{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001601268,0.0000645037,0.00007380788,0.00006819786,0.00008895484,0.0001099177,0.000215711,0.00002343783,0.00004926749],"category_scores_gemma":[0.000008559537,0.00003415419,0.00003925062,0.0001662888,0.00002342425,0.000340768,0.00002707667,0.0000148993,0.00003084132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002058145,"about_ca_system_score_gemma":0.00001304005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003312476,"about_ca_topic_score_gemma":0.000004783836,"domain_scores_codex":[0.9992901,0.00001897718,0.000134202,0.0002540594,0.0001772185,0.0001254235],"domain_scores_gemma":[0.9995303,0.0000961421,0.00006932062,0.000201061,0.00005999359,0.00004317987],"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":[0.00002814934,0.00006134152,0.005446344,0.000004224843,0.00005330655,5.60708e-7,0.0004877536,0.000009696333,0.0122467,0.05099787,0.004299228,0.9263648],"study_design_scores_gemma":[0.007070643,0.001024225,0.09512535,0.0002109538,0.0001103123,0.00001321425,0.001846592,0.6552747,0.0844839,0.006200003,0.1473237,0.00131647],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01512746,0.00001271316,0.980041,0.003709896,0.00006251784,0.0001066901,6.758161e-7,0.00007474126,0.0008643636],"genre_scores_gemma":[0.4977688,0.00001035582,0.495191,0.000296666,0.0001491507,0.00006376852,0.000006374767,0.000008134795,0.006505742],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9250484,"threshold_uncertainty_score":0.1392767,"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."}}