{"id":"W3093354771","doi":"10.1007/s42803-021-00032-5","title":"‘Go fish’: Conceptualising the challenges of engaging national web archives for digital research","year":2021,"lang":"en","type":"article","venue":"International Journal of Digital Humanities","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"ESRC National Centre for Research Methods, University of Southampton; Economic and Social Research Council; UK Research and Innovation; Social Sciences and Humanities Research Council of Canada; University of Southampton; Aarhus Universitet","keywords":"World Wide Web; Context (archaeology); Scholarship; Web 2.0; Sociology; Computer science; Web service; Political science; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.08378688,0.0009108086,0.001270259,0.008421606,0.02237589,0.04424956,0.006716185,0.008666505,0.00668998],"category_scores_gemma":[0.09588349,0.00175786,0.001176391,0.009688541,0.09166215,0.05077924,0.02988676,0.007167945,0.001038097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01524607,"about_ca_system_score_gemma":0.01900791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01390197,"about_ca_topic_score_gemma":0.01888919,"domain_scores_codex":[0.9093851,0.07753874,0.002106374,0.003085508,0.005136139,0.002748198],"domain_scores_gemma":[0.8664426,0.1057747,0.00503887,0.01406581,0.00531918,0.003358654],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0000477894,0.00002785459,0.002975103,0.0003312873,0.00001967722,0.0006777265,0.6380785,0.0004327391,0.0003472937,0.3441089,0.001184415,0.01176873],"study_design_scores_gemma":[0.00001275971,0.00004178506,0.001316655,0.00113964,0.00003227258,0.0006615774,0.6992952,0.001608299,0.0004374015,0.1957452,0.09965959,0.00004965331],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4135157,0.008139187,0.2432312,0.09445807,0.0006548904,0.0008576933,0.0003836341,0.0005994735,0.23816],"genre_scores_gemma":[0.9404721,0.001327437,0.05100758,0.001570036,0.00005529952,0.0006752677,0.00009734882,0.000244656,0.004550186],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9557505,"threshold_uncertainty_score":0.4431127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1845535825460962,"score_gpt":0.3625338833797037,"score_spread":0.1779803008336076,"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."}}