{"id":"W3087926002","doi":"10.1145/3415959.3416000","title":"Predicting Twitter Engagement With Deep Language Models","year":2020,"lang":"en","type":"article","venue":"","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Leverage (statistics); Language model; Benchmarking; Social media; World Wide Web; Task (project management); User engagement; Code (set theory); Data science; Deep learning; Information retrieval; Artificial intelligence","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":[0.000671963,0.001241333,0.0005777844,0.0009633362,0.0003464389,0.0008968432,0.0006999132,0.0009205341,0.003076324],"category_scores_gemma":[0.003467224,0.0004226974,0.0007188219,0.001059079,0.000243068,0.001542206,0.001055526,0.001646269,0.003474792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007219233,"about_ca_system_score_gemma":0.0006023963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01502399,"about_ca_topic_score_gemma":0.03668842,"domain_scores_codex":[0.9995821,0.0001403036,0.00002351335,0.0001062026,0.00005908832,0.00008878815],"domain_scores_gemma":[0.9992108,0.0004493422,0.00007409742,0.00008005563,0.0001149925,0.00007072306],"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":[0.001144805,0.001025137,0.07311536,0.0003122905,0.0003945325,0.000372076,0.0004902357,0.3719246,0.008997643,0.00487346,0.06072624,0.4766236],"study_design_scores_gemma":[0.00001739763,0.00004924478,0.00201895,0.00001515687,0.00001663595,0.00001820483,0.00005045707,0.9925915,0.0008323964,0.002408813,0.001970421,0.00001087375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6046605,0.004201791,0.3413282,0.005002579,0.0005363143,0.0002361422,0.01664219,0.0122444,0.01514783],"genre_scores_gemma":[0.9262987,0.0006592523,0.04294073,0.0004446538,0.0001946447,0.0001590415,0.01491369,0.0002174315,0.01417183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01502399,"threshold_uncertainty_score":0.02987307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04790758784266261,"score_gpt":0.2522579112034721,"score_spread":0.2043503233608095,"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."}}