{"id":"W4296511188","doi":"10.4995/carma2022.2022.15076","title":"Text mining methods for innovation studies: limits and future perspectives","year":2022,"lang":"en","type":"article","venue":"","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Word embedding; Word (group theory); Baseline (sea); Embedding; Information retrieval; Natural language processing; Ellipsis (linguistics); Turkish; Space (punctuation); Artificial intelligence; 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":[0.0008602491,0.00007200327,0.0001243229,0.0001428686,0.0004296154,0.00006159704,0.0002052856,0.00001869375,0.000005301676],"category_scores_gemma":[0.00009581824,0.00005975265,0.00002053349,0.0006126271,0.00001577284,0.0001558022,0.0001723424,0.00005956506,4.492386e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005416679,"about_ca_system_score_gemma":0.00002304538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003858489,"about_ca_topic_score_gemma":8.726412e-7,"domain_scores_codex":[0.9992495,0.0001109721,0.0001404677,0.0002794598,0.0000955794,0.0001240776],"domain_scores_gemma":[0.9993507,0.0002818491,0.0000644276,0.0001656441,0.000121461,0.00001590595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006037089,0.00003040542,0.0001434622,0.00002525137,0.00006277081,9.310821e-7,0.116884,0.00001073975,0.003193738,0.6235626,0.01214783,0.2439322],"study_design_scores_gemma":[0.0008445434,0.0006811899,0.0005390638,0.00001902393,0.000009578213,0.00005478906,0.4358087,0.05678869,0.002196663,0.005050074,0.4975615,0.0004461364],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0308506,0.008745242,0.9433029,0.01067494,0.001830597,0.0003717661,0.000001950826,0.0002489118,0.00397314],"genre_scores_gemma":[0.1749642,0.00006513003,0.8202721,0.0006088809,0.0004587766,0.0002322247,0.000001380443,0.00001003099,0.003387197],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6185126,"threshold_uncertainty_score":0.3304298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08451033897803484,"score_gpt":0.4080580015405287,"score_spread":0.3235476625624938,"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."}}