{"id":"W2903565856","doi":"","title":"Text Mining Methods for Social Representation Analysis in Large Corpora","year":2011,"lang":"en","type":"article","venue":"Papers on Social Representations","topic":"Social Media and Politics","field":"Social Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Data science; Representation (politics); Software; Digitization; Sentiment analysis; Information retrieval; Natural language processing","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.000936891,0.0001443264,0.0003614323,0.0003680836,0.001595998,0.00006552105,0.0002344265,0.000235099,0.0005229141],"category_scores_gemma":[0.002009735,0.0001714748,0.000409683,0.002038671,0.0003215464,0.000172592,0.00003030622,0.0001588398,0.0000164453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001988101,"about_ca_system_score_gemma":0.0002033354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004045708,"about_ca_topic_score_gemma":0.004195302,"domain_scores_codex":[0.9972626,0.000987513,0.0004127805,0.0003863706,0.0003777816,0.0005729626],"domain_scores_gemma":[0.9978163,0.001490314,0.0002422309,0.0001408653,0.0001806257,0.0001296606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00009140129,0.0002925575,0.1394558,0.000008092808,0.0003691009,0.000004071123,0.6010193,0.000004207901,0.000282485,0.2236213,0.001846569,0.0330051],"study_design_scores_gemma":[0.001245009,0.0000442999,0.445699,0.000006220021,0.0006832908,1.141132e-7,0.5120115,0.0001042166,0.0003701764,0.01834935,0.02106647,0.0004204116],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5632579,0.00004914291,0.005691329,0.004439324,0.001350216,0.001644476,0.0001675922,0.000258328,0.4231417],"genre_scores_gemma":[0.9865348,0.00002622835,0.01031733,0.0004424118,0.0008036,0.0003318114,0.00008597338,0.0000237656,0.001434087],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4232768,"threshold_uncertainty_score":0.9997038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2188205082425999,"score_gpt":0.5047090357421659,"score_spread":0.2858885274995659,"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."}}