{"id":"W2925086903","doi":"10.22215/etd/2017-11995","title":"Statistical Analysis of Classification Algorithms for Predicting Socioeconomics Status of Twitter Users","year":2017,"lang":"en","type":"dissertation","venue":"","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Support vector machine; Naive Bayes classifier; Decision tree; Computer science; Machine learning; Artificial intelligence; Statistical classification; Algorithm; Data mining","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":[0.008387101,0.0009307395,0.0009446151,0.004489115,0.000467881,0.001206889,0.0006520495,0.0008770073,0.0007118997],"category_scores_gemma":[0.03393367,0.0001782358,0.0008725671,0.002703973,0.0003789315,0.001665084,0.0004973491,0.0008699309,0.0004610158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006004179,"about_ca_system_score_gemma":0.0007460727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001684243,"about_ca_topic_score_gemma":0.001194904,"domain_scores_codex":[0.9955355,0.001950829,0.0005000941,0.0005230703,0.001273977,0.0002165294],"domain_scores_gemma":[0.9598236,0.03196454,0.002625386,0.001548037,0.003811126,0.0002272828],"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":[0.0009128372,0.0009025435,0.3339696,0.0003979287,0.001051774,0.0001698022,0.0002952421,0.1531473,0.004219401,0.003700904,0.004261399,0.4969712],"study_design_scores_gemma":[0.00002748311,0.0005054232,0.0860858,0.00006215781,0.0001425717,0.0002112649,0.0003269997,0.9034411,0.004150941,0.003880227,0.001120547,0.00004547025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7258628,0.002466373,0.2628824,0.001081871,0.0002212687,0.0003002727,0.001811347,0.001334665,0.004039008],"genre_scores_gemma":[0.9338267,0.0005337425,0.06298596,0.00008824847,0.0001376473,0.0002209527,0.001669455,0.00004514708,0.0004921932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008387101,"threshold_uncertainty_score":0.04435575,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05587029747400021,"score_gpt":0.340885170468379,"score_spread":0.2850148729943788,"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."}}