{"id":"W3037984866","doi":"10.22215/etd/2020-14060","title":"Using Data Analysis and Machine Learning for Studying and Predicting Depression in Users on Social Media","year":2020,"lang":"en","type":"dissertation","venue":"","topic":"Mental Health via Writing","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Word2vec; Computer science; Social media; Recall; Machine learning; Support vector machine; Artificial intelligence; Precision and recall; Classifier (UML); Feature engineering; Gradient boosting; Vocabulary; World Wide Web; Data science; Deep learning; Psychology; Cognitive psychology","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":[0.006198055,0.0007354005,0.0007045097,0.003537279,0.0006167867,0.002814129,0.0004625052,0.0008306836,0.001503504],"category_scores_gemma":[0.02987895,0.0002488967,0.001287551,0.003341814,0.0005022264,0.001524368,0.0009559286,0.002051387,0.0008183939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005332301,"about_ca_system_score_gemma":0.000847495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003071653,"about_ca_topic_score_gemma":0.003916957,"domain_scores_codex":[0.9964999,0.002121642,0.0003098428,0.0003206352,0.0006015815,0.0001463814],"domain_scores_gemma":[0.9728304,0.0237167,0.001148924,0.0007017285,0.001158025,0.0004442332],"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":[0.0004072842,0.0012602,0.4113634,0.0004980005,0.000920933,0.0001423816,0.001458226,0.004592067,0.002396318,0.001593031,0.01056933,0.5647989],"study_design_scores_gemma":[0.0001732641,0.002471253,0.6281493,0.001788554,0.001111432,0.0008323553,0.008601455,0.2836849,0.01022546,0.03881641,0.02374299,0.0004026906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8274993,0.01067434,0.1232632,0.01818057,0.0008462713,0.001206889,0.005852605,0.0008907312,0.01158601],"genre_scores_gemma":[0.8597773,0.00450237,0.1290936,0.0008980332,0.0005152126,0.0006898565,0.002491028,0.00007811185,0.001954458],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006198055,"threshold_uncertainty_score":0.0327788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2517543259711265,"score_gpt":0.475825720619203,"score_spread":0.2240713946480766,"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."}}