{"id":"W3090131812","doi":"10.18653/v1/2023.nllp-1.10","title":"Beyond The Text: Analysis of Privacy Statements through Syntactic and Semantic Role Labeling","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Privacy, Security, and Data Protection","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Task (project management); Domain (mathematical analysis); Recall; Natural language processing; Privacy policy; F1 score; Precision and recall; Information privacy; Information retrieval; Artificial intelligence; Internet privacy; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001660775,0.0001824218,0.0004206263,0.0002242521,0.0005784553,0.0002487461,0.0008519914,0.0002023689,0.0001762543],"category_scores_gemma":[0.0009413356,0.0001386402,0.0001518089,0.0009582248,0.0002296239,0.0003865919,0.002168826,0.0003854377,0.00002272631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008817539,"about_ca_system_score_gemma":0.0001679856,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07264471,"about_ca_topic_score_gemma":0.01536176,"domain_scores_codex":[0.9977947,0.0003622152,0.0004351668,0.0004907783,0.0006109865,0.0003061296],"domain_scores_gemma":[0.9983261,0.0003361865,0.0003596061,0.0007837168,0.000131795,0.0000626171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001925653,0.001117369,0.1583174,0.002383612,0.02535996,0.00003219321,0.6381702,0.002670175,0.00152268,0.1283111,0.009753534,0.03216917],"study_design_scores_gemma":[0.0005230082,0.00007738118,0.03207188,0.0002388004,0.007008887,6.916349e-7,0.06457628,0.01160071,0.0006282515,0.8718255,0.01048911,0.0009594825],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9341077,0.002893863,0.01585292,0.01458265,0.002153,0.003150305,0.0005581487,0.0006197217,0.0260817],"genre_scores_gemma":[0.9949741,0.003174225,0.0008269105,0.0001215813,0.0001190568,0.00004776251,0.0001056952,0.00001684439,0.0006137848],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7435144,"threshold_uncertainty_score":0.9335306,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05657710456648832,"score_gpt":0.3766990392892843,"score_spread":0.320121934722796,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}