{"id":"W2566371330","doi":"10.1109/dsaa.2016.80","title":"Word Segmentation Algorithms with Lexical Resources for Hashtag Classification","year":2016,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Segmentation; Precision and recall; Word (group theory); Text segmentation; Baseline (sea); Information retrieval; Linguistics","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":[0.001373909,0.001471765,0.001196377,0.007185319,0.001263318,0.002564524,0.001409357,0.001225691,0.005726749],"category_scores_gemma":[0.006277617,0.0006739335,0.0012469,0.005268281,0.0008284198,0.004584785,0.001544571,0.001575647,0.007012463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008989414,"about_ca_system_score_gemma":0.001606081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003475944,"about_ca_topic_score_gemma":0.005895203,"domain_scores_codex":[0.9982565,0.0003659273,0.0002625306,0.0004719696,0.0005104274,0.0001326972],"domain_scores_gemma":[0.9965897,0.001553998,0.0003451333,0.0004524611,0.0009310632,0.0001277539],"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":[0.0004453721,0.0003661503,0.00533215,0.0005226536,0.0002239947,0.0002986178,0.0006530464,0.007592435,0.07827613,0.0115421,0.01410208,0.8806452],"study_design_scores_gemma":[0.0002221632,0.0004398388,0.009915112,0.0002158458,0.0003184663,0.0009719821,0.001292034,0.7474822,0.1089924,0.07587354,0.05402921,0.0002471276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02914841,0.000610507,0.9519159,0.0002701647,0.0001494979,0.0006360661,0.001075837,0.01084179,0.005351744],"genre_scores_gemma":[0.1237605,0.0003102257,0.8682378,0.0002221804,0.0001503143,0.0007396504,0.003469083,0.0006655609,0.002444667],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007185319,"threshold_uncertainty_score":0.01915789,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04404161615383883,"score_gpt":0.2917415200383319,"score_spread":0.2476999038844931,"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."}}