The one rule: no stance is not neutral
Every successful answer is read for its stance on your brand. The stance is one of three things, or nothing:
Neutral and No clear stance look alike and mean opposite things. “Ledgerly is one of several reasonable options” is a neutral verdict and counts. “Ledgerly starts at $12 per seat” names you and judges nothing; it is left out. Counting it as neutral would move your score whenever the mix of questions you track moved, which is not sentiment.
Not scored yet is different again: it is the absence of a reading, not a reading. A new answer is not scored yet until it has been read for its stance, which happens after it is stored, never while it is being sampled.
How it is calculated
Every sentiment number divides by scored answers: the answers with a stance. Never by answers read.null, shown as —, means no answer in the window took a position, and there is nothing to average.
Read the score beside its counts: the scored answers, the answers read, and the answers not scored yet. When the scored count is small, read it before the score. Five scored answers out of three hundred read is five opinions, not a verdict on your brand.
Where to read it
In the app, sentiment is the Scoreboard’s Sentiment view, at/scoreboard/sentiment. Open it from Sentiment beside the Scoreboard’s title, or type sentiment in Search. It switches between 7, 30 and 90 days like the board, and Questions takes you back.
The view shows, in order:
- The score with its sample: the scored answers, the answers read, and the answers not scored yet, and the window. When nothing in the window took a position, it says so and offers to draft or add prompts, rather than showing a score.
- The split: positive, neutral and negative as shares of the scored answers, and the change in the positive share against the window before, shown only when it is more than noise.
- By day: the daily positive share.
- By engine and by topic: each with its score, its positive and negative shares, and both counts. Pressing a row narrows the whole view to that engine or topic.
- Answers: the scored answers the score was read from, with Load more and Export as CSV (the rows on screen). An answer opens a drawer with the full answer, the scored sentence marked, a link to the question on the Scoreboard, and Fix, which hands the answer to the agent.
GET /v1/projects/{id}/analytics/sentiment with days, and model, label, topic, offset and limit for the cut and the answer page. When your plan does not include analytics, the view says so with See plans.
Outside the view, the stance on you is also read answer by answer: in a question’s detail on the Scoreboard, in the brand order of every answer, and over MCP and the REST API (below).
Per-brand stance in the brand order
Each answer’s brand order lists every brand it names. Each brand in it carries its own stance under the same rule: a brand the answer names without judging has no stance, not a neutral one. In a question’s detail, your own entry in the brand order shows the answer’s stance on you: Positive, Neutral, Negative, or No clear stance. A competitor’s entry shows a dash with “not scored yet”: competitors are not scored. Over MCP and the REST API,answer_history and answer_slice rows carry the stance on you as stance (positive, neutral, negative, none or unscored), and the brand order as brands, where each brand has its own stance_label and stance_score. A brand with no stance has no stance_label and a stance_score of null. A stance_score of 0 is a balanced verdict.
Filtering answers by sentiment
answer_slice takes a sentiment term over your brand’s stance. It keeps the same distinction:
positive,neutralornegative: answers with that stance;none: answers that were scored and took no stance;unscored: answers nobody has scored yet.
none and unscored are never folded into neutral, or into each other. See MCP tools.