{"id":"W2397944984","doi":"10.2200/s00659ed1v01y201508hlt030","title":"Natural Language Processing for Social Media","year":2015,"lang":"en","type":"article","venue":"Synthesis lectures on human language technologies","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"University of Ottawa; University of Toronto; University of Southern California","keywords":"Social media; Interpersonal communication; Natural (archaeology); Computer science; Internet privacy; Data science; Psychology; Sociology; Linguistics; World Wide Web; Communication; History","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003203245,0.0002205772,0.0002943723,0.0003770926,0.0003069683,0.0002705415,0.001155757,0.0001559792,0.00001377347],"category_scores_gemma":[0.001169602,0.0001689334,0.0001454637,0.0003754821,0.000110921,0.000197499,0.0001978948,0.0002011265,0.00001571293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000067755,"about_ca_system_score_gemma":0.00003379262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007557471,"about_ca_topic_score_gemma":0.00004255518,"domain_scores_codex":[0.9985822,0.00004231586,0.0002128599,0.0004440436,0.0003503982,0.0003681549],"domain_scores_gemma":[0.9990211,0.0003019625,0.000149697,0.0004240236,0.00006984056,0.00003338945],"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":[0.00002200352,0.00007730637,0.00005157822,0.00003754577,0.00007610423,0.00003321381,0.02375674,0.00001656626,0.01201379,0.01333741,0.008609584,0.9419681],"study_design_scores_gemma":[0.001841053,0.0003324368,0.001034182,0.0002898349,0.0001822635,0.00002469756,0.09663545,0.01677491,0.8585749,0.01634307,0.005783231,0.002183927],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8772029,0.03234254,0.0579953,0.009902894,0.001231867,0.001150233,0.00003640198,0.01410414,0.006033726],"genre_scores_gemma":[0.9888109,0.000002285601,0.01065213,0.0001267973,0.0001621905,0.000115181,0.000009968336,0.00001871775,0.0001018321],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9397842,"threshold_uncertainty_score":0.6888906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05859163540961687,"score_gpt":0.3354402399822846,"score_spread":0.2768486045726677,"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."}}