{"id":"W2401224426","doi":"10.1609/icwsm.v5i1.14198","title":"Supervised Topic Segmentation of Email Conversations","year":2021,"lang":"en","type":"article","venue":"Proceedings of the International AAAI Conference on Web and Social Media","topic":"Personal Information Management and User Behavior","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Exploit; Segmentation; Conversation; Artificial intelligence; Natural language processing; Market segmentation; Graph; Information retrieval; Machine learning; Linguistics","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":[0.001583773,0.00108207,0.001159151,0.002548996,0.0008052668,0.001445761,0.001572711,0.001658383,0.001461379],"category_scores_gemma":[0.004863947,0.000541931,0.001517881,0.001410917,0.0006541356,0.002494463,0.001224582,0.001380225,0.00126988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001059616,"about_ca_system_score_gemma":0.001184918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005388842,"about_ca_topic_score_gemma":0.006500117,"domain_scores_codex":[0.9983961,0.0006917837,0.00007553824,0.0004701052,0.0002015569,0.0001649373],"domain_scores_gemma":[0.9970631,0.001771307,0.0003162136,0.0002523256,0.000440241,0.0001568457],"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":[0.001779891,0.0008288716,0.02169503,0.000678905,0.000469292,0.0005305668,0.003991657,0.3462257,0.04317012,0.03449206,0.01281668,0.5333213],"study_design_scores_gemma":[0.00001322073,0.00004501106,0.002200192,0.00001624249,0.00003967665,0.00007250322,0.0001367573,0.9810239,0.0028901,0.01191496,0.00162592,0.00002153143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09587907,0.0009297162,0.8967617,0.0004279305,0.00007515007,0.0001612105,0.0005434988,0.002166257,0.003055452],"genre_scores_gemma":[0.848406,0.000357967,0.1453098,0.0001911221,0.000221408,0.0002807977,0.001698204,0.000265547,0.00326917],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005388842,"threshold_uncertainty_score":0.01071501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2328588741157706,"score_gpt":0.3850110770473913,"score_spread":0.1521522029316208,"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."}}