{"id":"W2951232267","doi":"10.48550/arxiv.1211.6321","title":"Citation content analysis (cca): A framework for syntactic and semantic analysis of citation content","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Joint Information Systems Committee; National Science Foundation","keywords":"Citation; Computer science; Scope (computer science); Content analysis; Semantic analysis (machine learning); Citation analysis; Content (measure theory); Context (archaeology); Information retrieval; Ranking (information retrieval); Data science; World Wide Web; Sociology; Social science; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.03428156,0.002767688,0.002834307,0.06957211,0.006438944,0.01780833,0.004355867,0.003387717,0.006499961],"category_scores_gemma":[0.1024036,0.001063779,0.003885373,0.0552153,0.009635637,0.02199585,0.007360207,0.004185991,0.003111575],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007076063,"about_ca_system_score_gemma":0.01203301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005983012,"about_ca_topic_score_gemma":0.003638959,"domain_scores_codex":[0.9574661,0.02298438,0.004211924,0.004000421,0.01056342,0.0007737345],"domain_scores_gemma":[0.8818156,0.08362842,0.008143491,0.01122583,0.0140323,0.001154417],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004821836,0.00005042804,0.002645728,0.00167868,0.0003324847,0.0001849367,0.005957067,0.003034991,0.001975473,0.8057012,0.01040549,0.1679854],"study_design_scores_gemma":[0.00002919779,0.00004505402,0.002750319,0.0009202361,0.0002363884,0.0004226067,0.002095293,0.01866911,0.003121577,0.8412643,0.1302162,0.0002298197],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003615537,0.003019493,0.9759346,0.00184215,0.0003841988,0.0007789592,0.00195181,0.001631401,0.01084178],"genre_scores_gemma":[0.08481459,0.003265646,0.9000776,0.0004603959,0.001154267,0.003051228,0.002864352,0.001030037,0.003281899],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9657184,"threshold_uncertainty_score":0.1813004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1788789219699019,"score_gpt":0.2557730388244376,"score_spread":0.07689411685453576,"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."}}