, on A. Like this: [HUMS] Next measures rising. Do you have it? Show me.

In contrast, Jacob’s directions consist of words only: words about specific instruments, specific actions or emotions, and the number of iterations and/or for how long. For example:

It starts with piano bangs. Five bursts of cacophony.

In response to this particular prompt, Laufer had to guess the specific chords. He reports hypothesizing that Jacob might have in mind “this chord that I used to think about when I was young that I associated with the end of the world.” So Laufer played a specific chord he used to think about for Jacob, who apparently confirmed it as exactly what he had in mind—presumably by poking out some sort of affirmation on the keyboard held up by his father. In contrast to Mozart checking Salieri’s transcription, Jacob can only type “yes” or “no.“ But conveniently—because otherwise there could have been an endless back and forth—of all the tens of thousands of possible sets of five bangs within the 88 keys of the piano, Laufer guessed the correct ones.

Some of Jacob’s directions are more emotional:

I want triumph and happiness followed by terrified laughter and grief over so many years of painful silence.

Others more poetic:

The violins are demanding sleep and the horns are demanding pain. They battle for 3 minutes of call and response until the horns realize that they are defeated (Every manic horn met by soaring violin).

But while a skilled composer might translate these prompts into music that evokes them, countless translations are possible, and the chance of any particular one matching the music in someone else’s head is close to nil.

At this point, it might be interesting to contrast a sequence of prompts attributed to Jacob to a sequence of prompts attributed to Mozart in Amadeus.

It’s hard to imagine how Laufer could have translated a 70-minute symphony from thousands of prompts like the ones on the left unless most of the time he guessed correctly. But Laufer suggests this is more or less what happened: Jacob’s directions “made sense” because they were “coherent to the story he wanted to tell.”

Jacob, for his part, purportedly says:

I was unbelievably damn floored by Rob’s ability to tap into my emotions. I can only say that he is my great collaborator and he reads my musical mind. He can always feel what I want and turn it into amazing notes.

But there’s another possibility—assuming we take everything we read here on faith. Perhaps what was in Jacob’s head wasn’t really a symphony per se, but merely a bunch of verbal ideas for what kinds of emotions and interactions a symphony might express.

But that hardly counts as having an actual symphony in your head.

Regardless of what actually happened, there are a number of things at play here that suggest some broader possibilities about facilitation and translation in minimally verbal autism.

What might be going on in the minds of facilitators when they assist minimally verbal individuals with large projects and nonverbal tasks?

A number of facilitated individuals have accomplishments attributed to them that amount to far more than producing short passages of typed output. Many attend college and presumably produce long research papers, answer math problems, balance chemistry equations, and/or participate in labs; some direct movies; some compose; some co-author peer-reviewed journal articles. Even output that’s purely verbal must often go through multiple drafts, from large-scale reorganization to sentence- and paragraph-level revisions to word-level copy-edits to footnoting and formatting of bibliographies. Much of this goes beyond what can reasonably be accomplished by holding up keyboards to extended index fingers. So what happens behind closed doors?

Here’s a possibility. Perhaps, just like Laufer with Jacob, the facilitator goes beyond facilitation to “translation.” Perhaps the facilitator, like Laufer, makes very specific guesses at what their client wants to produce—without thinking too hard about how many actual possibilities are out there—and then seeks confirmation on the keyboard, and then finally (in cases where, unlike with Laufer and Jacob’s dad, the facilitator and translator are one and the same person) facilitates out affirmative responses from them. Perhaps the facilitator, like Laufer, presumes that the person is competent enough to produce something that “makes sense” and is “coherent,” and also that they know the person so well that they can guess what the person would produce on their own if they could: what kind of essay revision; what kind of movie direction; what kind of symphonic passage. And as long as they believe that they have obtained affirmation from their client on whether these are the melodies and chords, or the scene and camera angle, or the thesis statement and supporting paragraphs, or the steps in the mathematical solution or lab report, that their client had in mind, they can also believe that the resulting product is, in essence, the creation of their client.

