{"id":"W2604928139","doi":"10.1007/978-3-319-56608-5_36","title":"Predicting Users’ Future Interests on Twitter","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of New Brunswick; Toronto Metropolitan University","funders":"","keywords":"Computer science; Microblogging; Set (abstract data type); Semantic space; Social media; Interval (graph theory); Space (punctuation); Data science; Information retrieval; World Wide Web; Artificial intelligence","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","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009728777,0.0006769678,0.0006493166,0.0008255415,0.000496539,0.001517445,0.00619492,0.0005086225,0.00001593591],"category_scores_gemma":[0.00005653323,0.0005589918,0.000199749,0.0001546457,0.0003817072,0.0008225905,0.001962845,0.001327218,0.00005936915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003057984,"about_ca_system_score_gemma":0.0002740787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005072242,"about_ca_topic_score_gemma":0.0001515166,"domain_scores_codex":[0.9958375,0.0000457653,0.0005695455,0.001832783,0.0009887289,0.0007256862],"domain_scores_gemma":[0.9957195,0.0002474135,0.0005742399,0.003072164,0.0001848535,0.0002018241],"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":[0.000007214255,0.00003592415,0.0008035009,0.00006716103,0.00002647033,0.0002472031,0.001790344,0.0003346576,0.00003926329,0.02331312,0.0007925731,0.9725426],"study_design_scores_gemma":[0.001452828,0.002220043,0.003476991,0.008947372,0.00003613477,0.0008169035,0.000002036225,0.3288725,0.007009407,0.4988995,0.1431369,0.005129272],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001574107,0.0002031715,0.9703345,0.002589468,0.006148562,0.000474707,0.000003722046,0.0004136576,0.01967481],"genre_scores_gemma":[0.6687192,0.0001191906,0.315624,0.006214768,0.006139981,0.0000465351,0.000007925541,0.0001370618,0.002991333],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9674133,"threshold_uncertainty_score":0.9996862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03321667847680321,"score_gpt":0.2793424075692406,"score_spread":0.2461257290924374,"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."}}