Why Creative Writing Gets Flagged as AI by Turnitin
Students in creative writing courses sometimes see high AI scores on work they wrote entirely themselves. Turnitin's documentation says the model only analyzes qualifying prose sentences, and one help article lists poetry and scripts as text types it does not reliably detect. Short documents are also prone to all-or-nothing predictions. Here is what the documentation actually says.
HumanPen Team
· 4 min read
The Short Answer
Creative writing can trigger false positives on Turnitin's AI detector for several reasons documented by Turnitin itself. The model analyzes what it calls "qualifying text," which includes only prose sentences written in standard grammatical sentences. One Turnitin help article says the model "does not reliably detect AI-generated text in the form of non-prose, such as poetry, scripts, or code." Short creative pieces face an additional problem: the FAQ says that in documents of a few hundred words, "the prediction will be mostly 'all or nothing' because we're predicting on a single segment without the opportunity to overlap." The FAQ also lists characteristics that produce false positives, including "content without a lot of structural variation" and "text that literally repeats itself." Creative writing that uses repetitive motifs or uniform sentence structures can match this profile even when fully human-written.
What Turnitin Counts in the Percentage
The FAQ defines what the model examines:
"This qualifying text includes only prose sentences, meaning that we only analyze blocks of text that are written in standard grammatical sentences and do not include other types of writing such as lists, bullet points (short non-sentence structures), or other non-sentence structures."
The next sentence: "This percentage is not necessarily the percentage of the entire submission."
One Turnitin help article provides a broader list of text types the model does not reliably detect:
"The model does not reliably detect AI-generated text in the form of non-prose, such as poetry, scripts, or code, nor does it detect short-form/unconventional writing such as bullet points, tables, or annotated bibliographies."
This is a text-content boundary, not a file-format boundary. Turnitin's current file requirements accept .docx, .pdf, .txt, and .rtf, but an accepted file can still mix qualifying long-form prose with poetry, script-style dialogue, or unconventional structures. One help article says those creative forms are not reliably detected; it does not say every such section is always excluded. The FAQ says text that is not considered long-form prose is not included, so the percentage may not represent the entire submission.
Why Short Pieces Get All-or-Nothing Scores
Creative writing assignments are often short. An eligible 500-word flash-fiction piece sits in the "few hundred words" range described by the FAQ. It says:
"In shorter documents where there are only a few hundred words, the prediction will be mostly 'all or nothing' because we're predicting on a single segment without the opportunity to overlap."
The next sentence: "This means that some text that is a mix of AI-generated and original content could be flagged as entirely AI-generated."
Turnitin's current file requirements draw a separate boundary: to generate an AI Writing Report and percentage, a submission must contain at least 300 words of prose text in a long-form writing format.
Below that floor, the submission does not meet the published requirements for an AI report or percentage. Once an eligible piece still contains only a few hundred words, the current FAQ says the prediction is mostly all-or-nothing and that mixed AI-generated and original text can be flagged as entirely AI-generated. Why Turnitin says your work is 100% AI traces that swing segment by segment.
False Positive Characteristics in Creative Writing
The FAQ lists text characteristics that tend to produce false positives:
"Sometimes false positives (incorrectly flagging human-written text as AI-generated), can include content without a lot of structural variation, text that literally repeats itself, or text that has been paraphrased without developing new ideas."
The next sentence: "If our indicator shows a higher amount of AI writing in such text, we advise you to take that into consideration when looking at the percentage indicated."
Several of these characteristics overlap with common creative writing techniques. A piece that uses deliberate repetition as a stylistic device can match "text that literally repeats itself." A piece with a consistent narrative voice and uniform sentence rhythm can match "content without a lot of structural variation." The official advice is to take the percentage "into consideration" rather than treating it as definitive. Single stylistic habits get read the same way, which is the question behind is the em dash an AI tell.
How the Model Works on Your Text
The detection model processes your text by splitting it into overlapping segments and assigning each a probability score:
"When a paper is submitted to Turnitin, sentences from the submission are extracted and segmented into overlapping sections for prediction analysis. Each segment is classified by the AI detection model and given a value between 0 and 1, denoting the probability of the text being likely human or AI-generated."
In a longer document, segments overlap, which means a single sentence can receive multiple scores that are pooled together. This pooling smooths out individual prediction errors. In a short creative piece, there may be only one segment with no overlap, which is why the prediction becomes all-or-nothing. What AI detectors measure beyond perplexity and burstiness covers what each segment is scored on.
What This Means for You
To summarize what we have covered:
- The percentage is based on qualifying long-form prose and is not necessarily a percentage of the entire submission.
- One Turnitin help article lists poetry, scripts, and annotated bibliographies as text types the model does not reliably detect.
- For eligible documents of only a few hundred words, Turnitin says the prediction will be mostly all-or-nothing because there is no overlap.
- Submissions with fewer than 300 words of qualifying long-form prose do not meet the current requirements for an AI report or percentage.
- The FAQ advises instructors to take the percentage "into consideration" when text has little structural variation or repeats itself.
- Creative writing techniques like deliberate repetition and consistent voice can match false-positive-prone characteristics.
If you receive a Turnitin report on a creative writing piece and want to address the flagged passages, import the report and work on them. Eligible passages can be re-run at no charge.
KEEP READING