{"id":"W3194665160","doi":"10.18637/jss.v099.i02","title":"The R Package sentometrics to Compute, Aggregate, and Predict with Textual Sentiment","year":2021,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institut de Valorisation des Données; Innoviris; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"R package; Computer science; Aggregate (composite); Indexation; Sentiment analysis; Workflow; Index (typography); Volatility (finance); Series (stratigraphy); Information retrieval; Econometrics; Natural language processing; Mathematics; World Wide Web; Database; Programming language; Economics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00110605,0.00008664134,0.0002196519,0.00009270222,0.0005012577,0.000252784,0.0001513039,0.00003243086,0.00009184972],"category_scores_gemma":[0.002493791,0.00005308473,0.00005484381,0.0008837108,0.0002144434,0.00009202225,0.00007322339,0.0001724496,0.000006386404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006563176,"about_ca_system_score_gemma":0.0002886017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004925055,"about_ca_topic_score_gemma":0.0001658341,"domain_scores_codex":[0.9981265,0.0002879419,0.0003286307,0.00013439,0.0008974347,0.0002251173],"domain_scores_gemma":[0.9950793,0.003612903,0.0001723116,0.00007689303,0.000702607,0.0003559786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00020928,0.0003088526,0.03624225,0.00003248741,0.0004950528,0.001027982,0.003020219,0.0005181176,0.00003436216,0.08286735,0.02618069,0.8490633],"study_design_scores_gemma":[0.002781057,0.001506102,0.3451328,0.0003764574,0.0007443082,0.0004890179,0.01012514,0.0009894442,0.0002326279,0.0720166,0.5648035,0.0008029312],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01996706,0.0006574104,0.9753965,0.003137889,0.0001664431,0.00007648762,0.00003595183,0.00001449757,0.0005477208],"genre_scores_gemma":[0.4031909,0.0004291772,0.5935204,0.0007842412,0.0006025687,0.000003207941,0.000009824729,0.00001753731,0.001442174],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8482604,"threshold_uncertainty_score":0.385532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01761164827682454,"score_gpt":0.3292169960357477,"score_spread":0.3116053477589231,"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."}}