{"id":"W4390542458","doi":"10.1007/s13369-023-08567-1","title":"WASM: A Dataset for Hashtag Recommendation for Arabic Tweets","year":2024,"lang":"en","type":"article","venue":"Arabian Journal for Science and Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Social media; Information retrieval; Arabic; Task (project management); Categorization; Benchmark (surveying); Microblogging; Natural language processing; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.001624221,0.00009798219,0.0001024291,0.0002406606,0.0003713267,0.0008974692,0.000471933,0.000026252,0.000001283644],"category_scores_gemma":[0.000260193,0.00008652951,0.00004975027,0.0002806542,0.00002641495,0.001704228,0.00005810548,0.00009486068,0.000001135395],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006723596,"about_ca_system_score_gemma":0.0001351455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001029541,"about_ca_topic_score_gemma":9.216188e-7,"domain_scores_codex":[0.9989541,0.00000321577,0.0002062996,0.0003262629,0.0001463054,0.0003638445],"domain_scores_gemma":[0.9993835,0.0001641603,0.00003267551,0.0001560696,0.0001154674,0.000148146],"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":[0.00001917179,0.00002571633,0.00003279749,0.000563278,0.00004975542,0.000007270575,0.001723463,0.01864917,0.01952703,0.07496268,0.02379562,0.860644],"study_design_scores_gemma":[0.0001877418,0.00009352484,0.00002352985,0.00007221436,0.000007106715,0.00009491176,0.00001911715,0.8686222,0.0007018535,0.003268857,0.1267943,0.0001146331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006064832,0.0001939142,0.9878069,0.003559907,0.001953483,0.0002713408,0.00008709458,0.00005314354,0.000009374854],"genre_scores_gemma":[0.5227802,0.00005547886,0.4758949,0.000346057,0.0006414275,0.0001321318,0.00004805012,0.00002286527,0.00007888032],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8605294,"threshold_uncertainty_score":0.8654316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0375174136116534,"score_gpt":0.2986276063840521,"score_spread":0.2611101927723987,"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."}}