{"id":"W4285540454","doi":"10.52458/978-93-91842-08-6-38","title":"Web Scraping Techniques and Applications: A Literature Review","year":2021,"lang":"en","type":"review","venue":"Soft Computing Research Society eBooks","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"Cégep de Chicoutimi; Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; World Wide Web; Web intelligence; Big data; Data science; Web mining; Web analytics; Web application; Analytics; Social media; Web standards; Web development; Web engineering; Web modeling; The Internet; Web page; Data mining","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005636099,0.0004778932,0.001711047,0.0002721169,0.0009693469,0.001493235,0.002332933,0.000401508,0.000002560131],"category_scores_gemma":[0.0002678318,0.0004070455,0.001016715,0.002103393,0.0002898014,0.000158527,0.003452264,0.002303989,0.00001518285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001691963,"about_ca_system_score_gemma":0.001127404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005702033,"about_ca_topic_score_gemma":5.556943e-7,"domain_scores_codex":[0.9949663,0.001028073,0.0007784807,0.00149605,0.0009389654,0.00079208],"domain_scores_gemma":[0.9953763,0.001521798,0.0003286768,0.00183605,0.0006976274,0.0002395755],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[4.546244e-8,0.00001290574,2.03901e-7,0.0458517,0.0001431128,0.0000301363,0.0001949213,1.914527e-8,4.180214e-7,0.001426457,0.013433,0.9389071],"study_design_scores_gemma":[0.00003414802,0.00001537174,1.712722e-8,0.2018708,0.000100301,0.0001573805,0.000018705,0.0005531427,8.731259e-7,0.0001396995,0.7968107,0.0002988942],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.50666e-8,0.9748182,0.021992,0.0001707925,0.00002929275,0.001051031,0.00002552821,0.0004335192,0.001479612],"genre_scores_gemma":[2.127265e-7,0.9466663,0.05105902,0.0002523531,0.0005465426,0.0003032565,0.0001303793,0.00004354031,0.0009984055],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9386082,"threshold_uncertainty_score":0.9999977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0854457235976239,"score_gpt":0.4236613379830667,"score_spread":0.3382156143854428,"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."}}