As for the affirmation process, assuming the story of Jacob and the 70-minute symphony is representative, it seems to go swiftly: the facilitated answer to the suggested melodies and chords, or suggested scene and camera angle, or suggested thesis statement and sentence revisions, or suggested steps in the mathematical solution or lab report, is quite likely to be consistently “yes.”

In the majority of the cases where only a facilitator is involved (and not, say, a composer or cinematographer or mathematician), what all this means is that the facilitators may unwittingly produce not just verbal messages, but entire projects.

Anecdotally, we’ve heard anonymous behind-the-scenes accounts that precisely this sort of thing has happened: a facilitated college student has to write a long essay, the facilitator holds up the keyboard and extracts some starting words or sentences, the student wanders off after a while, and the facilitator writes the rest of the essay, checking in with the student later about whether it’s what she had in mind—or, worse, simply assuming that that’s what the student would have written, if only she could have.

Epilogue

Returning to the KQED piece, we learn that Jacob’s next composition is a Mozart-influenced opera. Will Laufer be up to the challenge? Time will tell

19th Century English Vocabulary

Notes from the last decade (or so) of reading 19^th century novels (a follow-up to my earlier post on syntax)

… with a special focus on “false friends”: words whose meanings have subtly shifted or narrowed in ways that may lead today’s novice reader astray.

“agree with” for “accord/mesh with”

“answer to/for” for “fulfills the need of”

“answerable” for “responsible”

“art” for “skill”

“bring to terms” for “force to surrender”

“careless” for “carefree”

“closet” for “private rooms”

“country” for “part of the country” or “countryside”

“condescension” for “kindness towards a person of lower status”

“check” for “limit”

“discover” for “find” (“My father is going to London to try to discover her”)

“discover” for “reveal” (“she risked discovering herself”)

“dull” for “stupid”

“easy” for “relaxed” or “at ease”

“even” for “just” (“even so”)

“gay” for “happy”

“fair” for pretty or nice

“fix” for sabotage (“Pelops bribed the charioteer to fix the chariot”)

“host” for army

“in a body” for “as a group”

“intercourse” for “social interaction”

“interview” for “conversation”

“issue” for “children/offspring”

“issue” for “consequence”

“late” for “recent”

“make love to” for “woo”

“miss” for “notice that something is missing”

“might” for “power”

“object” for “goal”

“person” for “personality”

“sensible of” for “aware of”

“signify” for “means something” (“That doesn’t signify”)

“society” for “company” or “social events”

“souls” for “people” (“a village of only 400 souls”)

“stay” for “wait”

“suffer” for “allow”

“suppose” for “assume” (“I supposed he wouldn't be at home”)

“throat” for “neck”

“use” for “treat” (“ill-used”)

 “want” for “need” or “be lacking in” (“He does not want abilities”)

“weeds” for “clothes”

News Roundup, May 2022 to April, 2024: Uncritical reports of S2C and RPM breakthroughs

 (Cross-posted at FacilitatedCommunication.org)

It’s been a busy two years for irresponsible, pro-FC reporting by the media, which means our “FC in the news” list needs some updating.

But first, we think, the news items that have crossed our radar since April, 2022 (most of which were passed along to us by other people—many thanks for these!) deserve a blog post of their own. I’ll discuss a few of these in detail and then give thumbnails of the rest, arranging each set in reverse chronological order. Nearly all of them are about the most recent versions of FC: Spelling to Communicate (S2C) and Rapid Prompting Method (RPM).

Set 1: Four longer items

April, 2024

BrainandLife.org—a site that describes itself as “trusted by neurologists” and as “offer[ing] the latest news and resources on specific neurologic disorders and brain health.”

On the April 4th Brain and Life Podcast host Dr. Daniel Correa, an assistant professor of neurology and epilepsy at Albert Einstein College of Medicine who specializes in traumatic brain injury, discussed communication in non-speaking autism.

Correa’s first guest was Khari “Needlz” Cain, a music producer and father to Makayla, a non-speaking 16-year-old who communicates via a held-up letterboard. As the podcast’s accompanying text puts it:

Khari and his family recently created a film titled “Makayla’s Voice: A Letter to the World” that shares her experience finding a way to communicate using letter board therapy. As Makayla’s voice has gradually emerged, she has shown her intelligence, interests, and sense of humor to her loved ones.

