{"id":"W3156008792","doi":"10.1109/access.2021.3071620","title":"Geo-Spatial Market Segmentation & Characterization Exploiting User Generated Text Through Transformers & Density-Based Clustering","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Universidad ICESI","keywords":"Computer science; Cluster analysis; Encoder; Workflow; Information retrieval; Data mining; Market segmentation; Artificial intelligence; Database","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006208241,0.0001630982,0.000216218,0.00009555162,0.001004071,0.000554487,0.0002334619,0.0001354019,0.002771009],"category_scores_gemma":[0.000141785,0.0001869946,0.0001201032,0.0007603197,0.0001135614,0.001090732,0.00001960183,0.0001426398,0.00005600063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002087321,"about_ca_system_score_gemma":0.0003847112,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01266512,"about_ca_topic_score_gemma":0.1649991,"domain_scores_codex":[0.9978513,0.0005291888,0.0003923868,0.0004161665,0.0004735817,0.0003373914],"domain_scores_gemma":[0.9989765,0.000146815,0.0001680025,0.0002184737,0.0003939632,0.00009625548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003878636,0.0009669476,0.08013397,0.0006007224,0.0005033602,0.00003620595,0.07103349,0.03921842,0.5985171,0.0002482523,0.001838299,0.2065154],"study_design_scores_gemma":[0.00696454,0.0001020731,0.1567045,0.0008410221,0.001426371,0.000007871533,0.01786039,0.116204,0.4859347,0.00104078,0.2082552,0.004658619],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5254687,0.000007306369,0.4726385,0.000643053,0.0002559868,0.0001667788,0.00001508513,0.00007150475,0.0007330982],"genre_scores_gemma":[0.9949023,0.00006684225,0.001173084,0.001197754,0.0003785978,0.00006205302,0.0009249493,0.00002169948,0.001272737],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4714654,"threshold_uncertainty_score":0.9981406,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05937569007575529,"score_gpt":0.3448376364518129,"score_spread":0.2854619463760576,"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."}}