{"id":"W3022552813","doi":"10.1007/978-3-030-46133-1_22","title":"Augmenting Semantic Representation of Depressive Language: From Forums to Microblogs","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Mental Health via Writing","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Word embedding; Computer science; Natural language processing; Artificial intelligence; Word (group theory); Embedding; Lexicon; Word2vec; Representation (politics); Domain (mathematical analysis); Semantics (computer science); Microblogging; Feature (linguistics); Distributional semantics; Task (project management); Social media; Semantic similarity; Linguistics; World Wide Web","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"],"consensus_categories":[],"category_scores_codex":[0.0002692309,0.0002669822,0.0004564358,0.0003230088,0.0001054022,0.00005507418,0.0007588207,0.0001968105,0.0002158762],"category_scores_gemma":[0.0001164168,0.0002762578,0.00007859535,0.0003247375,0.0001976112,0.00008748431,0.0005783513,0.0004631042,0.0001165958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001295637,"about_ca_system_score_gemma":0.00008753447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006322835,"about_ca_topic_score_gemma":0.0001543792,"domain_scores_codex":[0.9974385,0.0000521063,0.0005799233,0.001061574,0.0004354283,0.0004324386],"domain_scores_gemma":[0.9981925,0.0005606837,0.0004020117,0.000617728,0.00008174579,0.0001452779],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009812128,0.0000588074,0.003632314,0.0002575062,0.00006803063,0.000398931,0.02813238,0.002706549,0.02616131,0.002063646,0.0002959452,0.9361265],"study_design_scores_gemma":[0.01022562,0.003342952,0.04120606,0.02179673,0.0005355416,0.0005460728,0.0004606983,0.1075863,0.5148216,0.2889757,0.00252114,0.00798158],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02751367,0.0008225014,0.958758,0.0009102173,0.002004864,0.0009826877,0.00005210879,0.00007723705,0.008878728],"genre_scores_gemma":[0.9015462,0.000004261254,0.09392333,0.003321924,0.0006273222,0.00001802411,0.0000442174,0.00005115775,0.0004635676],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9281449,"threshold_uncertainty_score":0.9999689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03018310649340961,"score_gpt":0.3443944671188567,"score_spread":0.3142113606254471,"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."}}