{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03545424,0.0002658956,0.001526809,0.001516817,0.0004681767,0.0003489806,0.0003531235,0.00009633624,0.00005591339],"category_scores_gemma":[0.03066076,0.0002295534,0.0005683382,0.006665451,0.0001880944,0.0006358367,0.0001238015,0.0004282615,0.0000062013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001653685,"about_ca_system_score_gemma":0.0001714735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000964961,"about_ca_topic_score_gemma":0.001496107,"domain_scores_codex":[0.9914189,0.004356832,0.002142523,0.0003093112,0.001318188,0.0004542715],"domain_scores_gemma":[0.9889933,0.006442833,0.003046283,0.0002844591,0.0009979554,0.0002351608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004984296,0.0004147274,0.9122661,0.0003349549,0.007334146,0.00003418772,0.05090863,0.006579479,0.00003603233,0.000008576985,0.0004470268,0.02113776],"study_design_scores_gemma":[0.0005098655,0.0001266529,0.910608,0.0005956126,0.01252541,0.000001707569,0.04804597,0.02686915,0.000002620144,0.00008482951,0.0003173733,0.0003128211],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969112,0.0003812071,0.0001522714,0.000357723,0.0002251778,0.0004825494,0.00001137076,0.00004446179,0.001434089],"genre_scores_gemma":[0.9981409,0.001016982,0.0004307514,0.00001661905,0.0002195253,0.000005791924,0.00001561755,0.00001139337,0.000142435],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02082494,"threshold_uncertainty_score":0.9932029,"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."}}