{"id":"W2579161546","doi":"10.1109/tse.2017.2654244","title":"Using Natural Language Processing to Automatically Detect Self-Admitted Technical Debt","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":220,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Technical debt; Computer science; Debt; Quality (philosophy); Bad debt; Code (set theory); Finance; Software development; Business; Software; Programming language; Set (abstract data type)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003361088,0.001123525,0.0005177744,0.005592857,0.0006546698,0.001574574,0.001479048,0.001384535,0.00100284],"category_scores_gemma":[0.0233499,0.0005565571,0.000801995,0.002863269,0.0007379453,0.003324194,0.001387197,0.001602164,0.001020811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001133193,"about_ca_system_score_gemma":0.002301734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005790713,"about_ca_topic_score_gemma":0.00781743,"domain_scores_codex":[0.9954224,0.001212315,0.0006210185,0.000962073,0.00162461,0.0001576057],"domain_scores_gemma":[0.9529563,0.02899267,0.008670548,0.002315792,0.006552402,0.0005124075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009374428,0.001053197,0.1137413,0.004000246,0.0002102265,0.005476706,0.006697209,0.01457861,0.1603326,0.006939049,0.05151874,0.6345147],"study_design_scores_gemma":[0.0002509175,0.0006134757,0.08801452,0.0005486549,0.0002302011,0.003605772,0.004133665,0.7361432,0.07241608,0.03161733,0.06215944,0.0002667405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5426903,0.001194838,0.3868244,0.002646013,0.000270334,0.0009741845,0.01626451,0.04292936,0.006205924],"genre_scores_gemma":[0.5115628,0.0004884229,0.4453931,0.000763437,0.0001462972,0.0008269796,0.03655289,0.0009254484,0.003340679],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.005790713,"threshold_uncertainty_score":0.01777536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01647430844027475,"score_gpt":0.2907908957815483,"score_spread":0.2743165873412735,"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."}}