{"id":"W2524791359","doi":"10.1007/s11192-016-2134-8","title":"The linguistic patterns and rhetorical structure of citation context: an approach using n-grams","year":2016,"lang":"en","type":"article","venue":"Scientometrics","topic":"Topic Modeling","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Rhetorical question; Citation; Linguistics; Context (archaeology); Computer science; Linguistic context; Function (biology); Natural (archaeology); Natural language processing; Information retrieval; Linguistic analysis; History; Library science; Philosophy; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.006477996,0.0009318867,0.001268398,0.02799213,0.001981051,0.005871946,0.001271942,0.001752348,0.002325241],"category_scores_gemma":[0.03952212,0.0006491996,0.001256944,0.02988831,0.001396645,0.007938967,0.001941749,0.001572229,0.0009922113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001503273,"about_ca_system_score_gemma":0.002179258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003321151,"about_ca_topic_score_gemma":0.006483546,"domain_scores_codex":[0.9944656,0.002926996,0.0005187229,0.0007337331,0.001192353,0.0001624626],"domain_scores_gemma":[0.958456,0.03586601,0.002358836,0.001162005,0.001816793,0.0003404065],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009291704,0.0008804746,0.1130062,0.002602612,0.001298973,0.0008255044,0.01236787,0.02367574,0.01941712,0.1618395,0.01099059,0.6521662],"study_design_scores_gemma":[0.0001102282,0.0002922655,0.0575523,0.0007052216,0.001102768,0.0007625041,0.005131536,0.5478707,0.008416861,0.341279,0.03653565,0.0002410021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3768719,0.006962447,0.5785939,0.002685486,0.0003745612,0.000745774,0.007578831,0.002465422,0.02372165],"genre_scores_gemma":[0.8318157,0.001683608,0.1594008,0.0001414442,0.0004063968,0.0006201293,0.002922942,0.0003184156,0.002690617],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.993522,"threshold_uncertainty_score":0.03425932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08286568018633636,"score_gpt":0.3170019493522849,"score_spread":0.2341362691659486,"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."}}