{"id":"W4416794611","doi":"10.1007/s10980-025-02269-9","title":"Image auto-coding tools for social impact assessment: leveraging social media data to understand human dimensions of hydroelectricity landscape changes in Canada","year":2025,"lang":"en","type":"article","venue":"Landscape Ecology","topic":"Sustainability and Climate Change Governance","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Social media; Hydroelectricity; Landscape ecology; Latent Dirichlet allocation; Set (abstract data type); Probabilistic logic; Tourism; Cloud computing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0005386231,0.0005806379,0.000208014,0.005482191,0.0008753138,0.001401863,0.0007121175,0.0003463489,0.002905157],"category_scores_gemma":[0.002925253,0.0002029446,0.0004154405,0.004140575,0.0005811091,0.0007705913,0.001110738,0.00063478,0.000733547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005377486,"about_ca_system_score_gemma":0.003973881,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.8279312,"about_ca_topic_score_gemma":0.9117681,"domain_scores_codex":[0.999532,0.0000503501,0.00001712648,0.00009199902,0.0002128202,0.00009568794],"domain_scores_gemma":[0.9982544,0.0004201416,0.000177076,0.0002011602,0.000825169,0.0001220477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004319777,0.0002906202,0.2819743,0.000732774,0.0002406704,0.001130727,0.008198106,0.03148101,0.0219259,0.006429825,0.05769916,0.5894649],"study_design_scores_gemma":[0.00004179488,0.00006201023,0.5846182,0.0003145536,0.0001362555,0.0002666542,0.01396405,0.2708066,0.02024374,0.006476196,0.1028747,0.0001952425],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8007343,0.0009091381,0.05682474,0.001759899,0.0001236505,0.0007306955,0.08592843,0.007899949,0.04508919],"genre_scores_gemma":[0.865671,0.000627308,0.09285907,0.000149396,0.0000518373,0.0003354378,0.03211654,0.0004302201,0.007759095],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1720688,"threshold_uncertainty_score":0.3461642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0546592539607385,"score_gpt":0.3285539447159361,"score_spread":0.2738946907551976,"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."}}