{"id":"W4410320589","doi":"10.1080/15456870.2025.2501798","title":"Leveraging natural language processing (NLP) to understand media framing of Lyme disease","year":2025,"lang":"en","type":"article","venue":"Atlantic Journal of Communication","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Framing (construction); Natural language processing; Artificial intelligence; Computer science; Lyme disease; Linguistics; Medicine; History; Virology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008614248,0.00004415512,0.0001113678,0.000166479,0.0002095177,0.00007389655,0.0003460543,0.00002402524,0.0000203736],"category_scores_gemma":[0.0009963155,0.00003855491,0.00003844362,0.0003031212,0.00006934172,0.0004138481,0.00004054397,0.0001321261,0.000001636983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008590816,"about_ca_system_score_gemma":0.0003683511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001843904,"about_ca_topic_score_gemma":0.0001187955,"domain_scores_codex":[0.9991404,0.0001300529,0.0003077952,0.00002955117,0.0002896397,0.0001024898],"domain_scores_gemma":[0.9990614,0.0002094878,0.0002760541,0.0001532956,0.0002088648,0.00009089737],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001569255,0.00009834021,0.00647411,0.0001344125,0.00006100041,0.000004046216,0.8225551,0.0002328962,0.0008562946,0.01895595,0.002295163,0.1481758],"study_design_scores_gemma":[0.002032073,0.00005799405,0.1806119,0.004774699,0.0002212849,0.0000095724,0.7874974,0.005548907,0.0009190324,0.008180765,0.00974696,0.0003994121],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9752902,0.00376614,0.006145455,0.006456064,0.0001324715,0.00009111995,4.980558e-7,0.00001166676,0.00810639],"genre_scores_gemma":[0.998317,0.0002534177,0.0009476623,0.0003424658,0.00002969829,9.478327e-8,0.000002483467,0.000002386017,0.0001047809],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1741378,"threshold_uncertainty_score":0.1611462,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02406323053999597,"score_gpt":0.3431404979892601,"score_spread":0.3190772674492641,"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."}}