{"id":"W2161926933","doi":"","title":"When Specialists and Generalists Work Together: Overcoming Domain Dependence in Sentiment Tagging","year":2008,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":165,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Software portability; Computer science; Lexicon; WordNet; Classifier (UML); Artificial intelligence; Annotation; Natural language processing; Domain (mathematical analysis); Weighting; Sentiment analysis; Precision and recall; Training set; Information retrieval; Machine learning","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":[0.02769392,0.001072511,0.001452278,0.002653231,0.003135177,0.003791571,0.001828966,0.00226803,0.001544212],"category_scores_gemma":[0.06544276,0.00134934,0.000558907,0.002377756,0.001936355,0.01160647,0.005958196,0.002943568,0.001579573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001379257,"about_ca_system_score_gemma":0.001770449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004898302,"about_ca_topic_score_gemma":0.008711512,"domain_scores_codex":[0.9816595,0.009872016,0.0009905916,0.004459599,0.00218264,0.0008356997],"domain_scores_gemma":[0.938006,0.04112229,0.004731069,0.007109711,0.007329383,0.001701615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002550084,0.0004662247,0.1921034,0.0006986744,0.0003789397,0.00180399,0.03173734,0.005962857,0.05361289,0.005449903,0.01673001,0.6885058],"study_design_scores_gemma":[0.0004517911,0.001507519,0.2427695,0.0006436647,0.001206253,0.005366868,0.0443457,0.4564839,0.07398529,0.09377737,0.07884892,0.0006130913],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6405157,0.001013668,0.3263978,0.004118028,0.0005961139,0.0006499055,0.000556861,0.002284439,0.02386751],"genre_scores_gemma":[0.9310318,0.0002158095,0.0626994,0.0014106,0.0002909647,0.0001936798,0.0007507794,0.0004464383,0.002960481],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02769392,"threshold_uncertainty_score":0.1464611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02636169918772258,"score_gpt":0.2488749297044931,"score_spread":0.2225132305167705,"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."}}