{"id":"W2612705982","doi":"10.1007/s10664-017-9522-4","title":"Identifying self-admitted technical debt in open source projects using text mining","year":2017,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; Concordia University","funders":"Ministry of Science and Technology of the People's Republic of China; National Natural Science Foundation of China","keywords":"Technical debt; Computer science; Classifier (UML); Source code; Code review; Baseline (sea); Open source; Artificial intelligence; F1 score; Machine learning; Data mining; Natural language processing; Software; Software quality; Software development; 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":[0.003472366,0.0002633455,0.0003017028,0.006880254,0.000713843,0.001612203,0.0006649135,0.0009612949,0.001028692],"category_scores_gemma":[0.03971322,0.0001860112,0.0002806805,0.005615596,0.0003953213,0.002152466,0.001209338,0.0008259373,0.0005037529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005527096,"about_ca_system_score_gemma":0.0009208096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002375167,"about_ca_topic_score_gemma":0.004420753,"domain_scores_codex":[0.9970227,0.0006521685,0.0007276429,0.0004413209,0.0009093334,0.0002468158],"domain_scores_gemma":[0.9268764,0.03881427,0.02241508,0.002453806,0.007328088,0.002112351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001217976,0.0002080632,0.9606634,0.0001171363,0.00004186226,0.0003068089,0.001163281,0.0003719807,0.001937413,0.00049448,0.001406313,0.03316738],"study_design_scores_gemma":[0.0000142338,0.0001104508,0.9747272,0.0001559473,0.00005643192,0.0005643507,0.003298108,0.01267895,0.002632536,0.002212856,0.00351812,0.00003095637],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961922,0.0001392468,0.001305394,0.0001654391,0.00001214956,0.00002408645,0.00116835,0.00003299533,0.0009601532],"genre_scores_gemma":[0.9939329,0.0001288401,0.002197773,0.00004973359,0.00003499869,0.00004894513,0.002823114,0.00001670825,0.0007670712],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006880254,"threshold_uncertainty_score":0.01836389,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07815053665037296,"score_gpt":0.3568263279761991,"score_spread":0.2786757913258261,"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."}}