{"id":"W2460077910","doi":"10.18653/v1/n16-1095","title":"Capturing Reliable Fine-Grained Sentiment Associations by Crowdsourcing and Best–Worst Scaling","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Crowdsourcing; Computer science; Sentiment analysis; Annotation; Natural language processing; Ranking (information retrieval); Artificial intelligence; Set (abstract data type); Association (psychology); Process (computing); Word (group theory); Arabic; Linguistics; Psychology; World Wide Web","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006721686,0.0003373515,0.0004641388,0.0002435397,0.0003688177,0.0009104935,0.0006854205,0.0002173627,0.00008688585],"category_scores_gemma":[0.0000554547,0.0002815764,0.0002088013,0.000214435,0.000031284,0.0002796449,0.001926451,0.0003080294,0.00005546262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000153385,"about_ca_system_score_gemma":0.00006714668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002609472,"about_ca_topic_score_gemma":0.00001539725,"domain_scores_codex":[0.9974725,0.00006640741,0.0005759509,0.0009333079,0.000491469,0.0004603449],"domain_scores_gemma":[0.9984331,0.00015996,0.0004123624,0.0007084495,0.0001221254,0.0001639609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003812652,0.002316137,0.1981733,0.001051071,0.008145961,0.0001253487,0.02396036,0.02316738,0.03375906,0.1277197,0.4721931,0.1093505],"study_design_scores_gemma":[0.00304178,0.0001177004,0.002715605,0.002879899,0.0006601042,0.00001413491,0.0006450716,0.903942,0.03259582,0.02377695,0.02540561,0.004205315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06942605,0.00193914,0.9049835,0.007694115,0.001411811,0.0004561307,0.00003965915,0.0004710953,0.01357854],"genre_scores_gemma":[0.8864235,0.0002461405,0.08456187,0.0004194522,0.0005406621,0.00006173449,0.0001532752,0.00006174031,0.02753162],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8807746,"threshold_uncertainty_score":0.9999636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01920080534226783,"score_gpt":0.2587092016159663,"score_spread":0.2395083962736985,"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."}}