Word cloud questions
How InviziPoll's word cloud question works: the 50-character cap, tokens counted by distinct respondent, what the results panel and its two CSV downloads contain, and how to word the prompt.
On this page
A word cloud is the safest free-text question InviziPoll has, and it is still free text. The 50-character cap does most of the protecting; the wording of your prompt does the rest.
A word cloud question asks for a word or a short phrase: "One word for how this quarter felt." Every answer is encrypted in the respondent's browser like any other answer, and the results panel shows the words people used, sized by how many people used them.
What a respondent sees
A single-line box capped at 50 characters, with a privacy note above it that asks them to keep the answer short and to avoid details that would identify them — their team name, their role, a specific project.
The cap is the point. There is no room in fifty characters for the account of a specific incident, which is exactly the kind of answer that becomes identifying no matter how well it is encrypted. If you want that account, ask for it with an open text question and accept the different risk profile that comes with it.
Setting one up
Add a question in the poll wizard and pick Word cloud. Two fields matter:
- The prompt, up to 200 characters. Ask for one thing. "One word for how this quarter felt" returns usable words; "How do you feel about the quarter?" returns sentences that get truncated.
- The character limit, anywhere from 1 to 50, defaulting to 50. Lowering it to 20 or so is a reasonable way to force single words if that is what you want to chart.
How the counts work
Each answer is split into words. Punctuation at the edges is trimmed, inner apostrophes are kept, and everything is lower-cased, so Tired. and tired are the same token.
Within one answer a repeated word counts once. Someone who writes tired, tired, tired contributes a single tired. The number beside a token is how many different people used it, not how many times it appeared — which is why a token's count can never exceed the number of people who answered.
Reading the results
Once the poll clears its anonymity threshold and you unlock results, the panel shows three things:
- The cloud itself — the top 60 tokens, sized and shaded by count.
- All tokens, listed in full underneath with their counts, in a scrollable list.
- Two downloads: a token CSV, and the raw answers in shuffled order.
The token CSV has one row per distinct token with its count and its share of respondents. The raw download has one row per answer, shuffled, so an answer's position in the file says nothing about when it was submitted.
An on-device summary of the words
Once at least five people have answered, the panel offers a short AI draft describing the answers: not the tokens the chart already shows, but what the words add up to. It is written by a small model running inside your own browser tab, on answers your browser has already decrypted, and nothing about it reaches our servers or any AI provider. The full account of what is downloaded and what never leaves the tab is in on-device AI summaries.
Two things are worth knowing before you use one on a word cloud specifically. A fifty-character answer is short enough that a distinctive one can be paraphrased closely, so read a draft as a pointer back to the answers rather than as a neutral aggregate. And the draft is a draft: it is labelled as one, it is not stored, and it never appears on a public results link or in a shared snapshot.
A word only one person used still appears
This is the honest difference between a word cloud and an open text question, and it is worth knowing before you write the prompt.
Open text suppresses a theme until at least two different respondents have used it, because one person's vocabulary is not a theme. A word cloud does not: after the poll clears its threshold, the full token list includes tokens with a count of one. That is deliberate — the aggregate is the answer, and dropping the long tail would give you a chart that quietly disagrees with the responses behind it.
It does mean an unusual word is visible as an unusual word. Nothing attaches it to a person, and nothing on any surface pairs two tokens back to the same answer, but a distinctive turn of phrase in a team of nine is still a distinctive turn of phrase. Set the expectation in the prompt, keep word clouds out of the questions where someone would want to explain themselves, and use a higher unlock threshold when the group is small.
What a public results link includes
If you turn on a public results link, the word cloud goes with it: the cloud, the token list, and both downloads, including the shuffled raw answers.
That is a real difference from open text, whose verbatims never leave the signed-in results view. A word cloud answer is a token by construction — capped at fifty characters, stripped of order, and detached from every other answer in the same response — so it is publishable in a way a paragraph is not. Decide it at the poll level: if you would not be comfortable with the raw fifty-character answers on a forwardable URL, do not turn the public link on for that poll.
Word cloud vs. open text
| Word cloud | Open text | |
|---|---|---|
| Length | Up to 50 characters | 200–5,000 characters |
| Counted by | Distinct respondents | Distinct respondents |
| Single-use entries | Shown | Suppressed |
| On a public link | Yes | Never |