Back to blog
Product Updates 3 min read
New · Issue-level sentiment analysis

Your community tells you everything. Now you can hear all of it.

Until now, feedback tools gave each response one sentiment score and called anything complicated mixed. Communiti now reads every submission the way your best analyst does: every issue, its own sentiment, and the resident's exact words - filed straight into your dashboard topics, in more than 50 languages.

One response, two real issues

One real-style response What Communiti reads

"I really love the train service, but I hate how terrible the bus delays are getting!"

Train service positive Trains & Ferries Bus delays negative Buses

Every other tool we tested scores this whole response as mixed, and the trains and buses both disappear.

At a glance

Three ways to analyse the same response

Take that one sentence about trains and buses, multiply it by five thousand responses, and here is what each approach actually gives you.

Comparison of manual review, standard sentiment platforms, and Communiti Intelligence for issue-level feedback analysis.
Capability Reading it yourself Analyst + spreadsheet Existing platforms Standard sentiment tooling Communiti Intelligence New - issue-level analysis
What this response becomes Complete

Both points noted - when there's time to read every row closely

Collapsed

One label for the whole response: "MIXED". Trains and buses both vanish

Complete

Trains · positive and Bus delays · negative, with the resident's words highlighted

Issues residents imply but never name Caught

A good reader sees "twenty minutes on hold" for what it is

Missed

Found about 1 in 100 in our testing - there's no named "thing" to tag

Caught

Found 9 in 10, scored and filed like any other issue

Feedback in community languages Sometimes

Only the languages your team happens to read - unless you pay for a translation service

English only

Issue-level analysis supports no other languages

50+ languages

10 benchmarked natively, including mid-sentence switching - nothing skipped

Filing issues under your report topics By hand

Every issue copied and categorised manually - and each reader files differently

Not available

No concept of your project's topics

Automatic

Filed into your topics as it reads - rename or merge topics any time

Evidence behind every finding By hand

Quotes pasted into the report, hours of copy-and-paste

Not linked

A score, and at best keyword tags - the words aren't tied to the sentiment or your topics

Built in

Every issue links to the exact words in the original response

5,000 responses Weeks

And consistency drifts as readers tire

Hours

Fast - but you get one shallow score per response

Under 3 hours

Your best analyst's read, at machine speed, the same rules on row 1 and row 5,000

What this looks like in action

Watch feedback become understanding

Below, responses from our published test set arrive exactly as residents wrote them - different languages, different styles, half-finished sentences. Watch each one get read, separated into issues, and filed onto the dashboard. Then see what opening one topic gives you.

Incoming feedback Analysing

Survey export · English

"Love the weekend markets, but the lack of toilets there is a disgrace."

Weekend markets Parks & playgrounds Public toilets Parks & playgrounds

Buses

0 issues

Swimming pools

0 issues

Car parking

0 issues

Parks & playgrounds

0 issues

Council services

0 issues

Community programs

0 issues

Issues file themselves under your project's topics as each response is read.

Buses

Topic opened - what your team sees

23
issues raised
78% negative
sentiment
4
languages
Delays & shelters
most-raised themes
"I hate how terrible the bus delays are getting!"
English · negative
"公交车总是晚点, but the new library hours are very helpful."
Mandarin · negative
"the buss never come on time an wen it do its full"
English · negative
"E lelei le polokalame mo tupulaga, but the bus shelter leaks when it rains."
Samoan · negative

Animated illustration using responses from our published benchmark corpus - every highlight, issue, and filing decision shown here is a real output from the evaluation runs.

Tested before we shipped it

Benchmarked on the messiest feedback we could write

We built a 217-response test set designed to break sentiment tools: typos, sarcasm, rambling voice transcripts, low-literacy writing, and ten languages. The full method and results are published alongside this page.

92%
of issues found, even in deliberately messy feedback
99%
sentiment accuracy on the issues it finds
100%
of mixed responses split into their real issues
10
community languages benchmarked natively, including Te Reo Māori and Samoan

Head to head № 1

The industry-standard tool misses what residents do not name

Most platforms and many in-house projects run on Amazon Comprehend. It tags things it can recognise. But residents rarely name things. They write, "Twenty minutes on hold just to ask why my rates notice changed." There is no customer service in that sentence, only the experience of it.

PDF Submission_041 - Draft Transport and Open Space Plan.pdf One of the 60 long submissions from the benchmark, read by both tools below
Reading

What Communiti reads

Issue-level analysis

I want to start by saying the new playground at Riverside Park has been wonderful for our family - my kids ask to go every weekend. But getting there is another story. We waited forty minutes for a bus the timetable said ran every fifteen, and when one finally arrived it drove straight past because it was already full.

My mother is in her late seventies and can't manage the walk from the closest stop - the footpath on Hartley Street has been lifted by tree roots for over a year. She has stopped coming with us. And the water pools right across the path near the underpass every time it rains - you need gumboots just to get through.

On the plan itself, I support the new cycleway and would use it to ride to work, but nothing in the document mentions lighting - walking back from the 6pm session it was pitch black by the carpark. Twenty minutes on hold when I rang to ask about session times didn't help either.