In the film’s trailer, we see brief clips of Makayla typing on a held-up letterboard, and we hear, attributed to her, the following voiced-over message:

I do not speak but I do communicate. I use a letterboard to type out my thoughts. I hope to help others. I hope to keep learning about the world. I hope I can end silence in autism.

We also learn that Makayla has Phelan-McDermid Syndrome, a genetic abnormality that involves deletions or rearrangements on chromosome 22 and which, in addition to causing autism in at least a quarter of cases, causes intellectual disability in nearly all of them.

In the interview, “Needlz” Cain tells Dr. Correa that Makayla’s first symptoms of atypical development were an inability to follow directions. This he attributes to what he says is Makayla’s inability to control her body. The possibility that the actual problem may be a cognitive or linguistic challenge—specifically, a difficulty in comprehending directions (comprehension difficulties being a well-documented area of major difficulty in autism)—is entertained neither by “Needlz” Cain, nor by Dr. Correa.

“Needlz” Cain proceeds to describe how he came across the S2C-providing service ReClif, how letterboarding unlocked Maykala at age 14 (she’s now 16), and how much language and intelligence was locked up inside her disobedient body.

Dr. Correa is as impressed as any of us might be—provided we don’t know any better and/or don’t think to look past the feel-good anecdotes:

Up until you started to work with Roxy [S2C practitioner Roxy Sewell, Makayla’s “communication partner”] and the letterboard, you guys didn’t really know all the context that Makayla had in her herself and in the movie you can see how she can express herself so clearly and in a lovely way.

…

I found it incredibly touching…that ability that you guys now have to connect with her to help her express herself… and to increase awareness in the community.

Dr. Correa’s second guest is Dr. Deepa Menon, the Assistant Medical Director, Center for Autism Services, Science and Innovation at the Kennedy Krieger Institute.

When asked specifically about the letterboarding, Dr. Menon says she was unfamiliar with it. However, rather than looking up the empirical and critical literature on language acquisition in autism, literacy acquisition in general, and concerns about held-up letterboards, Dr. Menon reports that

I went back and looked at the video [Makayla’s Voice: A Letter to the World]. And it actually looks pretty good. It actually shows that she has the literacy component to be able to spell it out so that it actually to me intriguing.

Dr. Menon does acknowledge that Makayla’s story doesn’t fit the typical literacy and language learning trajectory that begins with phonics and simpler communication systems like PECS (Picture Exchange Communication System). However, apparently on the basis of what she observed in the video, she concludes:

I would think of the letterboard as another part of the augmented communication… Makayla is actually learning to put the words together.

Dr. Menon wonders whether Makayla might be able to type on a keyboard as well, but omits the key question: namely, can Makayla type on a stationary surface without anyone within auditory or visual cueing range providing cues about where her extended index finger should move?

The discussion of Makayla concludes with Dr. Correa proposing that Makayla may have acquired literacy by surfing the Internet (something her father reports that she does) and reminding us of the difficulty that she purportedly has controlling her body, and with Dr. Menon proposing that Makayla may indeed be, as the father suggested, “sort of locked in, almost.”

No matter that this overturns all we know about language acquisition in autism, literacy acquisition in general, and concerns about held-up letterboards, not to mention non-speaking autism and Phelan-McDermid Syndrome.

March, 2024

PBS

PBS removed its well-researched 1993 FC exposé, Prisoners of Silence, from its website years ago, replacing it with pro-FC pseudoscience. (Prisoners of Silence is now only available on the Internet Archive, to which I now donate the money I used to donate to PBS).

The first of the pro-FC documentaries to appear on PBS’s website was Deej; now comes a documentary entitled Understanding Autism.  Its director, Scott Steindorff, diagnosed as an adult as autistic, interviews a variety of individuals with autism. Only one of them, Elizabeth Bonker, is an FC user, but Steindorff gives Bonker and her mother quite a bit of air time and enthusiastic commentary.

