What human rating criteria does HANNA use for story quality and how consistent are raters?

HANNA defines six human criteria (relevance, coherence, empathy, surprise, engagement, complexity) on a 5-point Likert scale and annotates 1,056 stories from 96 WritingPrompts prompts (human story plus 10 systems) with 3 MTurk raters each. Averaged-rater reliability (ICC2k) is only fair to moderate (0.28-0.56), the criteria are weakly to moderately intercorrelated (Kendall 16%-62%, mean 40.7%), and human stories scored highest on every criterion. Curator qualifications: Table 3 (pdftotext order): LB RE 0.18, CH 0.10, EM 0.25, SU 0.16, EG 0.34, CX 0.48; ICC2k 0.48, 0.29, 0.34, 0.28, 0.46, 0.56; UB 0.65, 0.48, 0.41, 0.37, 0.55, 0.63. 'ICC2k coefficient (ICC for average random raters) is the most relevant one'. '1,056' 5 hits. Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.

{
  "citations": [
    {
      "url": "https://arxiv.org/abs/2208.11646v4",
      "note": "HANNA arXiv 2208.11646v4 PDF, Table 3"
    }
  ]
}