Contribution to the handbook
Supporting · Assessed 2026-10-27
The text-embedding and question-specific position axis are useful context for interpreting claims about majority and minority representation. The reported check against participant ratings and the alternative measurement choices qualify the findings, but this method description alone does not specify a governance design.
Does this challenge the goal?
In-scope gap
Understanding how statement positions were measured helps assess evidence about representation within the existing goal; the question does not contest that goal or its beneficiary boundary.
The evidence describes one measurement method and acknowledges alternatives; it does not establish that the measure captures every relevant meaning or fairness concern.
Why this category?
- measurement background
- limits of evidence
The article-derived records share a source root. Correlation with participant ratings supports the method’s relevance but does not show that it captures all nuance or transfers to other populations and issues.
This is an AI assessment of contribution to the goal, separate from whether the question has an answer.
Tests, stop conditions and unresolved work →
Authority, accountability and resilience →
Read the exploration goalNew evidence is being assessed. Any answer below is provisional; parts whose evidence changed or was withdrawn are withheld.
Describe the text representations, the question-specific axis defined by affirming and negating statements, and how a statement’s position was measured on it.
What we can say so far
The authors used Sentence T5 to turn opinions, group statements, and question-specific affirming and negating position statements into numerical text representations. For each question, they defined the position axis as the line between the representations of the affirming and negating statements. A statement’s position was measured by where its representation fell along that axis.
What remains open
No material gap is recorded within this part’s current scope.
Conditions and limits
- The account is based on the readable article text; supplementary materials were not included.
- Other text models or axis definitions could yield different measurements.
- The reported comparison with earlier ratings was correlated but not exact, and does not establish that the scores capture every nuance of written opinions.
Objections to consider
- The imperfect rating correspondence and inability to capture every nuance qualify claims about interpretive validity, but do not prevent describing the operational measurement procedure.
Evidence and related ideas
Supporting evidence, qualifications and context play different roles in this answer.
supports
Measuring text positions The authors used Sentence T5 to create numerical representations of opinions, group statements, and affirming and negating position statements for each question. They defined the question’s position axis as the line between the negating and affirming statements’ representations, then measured where opinions and group statements fell along that axis.
Directly supplies the Sentence T5 representations, affirming-to-negating axis construction, and placement of opinions and group statements.
AI can help humans find common ground in democratic deliberation
Read full source: AI can help humans find common ground in democratic deliberation (opens in a new tab) ↗Read source discussion: AI can help humans find common ground in democratic deliberation →
qualifies