Starting at 29:00-30:30, her mother sitting next to her and staring at the keyboard whenever Bonker types, we see Bonker pushing a button that plays a much-quoted line from her valedictory speech at Rollins College: “There are 31 million non-speakers with autism who are locked in a in silent cage…” This is followed by a line about getting schools to help free non-speakers by abiding by the Americans with Disabilities Act, and then by Steindorff asserting:

And so we need to get computers and technologies into schools [Here we wonder whether Steindorff has been inside a classroom since the early 1990s] and allow this to happen [What “this” refers to is left unsaid].

Steindorff then asks, “Can somebody give me a rational reason why this is not happening?”

A computerized voiceover attributed to Bonker replies: “This is a matter of money and ego. The service providers will lose money and admit that they were wrong about our capabilities.”

Carefully edited clips of Bonker typing follow, as her mother, Virginia Breen, describes how they had to hire a lawyer to “have her be in public school”—a rather extraordinary statement that Steindorff leaves unchallenged.

The film returns to Bonker at 34:06-36:19, with a computerized voiceover attributed to her, accompanied by soft piano notes, saying “My life is for service for those who are voiceless.” Steindorff brings up the 2011 memoir I am in Here, which contains 70 poems credited to Bonker. He rhapsodizes first about Bonker’s brilliance and the life within her, then about the reference in her valedictory speech to Viktor Frankl’s Man’s Search for Meaning, which Steindorff states is his favorite book. The soft piano notes continue, as does Steindorff’s rhapsodizing. The scene concludes with Steindorff saying “You are such a beautiful soul. Thank you for doing what you do,” and asking Bonker if he can give her a hug. Bonker, unsmiling, leans towards him and Steindorff hugs her.

In discussing his film, Steindorff has stated:

There is a lot of misunderstanding around autism, and through a more thorough understanding of neurodiversity we can reduce the shame and stigma surrounding them. This film is not only for people on the spectrum, but also for the world to watch and learn.

We can certainly agree on the first eight words of that statement.

Egregiously absent from a film called “Understanding Autism” is any commentary by experts in the fields of nonverbal autism and assisted communication regarding the rather surprising claims it airs, and impressions it conveys, about non-speaking autism.

September, 2023

MLB.com website (the official site of Major League Baseball)

A news item on MLB.com website (the official site of Major League Baseball) recounts the friendship between Atlanta Braves’ first baseman Matt Olsen and Reece Blankenship, a high school classmate who “has non-speaking autism.” Reporter Anthony Castrovince describes non-speaking autism as a condition that “leaves [Reece] with little authority over his body movements,” “trapped inside a nightmare,” and “fully capable of understanding the world around him, yet unable to transmit his thoughts”—a set of purported symptoms that is completely inconsistent with the symptoms that have defined autism since the term was first coined 8 decades ago.

Castrovince then discusses the “communication breakthrough that allowed [Reece] to pursue the dreams once locked inside him”: namely, the letterboard.

Cannily, from here Castrovince segues to the claim that “Reece’s condition is not uncommon. According to the National Autism Association, 1 in 36 children are affected by autism, and about 40% of those children do not speak”—thus implying that the rest of those 40% could also benefit from letterboarding.

Returning to Reece, Castrovince recounts how in high school “Reece was diagnosed to have the intellectual capabilities of a 3-year-old,” but then “in 2014, Reece had a quantum leap in communication” after his parents took him to an S2C workshop. Interestingly, Castrovince states that “Reece had done quite a bit of practicing via home-based therapy in the weeks leading up”—though he’s unclear on what this home-based therapy was and whether it amounted to something like S2C. In any case, the actual breakthrough “came early in the workshop,” when one of the therapists asked him what he knew about astronomy:

“We’re going to talk about astronomy,” one of the therapists said to Reece. “Do you know anything about that?”

Reece began pointing to letters on the board, spelling out a complete sentence: “I know Copernicus advocated that the Earth revolves around the sun.”

Lou and Jeff looked at each other in amazement. Doctors had told them their son had the intellectual equivalent of a toddler. But in that moment, he showed he had so much more to offer. “The joke's on us,” says Matt, “because Reece is probably the smartest person in the room.”

One of the consequences of Reece’s communication breakthrough, Castrovince notes, is Reece’s founding of ReClif, a company whose offerings include S2C. Just like Bonker, Reece wants to spread S2C to others. And he has: remember “Needlz” Cain? That’s how he got Makayla started on S2C.

