{"id":"W2895553377","doi":"10.21105/joss.00774","title":"quanteda: An R package for the quantitative analysis of textual data","year":2018,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1323,"is_retracted":false,"has_abstract":true,"ca_institutions":"De Beers (Canada)","funders":"London School of Economics and Political Science","keywords":"R package; Computer science; Natural language processing; Information retrieval; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.006707033,0.002441942,0.002382296,0.004722014,0.0008669276,0.004059064,0.00294895,0.0008442505,0.07443252],"category_scores_gemma":[0.06362126,0.001460198,0.002594867,0.004280706,0.001017138,0.002820018,0.003058546,0.002848078,0.04489454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007382481,"about_ca_system_score_gemma":0.003106107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002930819,"about_ca_topic_score_gemma":0.004392474,"domain_scores_codex":[0.9946527,0.002297923,0.0005183062,0.001132652,0.001216435,0.0001819919],"domain_scores_gemma":[0.9680011,0.02364318,0.002284335,0.003285485,0.002339555,0.000446265],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007693812,0.0001001968,0.01101151,0.007867895,0.003391676,0.0005506496,0.0008980616,0.008467674,0.006437853,0.01884106,0.8058477,0.1358163],"study_design_scores_gemma":[0.0004562131,0.0001991877,0.01804657,0.000929651,0.001225604,0.001050459,0.0003217137,0.04899456,0.009679314,0.08912782,0.8295979,0.0003709803],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.005810041,0.001439445,0.4754369,0.001159322,0.0006601073,0.0007521333,0.3189017,0.188569,0.007271363],"genre_scores_gemma":[0.04798994,0.001318781,0.614308,0.00140266,0.0004191116,0.006595136,0.1711677,0.1455392,0.01125947],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.07443252,"threshold_uncertainty_score":0.2490016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1220943930715411,"score_gpt":0.4211929597768534,"score_spread":0.2990985667053123,"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."}}