{"id":"W2018222148","doi":"10.1145/1860559.1860615","title":"Structure-aware topic clustering in social media","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Conversation; Meaning (existential); Social media; Variety (cybernetics); Set (abstract data type); Cluster analysis; Software; Data science; World Wide Web; Scale (ratio); Artificial intelligence; Sociology; Communication; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000688306,0.00007510309,0.0001113114,0.0001150197,0.00004925687,0.00005185726,0.0005846519,0.00006854413,0.00008992341],"category_scores_gemma":[0.00003042035,0.00006600656,0.00003242186,0.0002830853,0.00002304837,0.0003211862,0.0002456116,0.0002142709,0.000005986108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001837476,"about_ca_system_score_gemma":0.00001521351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000168205,"about_ca_topic_score_gemma":0.003991205,"domain_scores_codex":[0.9993488,0.00001297639,0.0001331464,0.0002090587,0.0001336405,0.0001623585],"domain_scores_gemma":[0.9996049,0.00004274544,0.00003252838,0.000264352,0.00002561311,0.00002981483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002837733,0.00004599922,0.007842816,0.00001435996,0.00001351654,0.000042601,0.003539555,0.00004533237,0.06990242,0.3548707,0.0009545698,0.5627252],"study_design_scores_gemma":[0.0009713568,0.0000403193,0.113337,0.00001803091,0.00001160898,0.00003300636,0.0001875922,0.1713791,0.1420355,0.5618187,0.008912696,0.001255111],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09706293,0.00000329882,0.8993022,0.0004809094,0.0002295121,0.00005172607,5.153556e-7,0.0003352316,0.002533668],"genre_scores_gemma":[0.8611577,6.536901e-7,0.138538,0.0001222452,0.0001073351,0.00000299119,8.889387e-7,0.000003575198,0.00006661679],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7640947,"threshold_uncertainty_score":0.2691669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01119701689460568,"score_gpt":0.2779358857674432,"score_spread":0.2667388688728375,"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."}}