Arizona Public Radio

Another news item from last September showcases S2C, this time in connection with legal guardianship. The person in question, Beth Papp “uses boards with letters and some symbols to spell out phrases” and “then her communication partner, Emily Ulan, reads them out.” Reporter Kirsten Dorman notes that Ulan “also holds the boards up for Papp to access better.”

Based on Papp’s purported communicative capabilities and the messages attributed to her, her mother has made a major decision regarding Papp’s future: they’ve decided against seeking legal guardianship over Papp in her adulthood, and instead opted for something called “supported decision-making.” Apparently Beth has typed out, while Ulan held up the letterboard to her outstretched index finger, “I want to be my own guardian.”

Supported decision-making might be appropriate in cases where the person with disabilities can clearly and authentically communicate their aspirations for adult life. But in cases where the messages are likely to be coming from the communication partner, the process is highly susceptible to hidden, self-serving agendas on the part of the latter that potentially undermine their client’s best interests—as we see, for example, in a chilling moment in Prisoners of Silence where FC-practitioner Rosemary Crossley asks a man in a coma where he wants to live and then slowly moves the man’s head to point to one of four choices on a piece of paper, thus making him appear to choose “nursing home” over “parents.”

Dorman does briefly acknowledge that controversy exists. She quotes Beth’s mother as saying that “Papp’s communication method isn’t recognized by the court system.” She adds that “some consider it controversial due to concerns surrounding authorship – or who’s crafting and influencing the messages.” But she immediately follows this with:

But one message is clear: “I want to be my own guardian. I want to make decisions for myself,” Papp said.

And later, Dorman adds:

In Papp’s case: Her communication method is so new that there’s little research on it.

No, S2C is not new, and there’s plenty of research showing its lack of empirical support. But S2C is apparently new to Dorman, who, like all the journalists and neuropsychology professionals discussed above, has apparently done little-to-no research before discussing it.  

The pattern continues below.

Set 2: 20 additional stories in brief

April, 2024

LAist, a newsroom that is home to L.A.’s largest National Public Radio station.

In an LAist news story, Gab Chabrán, a food editor and father of an autistic girl, reports on a beer “made and marketed by nonspeaking autistics” who use “the Spellers Method, a series of letter boards that allowed individuals to point to letters to help them spell out the words to communicate.” Meg Gill, the CEO and co-founder of the brewery and also the parent of an autistic girl, discovered JB Handley’s S2C-promoting memoir Underestimated, which connected her to Dawnmarie Gaivin, who plays a starring role in Underestimated and runs a nearby S2C outfit.

No mention of the complete lack of evidence base for S2C or of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

The Sun Journal, a Lewiston Maine newspaper

A puff piece on S2C practitioner Rebekah Carmichael-Austin, which consists of a bunch of softball questions and extended answers from Carmichael-Austin. The latter recounts how she learned about S2C after watching the documentary Far from the Tree (see Janyce’s review), taking her son to Elizabeth Vosseller’s S2C clinic, and “witnessing Kaleb answer age-appropriate questions on the letter board.” Carmichael-Austin later founded her own S2C clinic. She states that 70% of her clients are autistic, while “the other 30% have a motor component to it like Down syndrome or Angelman syndrome, and that most “have apraxia, a neurological condition that disrupts their ability to control body movements despite their desire and physical capability to do so.”    

No mention of the complete lack of evidence base for S2C, including its claims about apraxia, or of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

February, 2024

CFJC Today, a TV news show out of Kamloops, British Columbia

Reporter Adam Donelly reports on an RPM user who goes from nonspeaking to “incredibly well-spoken” thanks to the work of RPM practitioner Madison Imber. Donelly also discusses the promotion of RPM and S2C by both Imber and the boy and his family.

