{"id":"W2620728056","doi":"10.48550/arxiv.1708.03994","title":"Data Sets: Word Embeddings Learned from Tweets and General Data","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":17,"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":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0004620021,0.0003423186,0.000404386,0.0001386718,0.0003018493,0.0006492474,0.01481385,0.0003068211,0.00002534052],"category_scores_gemma":[0.0001229481,0.0004037007,0.00005004491,0.0001093716,0.0001354294,0.001820501,0.0465611,0.0006960515,0.00004805985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007367237,"about_ca_system_score_gemma":0.000231496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00195429,"about_ca_topic_score_gemma":0.0002972713,"domain_scores_codex":[0.9961035,0.0001149252,0.0002134376,0.003051989,0.0001368706,0.0003792731],"domain_scores_gemma":[0.9864786,0.0001005402,0.000354731,0.01278245,0.00006690548,0.000216753],"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":[0.0003383743,0.0007333846,0.07926136,0.0008032719,0.003154235,0.008847963,0.005323185,0.2410844,0.000506694,0.1930364,0.0483668,0.4185439],"study_design_scores_gemma":[0.000379651,0.000006860894,0.00116039,0.00009502383,0.00007691708,0.000003613849,0.00002437537,0.9504558,0.000007447091,0.04103672,0.006318224,0.0004349741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3856756,0.0002723872,0.6104829,0.0005370302,0.0009007636,0.0001960189,0.0006932463,0.0002304485,0.0010116],"genre_scores_gemma":[0.9559717,0.0006202146,0.04066398,0.0001424255,0.0002743471,2.650409e-7,0.0009386326,0.0000244319,0.001364017],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7093714,"threshold_uncertainty_score":0.9998415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3216883880300847,"score_gpt":0.2625350096984135,"score_spread":0.05915337833167117,"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."}}