{"id":"W4362723067","doi":"10.1057/s41270-023-00218-6","title":"Extracting marketing information from product reviews: a comparative study of latent semantic analysis and probabilistic latent semantic analysis","year":2023,"lang":"en","type":"article","venue":"Journal of Marketing Analytics","topic":"Digital Marketing and Social Media","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Probabilistic latent semantic analysis; Computer science; Latent semantic analysis; Automatic summarization; Latent Dirichlet allocation; Leverage (statistics); Product (mathematics); Information retrieval; Data science; Topic model; Probabilistic logic; Semantic analysis (machine learning); New product development; Data mining; Artificial intelligence; Marketing; Business","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005096904,0.001066054,0.001324814,0.01381209,0.0006696749,0.004203318,0.0008794596,0.001042011,0.001037649],"category_scores_gemma":[0.02886183,0.0003766812,0.001859784,0.01225861,0.0006596005,0.007128006,0.001344039,0.001090379,0.0008866024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008379862,"about_ca_system_score_gemma":0.001953624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003667305,"about_ca_topic_score_gemma":0.006077315,"domain_scores_codex":[0.994837,0.002177617,0.0005488679,0.000647478,0.001553694,0.0002353294],"domain_scores_gemma":[0.9674773,0.02583946,0.00221198,0.0009089998,0.003302749,0.0002594298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007800642,0.0008717129,0.04721957,0.001962023,0.0007710975,0.0001950888,0.002123408,0.007194764,0.007929751,0.008908196,0.004807947,0.9172363],"study_design_scores_gemma":[0.000159395,0.0007712931,0.147454,0.0007191029,0.001952594,0.001104626,0.005915926,0.752651,0.01332148,0.05525916,0.02030822,0.0003831765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3515715,0.01544494,0.6154885,0.002070277,0.0002254534,0.0004955087,0.003540063,0.001832194,0.009331618],"genre_scores_gemma":[0.7974762,0.005255415,0.1898282,0.0001424732,0.0003590404,0.0002075356,0.005320489,0.0001949691,0.001215517],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01381209,"threshold_uncertainty_score":0.02695531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05342708161358858,"score_gpt":0.3336452052220688,"score_spread":0.2802181236084802,"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."}}