No mention of the complete lack of evidence base for RPM or of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

November, 2023

BBC News

A video posted on the BBC news website profiles a non-speaker with autism who purportedly directed and starred in a short, autobiographical film. A brief clip of the person typing shows another person holding his upper arm as he slowly picks out letters with his index finger. The film’s voiceover, in a statement attributed to the letter-selector, states that he was desperate to move on from Teletubbies to books written for people his age. The voice adds, in words that echo other FC-generated messages, including the statements attributed to Naoki Higashida in The Reason I Jump (see here), that nonverbal people are “deep thinkers” and “people watchers” who “sense the world in deeper ways than those who talk.” But they also, the voice adds, have “the same dreams as everyone else.”

The same non-speaker is also featured, around the two-minute mark, in this earlier BBC news segment.

No mention of the complete lack of evidence base for FC or of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

October, 2023

Channel 19 in Cleveland

A brief report about a “new tool” called S2C that “gives people with motor challenges the skills they need to be able to point to letters to spell words.” The hosts, together with a local S2C practitioner, mostly recite the main talking points of S2C proponents. The report closes with information about the local S2C clinic, AccessS2C.com, with one host emphatically asserting that its mission is “to support every speller’s human right to communication and self-advocacy.” Cleveland 19 provides a link with more information and testimonials.

No mention of the complete lack of evidence base for S2C or of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

September, 2023

San Francisco Public Radio

An article on KQED’s California Report Magazine reports on a non-speaking 19-year-old who has purportedly learned to slowly type out messages with his index finger using some unspecified method (in the picture, the device is held up, RPM/S2C-style). The article reports that people assumed that the boy’s IQ was low because “he didn’t have the motor skills to point to the right answers in school.” While the article acknowledges the controversy surrounding FC, it lets Dr. Margaret Bauman, one of the boy’s neurologists, have the last word on both Jacob’s purportedly high intelligence and the purported independence of his typing. (Bauman has a history of defending FC.)

No mention of the complete lack of evidence base for RPM/S2C or of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

Good Morning America

A segment in which Juju Chang interviews Angie Kim about Kim’s pro-S2C book Happiness Falls and visits Kim at Elizabeth Vosseller’s S2C clinic. Here, Chang reports in a tone of awe, as clips play of Vosseller’s clients pointing to letters on held-up letterboards, how “We watched as trained practitioners sat with students to spell their thoughts on their own, letter by painstaking letter.” The closest Chang comes to acknowledging the lack of empirical support for S2C is to call it “unique yet controversial.”

No mention of the complete lack of evidence base for S2C or of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

September, 2023

The Irish Times

An opinion piece by a mother on how she unlocked her son through S2C.

No mention of the complete lack of evidence base for S2C or of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

July, 2023

Good Morning America

A GMA  YouTube video features S2C user Gabe purportedly sharing his thoughts about his friendship with a speaking autistic teenager like Ariel. Clips of him using S2C start at around 1:30.

No mention of the complete lack of evidence base for S2C or of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

Time Magazine

An article on autism research priorities is attributed to a non-speaking autistic individual of whom there is no public record of independent typing; only videos of pre-recorded messages or of slow typing with someone sitting or standing within cueing range.

No mention of any attempt to validate the surprising notion that the article was actually authored by the non-speaking autistic person credited with writing it—someone who, by virtue of his diagnosis, is highly unlikely to have the language and literacy skills the article exemplifies.

KJRH TV in Tulsa

A segment entitled “Spelling to Communicate allows Tulsa teen to speak for the first time” features the teen, his mother, and the speech-language pathologist who directs the local S2C clinic and introduced S2C to him. Reporter Naomi Keitt states that the boy, Jake, “has autism and apraxia which is a motor condition that makes it difficult for Jake to gain control of his body.” She also reports that Jake recently presented at the Eastern Oklahoma Autism Conference, earns straight As, and hopes to study neuropsychology at the University of Oklahoma. As the segment closes, one of the news anchors adds “That is very impressive” and the other responds “That is incredible, how they can finally communicate.”

No mention of the complete lack of evidence base for S2C or these claims about apraxia, or of any of the many health, education, and advocacy groups that have expressed serious concerns about S2C.

May, 2023

Nature

A story in Nature entitled ‘I am not a broken version of normal’— autistic people argue for a stronger voice in research, which we blogged about here, attributes sophisticated commentary about research priorities from two non-speaking individuals whose verbal communications are known to be extracted via the prompting and held-up letterboards/keyboards that characterize RPM and S2C.