0 of 8 issues found

What Amazon Comprehend sees

Targeted sentiment, best setting

I want to start by saying the new playground at Riverside Park has been wonderful for our family - my kids ask to go every weekend. But getting there is another story. We waited forty minutes for a bus the timetable said ran every fifteen, and when one finally arrived it drove straight past because it was already full.

My mother is in her late seventies and can't manage the walk from the closest stop - the footpath on Hartley Street has been lifted by tree roots for over a year. She has stopped coming with us. And the water pools right across the path near the underpass every time it rains - you need gumboots just to get through.

On the plan itself, I support the new cycleway and would use it to ride to work, but nothing in the document mentions lighting - walking back from the 6pm session it was pitch black by the carpark. Twenty minutes on hold when I rang to ask about session times didn't help either.

0 of 8 found 0 missed

Comprehend's export for this submission contains 2 issues. The other 6 - the ones the resident implied but never named - never arrive in any report. The charts below score the same gap across all 60 submissions.

Issue detection score - long written submissions

60 multi-issue submissions, 700 issues to find, same scoring for both

Comprehend left 233 significant issues unreported across those 60 submissions. Communiti left none.

Issue detection score - issues implied, never named

96 responses like, water comes over the kerb every time it rains

This is most of what consultation feedback looks like, and it is structurally invisible to entity-tagging tools.

Head to head № 2

Feedback in 50+ languages - read, not skipped

Residents write the way they speak - sometimes switching language mid-sentence: "公交车总是晚点, but the new library hours are very helpful." Communiti reads the complaint about buses and the praise for the library. It supports more than 50 languages, and the ten below are the ones we benchmarked natively, end to end. Comprehend's issue-level analysis supports English only.

  • Mandarin 中文
  • Arabic العربية
  • Vietnamese Tiếng Việt
  • Cantonese 廣東話
  • Punjabi ਪੰਜਾਬੀ
  • Greek Ελληνικά
  • Italian Italiano
  • Hindi हिन्दी
  • Te Reo Māori
  • Samoan Gagana Sāmoa

These ten are the natively benchmarked set - 40+ more are supported via automatic translation. Industry-standard issue-level analysis: 0 of 10 supported.

Head to head № 3

Could we just paste it into an AI assistant?

Fair question. We tested it properly, including with the same AI model we use ourselves. Today's AI assistants read well. The difference is what arrives at the other end: a consultation dashboard needs every issue filed under your topics, with the resident's words attached, for every row in the spreadsheet, every time.

Share of issues that arrive in your dashboard, correctly filed

60 long submissions, found and filed under the right reporting topic

The assistant finds issues, then names its themes differently on every row - so almost nothing lands in your reporting structure without someone re-filing it by hand. That re-filing is the job Communiti does.

How it works

Nothing new to learn

1

Upload as usual

Spreadsheets, survey exports, documents, audio transcripts, photos of workshop sticky notes - exactly as you do today.

2

Every issue surfaces

Each response is read for every issue it raises, with its own sentiment and the resident's exact words highlighted.

3

Your dashboard fills itself

Issues are filed under your project's topics automatically, and you can rename or merge topics at any time.

For your IT and governance teams

Built for Australian data requirements

Processed in Australia

Analysis runs on AWS in Sydney and Melbourne using Australia-geographic AI infrastructure. Feedback is not processed offshore.

Never used to train AI

Your community's feedback is not used to train any AI model, and the model provider has no access to it - contractually guaranteed by AWS.

Evidence on request

The complete benchmark pack - test data, scoring code, raw outputs, and methodology notes - is available for technical review.

Every claim traceable

Each issue links to the exact words in the original response. Nothing is summarised beyond what a reviewer can verify in one click.

How we measured - the fine print we think you should read

  1. Test data. All benchmarks use synthetic feedback written for testing, with no resident data, spanning 473 responses across two test sets: a 217-response stress set and a 256-response set of long submissions, implied issues, and mixed-language responses. Headline accuracy figures of 92% and 99% come from the stress set.
  2. Comprehend comparison. Amazon Comprehend Targeted Sentiment was scored on its best-performing configuration, only on English content, with identical matching rules to ours. The comparison is about what each tool can see.
  3. AI-assistant comparison. The per-response test used a well-crafted prompt on the same AI model Communiti uses, plus a stronger model, so the gap shown is workflow and product, not model quality. Correctly filed means the issue was found and assigned to the project's reporting topic.
  4. Reproducibility. Every number on this page traces to a published results file, and the full evaluation suite re-runs end to end. Ask us for the benchmark pack.

Available now in Communiti

See your own consultation analysed this way

Bring one real, de-identified feedback export to a 30-minute walkthrough and watch every issue, in every language, land on your dashboard.

Want the numbers behind this release? Explore the full published benchmark - precision, recall, difficulty tiers, and methodology.

Stay close to the future of community engagement

Product notes, practical field guides, and evidence-led thinking for teams working under public scrutiny.

Read about ourWe care about your data in our privacy policy.

End-to-end engagement workflow