{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001721302,0.001509196,0.0006975606,0.00199517,0.0005825906,0.0009107565,0.001230132,0.001946218,0.003013011],"category_scores_gemma":[0.01355637,0.0004791942,0.001585667,0.002805996,0.000932887,0.002840655,0.001633808,0.002276695,0.002160752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008049292,"about_ca_system_score_gemma":0.0006293341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004169811,"about_ca_topic_score_gemma":0.00575705,"domain_scores_codex":[0.9984031,0.000483659,0.0001892599,0.000494993,0.0002996262,0.0001294322],"domain_scores_gemma":[0.9945506,0.002301591,0.0004096766,0.001601678,0.0008897723,0.0002466758],"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":[0.004929588,0.004723922,0.1492983,0.003726585,0.001807412,0.002587627,0.001391192,0.1489378,0.02119951,0.008817229,0.1635444,0.4890363],"study_design_scores_gemma":[0.0007912722,0.001722878,0.1137473,0.0003062318,0.0007004518,0.002962254,0.001449445,0.7125772,0.03714984,0.02473088,0.103429,0.0004332879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.7025136,0.00268575,0.1056889,0.002328635,0.001063338,0.001607489,0.1718067,0.005127406,0.007178213],"genre_scores_gemma":[0.6120481,0.0008511355,0.1144703,0.0005163882,0.0002720427,0.001706808,0.2655337,0.0002567382,0.004344705],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.004169811,"threshold_uncertainty_score":0.01007956,"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."}}