No mention of any attempt to validate the crucial question of whether these commentaries were actually authored by the non-speaking autistic individuals credited with making them—individuals who, by virtue of their diagnoses, are highly unlikely to have the language and literacy skills the article exemplifies, and whose messages are generated by methodologies known to be susceptible to facilitator control.

April, 2023

Fox 17 News, Western Michigan

A local news station reports on the S2C movie Spellers (see our review here).

No mention of the complete lack of evidence base for S2C or of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

CityLifestyle.com, a Leesburg Virginia publication

A report of a Leesburg Virginia publication of an RPM user (one of 16 runners-up in the 2021 New York Times Middle School Essay Contest).

No mention of the complete lack of evidence base for RPM or of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

February, 2023

USA Today

A story on the problem of “elopement” in autism works in a plug for S2C “inventor” Elizabeth Vosseller. Journalist Cybele Mayes-Osterman states that Vosseller’s therapy center “is dedicated to teaching individuals who are nonverbal how to communicate through spelling.” She then cites one of the messages purportedly generated by one of Vosseller’s nonspeaking clients, which recites the FC-friendly myth that autism is primarily a sensorimotor disorder: "We aren’t in control when it happens, our bodies just take off. It often happens for me when my sensory system is overstimulated. My body just needs to get out of there even if my mind wants to stay."

No mention of the complete lack of evidence base for S2C or of the authenticity of the messages generated through it that are cited here, nor of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

January, 2023

WBIR, local TV station in Knoxville, Tennessee

A WBIR news segment showcases a non-speaking autistic boy who types via a held-up keyboard and started a nonprofit called The Peyton Project to help non-speakers like him “find their voice.” Now a teenager, the reporter tells us, Peyton “spells out his hopes for others.” After Peyton’s mother states, “There are so many out there living in silence,” the narrator adds “So many people who are living in… [here the computer-generated word “silence” is spliced in, along with a clip of Peyton typing] just like Peyton was, all those years.” The report concludes with a brief plug for the Peyton Project.

No mention of any attempt to check in with any autism experts about any of these rather surprising claims about non-speaking autism or about the rather surprising achievements of someone with such a diagnosis.

December 24th, 2022

The New York Post                                                                                                          

A piece by Lenore Skenazy, which Janyce critiqued here, accepts S2C and RPM as valid and repeats proponents’ talking points.

No mention of the complete lack of evidence base for RPM/S2C or of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

November 23rd, 2022

Fox 17 News, Nashville.

A news segment on a boy who purportedly communicates by typing (the video shows him typing on a held-up letterboard) and wants to study nanobiology and calculus rather than the “circles and squares and double-digit addition” that his mom says he was stuck in for “years and years and years.” Reporter Kaitlin Miller explains that the Metro Nashville Public Schools at first wouldn’t allow the held-up letterboard to be used in the screening process that determines which classes the student could take, but that after a hearing before the Tennessee Department of Education, this decision was overturned. Miller, apparently convinced this was the right decision, says that she requested an interview with Nashville Schools “to see what they’re going to do to prevent this from happening to other students.” But, Miller states, they “declined the interview request claiming they can’t go into specifics about a student due to state and federal student privacy protections.”

No mention of any attempt to check in with any autism experts about any of these rather surprising achievements by someone with non-speaking autism.

June, 2022

Spectrum Life

Starting with this article, and subsequently with this one, Spectrum Life, an autism-focused online magazine, has been reporting on the virtues of S2C.

No mention of the complete lack of evidence base for S2C or of any of the many health, education, and advocacy groups that have expressed serious concerns about it.

May, 2022

ABC News 7, Bay Area

A news segment reported uncritically on two non-speaking individuals who graduated from Berkeley. Senior Education reporter Lyanne Melendez says she sat down with one of these individuals and his mother and watched him type. “Without looking at the keyboard he taps one letter at a time,” she reports, apparently producing the message that “I want people to know that we can achieve a lot if we are able to participate.”

No skepticism expressed about whether anyone can actually type such a message, one letter at a time, without looking at the keyboard.