{"id":"W3033366604","doi":"10.1007/s10489-020-01760-x","title":"Is position important? deep multi-task learning for aspect-based sentiment analysis","year":2020,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sentiment analysis; Autoencoder; Artificial intelligence; Intuition; Position (finance); Benchmark (surveying); Deep learning; Task (project management); Machine learning; Natural language processing","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":[0.001141275,0.0006682356,0.0005363592,0.0005987142,0.0004727463,0.00133881,0.0007176425,0.0008612202,0.002633434],"category_scores_gemma":[0.004747292,0.0002319408,0.0004288057,0.0007972931,0.0003228893,0.002624135,0.00089185,0.001584967,0.001351938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005245988,"about_ca_system_score_gemma":0.0005714191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002675013,"about_ca_topic_score_gemma":0.004135902,"domain_scores_codex":[0.9995375,0.000138277,0.00002756579,0.0001220523,0.00007126455,0.0001034976],"domain_scores_gemma":[0.9987601,0.0005947964,0.0001728596,0.00009346713,0.0002798336,0.00009898578],"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":[0.001268308,0.0005924024,0.02671106,0.0003676611,0.0002159934,0.0003084491,0.0006303999,0.02908131,0.03721141,0.01288266,0.06014289,0.8305875],"study_design_scores_gemma":[0.00004035985,0.00009809561,0.00580164,0.00004904488,0.00009077164,0.00008286232,0.0002602843,0.9487665,0.006282614,0.03297825,0.005527514,0.00002212634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4378313,0.003653691,0.5300347,0.006784743,0.001079508,0.0001230048,0.002261683,0.002236509,0.01599495],"genre_scores_gemma":[0.9565568,0.000390271,0.03756712,0.0003959674,0.0003148881,0.00003374793,0.001382894,0.000105385,0.003252976],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002675013,"threshold_uncertainty_score":0.008809686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03658619565020053,"score_gpt":0.2907311869410829,"score_spread":0.2541449912908823,"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."}}