{"id":"W2963418282","doi":"10.1609/icwsm.v11i1.14859","title":"Data Sets: Word Embeddings Learned from Tweets and General Data","year":2017,"lang":"en","type":"article","venue":"Proceedings of the International AAAI Conference on Web and Social Media","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Computer science; Word (group theory); Word embedding; Natural language processing; Embedding; Artificial intelligence; Representation (politics); Information retrieval; Sentiment analysis; 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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003792594,0.0001345886,0.0001765931,0.00004939505,0.0003307525,0.0009417763,0.007240063,0.00008810102,0.00001189517],"category_scores_gemma":[0.0010264,0.00009931609,0.00001864165,0.00003803238,0.0002687686,0.001512336,0.00567853,0.0002478412,0.000001447108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001723664,"about_ca_system_score_gemma":0.00007313061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008514978,"about_ca_topic_score_gemma":0.00005380576,"domain_scores_codex":[0.9986637,0.000006990114,0.0001840552,0.0005328301,0.000471462,0.0001409267],"domain_scores_gemma":[0.9987637,0.00008944015,0.0003703707,0.0004888236,0.0002399606,0.00004771719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009582406,0.00008992939,0.008227023,0.00005763537,0.0001463558,0.000004548939,0.006359296,2.279602e-8,0.03625446,0.4358041,0.01297454,0.4999862],"study_design_scores_gemma":[0.00154862,0.00006367974,0.02530663,0.0007666933,0.00007955638,0.00001958491,0.0008593707,0.08778743,0.01523938,0.854622,0.01286264,0.0008443758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9401365,0.0003578514,0.0003235101,0.05380139,0.0009733058,0.0001830445,0.0006902722,0.0001572293,0.00337689],"genre_scores_gemma":[0.9691657,0.000161343,0.02987004,0.0003261285,0.000317174,0.00000370365,0.00004309318,0.000007539609,0.0001052724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4991419,"threshold_uncertainty_score":0.9981312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1245390394014516,"score_gpt":0.3492956645279873,"score_spread":0.2247566251265358,"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."}}